Compare commits

..

2 Commits

Author SHA1 Message Date
ntohidi
2b3b728dcd fix(metadata): improve title extraction with fallbacks for edge cases. REF #995
Some pages include a <title> tag in HTML but lxml fails to parse it due to unusual structure.
Added fallback logic using .find() and OpenGraph/Twitter meta tags to ensure reliable title extraction.
2025-05-28 10:17:50 +02:00
ntohidi
bfec5156ad Refactor content scraping strategies: comment out WebScrapingStrategy references and update to use LXMLWebScrapingStrategy across multiple files. Bring WebScrapingStrategy methods to LXMLWebScrapingStrategy 2025-05-27 17:32:45 +02:00
216 changed files with 102633 additions and 84810 deletions

View File

@@ -1,28 +0,0 @@
{
"permissions": {
"allow": [
"Bash(cd:*)",
"Bash(python3:*)",
"Bash(python:*)",
"Bash(grep:*)",
"Bash(mkdir:*)",
"Bash(cp:*)",
"Bash(rm:*)",
"Bash(true)",
"Bash(./package-extension.sh:*)",
"Bash(find:*)",
"Bash(chmod:*)",
"Bash(rg:*)",
"Bash(/Users/unclecode/.npm-global/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-darwin/rg -A 5 -B 5 \"Script Builder\" docs/md_v2/apps/crawl4ai-assistant/)",
"Bash(/Users/unclecode/.npm-global/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-darwin/rg -A 30 \"generateCode\\(events, format\\)\" docs/md_v2/apps/crawl4ai-assistant/content/content.js)",
"Bash(/Users/unclecode/.npm-global/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-darwin/rg \"<style>\" docs/md_v2/apps/crawl4ai-assistant/index.html -A 5)",
"Bash(git checkout:*)",
"Bash(docker logs:*)",
"Bash(curl:*)",
"Bash(docker compose:*)",
"Bash(./test-final-integration.sh:*)",
"Bash(mv:*)"
]
},
"enableAllProjectMcpServers": false
}

View File

@@ -5,42 +5,6 @@ All notable changes to Crawl4AI will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
### Added
- **AsyncUrlSeeder**: High-performance URL discovery system for intelligent crawling at scale
- Discover URLs from sitemaps and Common Crawl index
- Extract and analyze page metadata without full crawling
- BM25 relevance scoring for query-based URL filtering
- Multi-domain parallel discovery with `many_urls()` method
- Automatic caching with TTL for discovered URLs
- Rate limiting and concurrent request management
- Live URL validation with HEAD requests
- JSON-LD and Open Graph metadata extraction
- **SeedingConfig**: Configuration class for URL seeding operations
- Support for multiple discovery sources (`sitemap`, `cc`, `sitemap+cc`)
- Pattern-based URL filtering with wildcards
- Configurable concurrency and rate limiting
- Query-based relevance scoring with BM25
- Score threshold filtering for quality control
- Comprehensive documentation for URL seeding feature
- Detailed comparison with deep crawling approaches
- Complete API reference with examples
- Integration guide with AsyncWebCrawler
- Performance benchmarks and best practices
- Example scripts demonstrating URL seeding:
- `url_seeder_demo.py`: Interactive Rich-based demonstration
- `url_seeder_quick_demo.py`: Screenshot-friendly examples
- Test suite for URL seeding with BM25 scoring
### Changed
- Updated `__init__.py` to export AsyncUrlSeeder and SeedingConfig
- Enhanced documentation with URL seeding integration examples
### Fixed
- Corrected examples to properly extract URLs from seeder results before passing to `arun_many()`
- Fixed logger color compatibility issue (changed `lightblack` to `bright_black`)
## [0.6.2] - 2025-05-02
### Added

View File

@@ -2,12 +2,11 @@
import warnings
from .async_webcrawler import AsyncWebCrawler, CacheMode
# MODIFIED: Add SeedingConfig here
from .async_configs import BrowserConfig, CrawlerRunConfig, HTTPCrawlerConfig, LLMConfig, ProxyConfig, GeolocationConfig, SeedingConfig
from .async_configs import BrowserConfig, CrawlerRunConfig, HTTPCrawlerConfig, LLMConfig, ProxyConfig, GeolocationConfig
from .content_scraping_strategy import (
ContentScrapingStrategy,
WebScrapingStrategy,
# WebScrapingStrategy,
LXMLWebScrapingStrategy,
)
from .async_logger import (
@@ -66,18 +65,6 @@ from .deep_crawling import (
DFSDeepCrawlStrategy,
DeepCrawlDecorator,
)
# NEW: Import AsyncUrlSeeder
from .async_url_seeder import AsyncUrlSeeder
# C4A Script Language Support
from .script import (
compile as c4a_compile,
validate as c4a_validate,
compile_file as c4a_compile_file,
CompilationResult,
ValidationResult,
ErrorDetail
)
from .utils import (
start_colab_display_server,
@@ -91,10 +78,6 @@ __all__ = [
"BrowserProfiler",
"LLMConfig",
"GeolocationConfig",
# NEW: Add SeedingConfig
"SeedingConfig",
# NEW: Add AsyncUrlSeeder
"AsyncUrlSeeder",
"DeepCrawlStrategy",
"BFSDeepCrawlStrategy",
"BestFirstCrawlingStrategy",
@@ -117,7 +100,7 @@ __all__ = [
"CrawlerHub",
"CacheMode",
"ContentScrapingStrategy",
"WebScrapingStrategy",
# "WebScrapingStrategy",
"LXMLWebScrapingStrategy",
"BrowserConfig",
"CrawlerRunConfig",
@@ -149,13 +132,6 @@ __all__ = [
"ProxyConfig",
"start_colab_display_server",
"setup_colab_environment",
# C4A Script additions
"c4a_compile",
"c4a_validate",
"c4a_compile_file",
"CompilationResult",
"ValidationResult",
"ErrorDetail",
]
@@ -184,4 +160,4 @@ __all__ = [
# Disable all Pydantic warnings
warnings.filterwarnings("ignore", module="pydantic")
# pydantic_warnings.filter_warnings()
# pydantic_warnings.filter_warnings()

View File

@@ -17,7 +17,7 @@ from .extraction_strategy import ExtractionStrategy, LLMExtractionStrategy
from .chunking_strategy import ChunkingStrategy, RegexChunking
from .markdown_generation_strategy import MarkdownGenerationStrategy, DefaultMarkdownGenerator
from .content_scraping_strategy import ContentScrapingStrategy, WebScrapingStrategy
from .content_scraping_strategy import ContentScrapingStrategy, LXMLWebScrapingStrategy
from .deep_crawling import DeepCrawlStrategy
from .cache_context import CacheMode
@@ -207,6 +207,7 @@ class GeolocationConfig:
config_dict.update(kwargs)
return GeolocationConfig.from_dict(config_dict)
class ProxyConfig:
def __init__(
self,
@@ -317,6 +318,8 @@ class ProxyConfig:
config_dict.update(kwargs)
return ProxyConfig.from_dict(config_dict)
class BrowserConfig:
"""
Configuration class for setting up a browser instance and its context in AsyncPlaywrightCrawlerStrategy.
@@ -594,6 +597,7 @@ class BrowserConfig:
return config
return BrowserConfig.from_kwargs(config)
class HTTPCrawlerConfig:
"""HTTP-specific crawler configuration"""
@@ -721,7 +725,7 @@ class CrawlerRunConfig():
parser_type (str): Type of parser to use for HTML parsing.
Default: "lxml".
scraping_strategy (ContentScrapingStrategy): Scraping strategy to use.
Default: WebScrapingStrategy.
Default: LXMLWebScrapingStrategy.
proxy_config (ProxyConfig or dict or None): Detailed proxy configuration, e.g. {"server": "...", "username": "..."}.
If None, no additional proxy config. Default: None.
@@ -911,7 +915,6 @@ class CrawlerRunConfig():
semaphore_count: int = 5,
# Page Interaction Parameters
js_code: Union[str, List[str]] = None,
c4a_script: Union[str, List[str]] = None,
js_only: bool = False,
ignore_body_visibility: bool = True,
scan_full_page: bool = False,
@@ -976,7 +979,7 @@ class CrawlerRunConfig():
self.remove_forms = remove_forms
self.prettiify = prettiify
self.parser_type = parser_type
self.scraping_strategy = scraping_strategy or WebScrapingStrategy()
self.scraping_strategy = scraping_strategy or LXMLWebScrapingStrategy()
self.proxy_config = proxy_config
self.proxy_rotation_strategy = proxy_rotation_strategy
@@ -1010,7 +1013,6 @@ class CrawlerRunConfig():
# Page Interaction Parameters
self.js_code = js_code
self.c4a_script = c4a_script
self.js_only = js_only
self.ignore_body_visibility = ignore_body_visibility
self.scan_full_page = scan_full_page
@@ -1086,59 +1088,6 @@ class CrawlerRunConfig():
# Experimental Parameters
self.experimental = experimental or {}
# Compile C4A scripts if provided
if self.c4a_script and not self.js_code:
self._compile_c4a_script()
def _compile_c4a_script(self):
"""Compile C4A script to JavaScript"""
try:
# Try importing the compiler
try:
from .script import compile
except ImportError:
from crawl4ai.script import compile
# Handle both string and list inputs
if isinstance(self.c4a_script, str):
scripts = [self.c4a_script]
else:
scripts = self.c4a_script
# Compile each script
compiled_js = []
for i, script in enumerate(scripts):
result = compile(script)
if result.success:
compiled_js.extend(result.js_code)
else:
# Format error message following existing patterns
error = result.first_error
error_msg = (
f"C4A Script compilation error (script {i+1}):\n"
f" Line {error.line}, Column {error.column}: {error.message}\n"
f" Code: {error.source_line}"
)
if error.suggestions:
error_msg += f"\n Suggestion: {error.suggestions[0].message}"
raise ValueError(error_msg)
self.js_code = compiled_js
except ImportError:
raise ValueError(
"C4A script compiler not available. "
"Please ensure crawl4ai.script module is properly installed."
)
except Exception as e:
# Re-raise with context
if "compilation error" not in str(e).lower():
raise ValueError(f"Failed to compile C4A script: {str(e)}")
raise
def __getattr__(self, name):
@@ -1380,6 +1329,7 @@ class CrawlerRunConfig():
config_dict.update(kwargs)
return CrawlerRunConfig.from_kwargs(config_dict)
class LLMConfig:
def __init__(
self,
@@ -1464,53 +1414,4 @@ class LLMConfig:
config_dict.update(kwargs)
return LLMConfig.from_kwargs(config_dict)
class SeedingConfig:
"""
Configuration class for URL discovery and pre-validation via AsyncUrlSeeder.
"""
def __init__(
self,
source: str = "sitemap+cc", # Options: "sitemap", "cc", "sitemap+cc"
pattern: Optional[str] = "*", # URL pattern to filter discovered URLs (e.g., "*example.com/blog/*")
live_check: bool = False, # Whether to perform HEAD requests to verify URL liveness
extract_head: bool = False, # Whether to fetch and parse <head> section for metadata
max_urls: int = -1, # Maximum number of URLs to discover (default: -1 for no limit)
concurrency: int = 1000, # Maximum concurrent requests for live checks/head extraction
hits_per_sec: int = 5, # Rate limit in requests per second
force: bool = False, # If True, bypasses the AsyncUrlSeeder's internal .jsonl cache
base_directory: Optional[str] = None, # Base directory for UrlSeeder's cache files (.jsonl)
llm_config: Optional[LLMConfig] = None, # Forward LLM config for future use (e.g., relevance scoring)
verbose: Optional[bool] = None, # Override crawler's general verbose setting
query: Optional[str] = None, # Search query for relevance scoring
score_threshold: Optional[float] = None, # Minimum relevance score to include URL (0.0-1.0)
scoring_method: str = "bm25", # Scoring method: "bm25" (default), future: "semantic"
filter_nonsense_urls: bool = True, # Filter out utility URLs like robots.txt, sitemap.xml, etc.
):
self.source = source
self.pattern = pattern
self.live_check = live_check
self.extract_head = extract_head
self.max_urls = max_urls
self.concurrency = concurrency
self.hits_per_sec = hits_per_sec
self.force = force
self.base_directory = base_directory
self.llm_config = llm_config
self.verbose = verbose
self.query = query
self.score_threshold = score_threshold
self.scoring_method = scoring_method
self.filter_nonsense_urls = filter_nonsense_urls
# Add to_dict, from_kwargs, and clone methods for consistency
def to_dict(self) -> Dict[str, Any]:
return {k: v for k, v in self.__dict__.items() if k != 'llm_config' or v is not None}
@staticmethod
def from_kwargs(kwargs: Dict[str, Any]) -> 'SeedingConfig':
return SeedingConfig(**kwargs)
def clone(self, **kwargs: Any) -> 'SeedingConfig':
config_dict = self.to_dict()
config_dict.update(kwargs)
return SeedingConfig.from_kwargs(config_dict)

View File

@@ -29,7 +29,7 @@ class LogLevel(Enum):
class LogColor(str, Enum):
"""Enum for log colors."""
DEBUG = "bright_black"
DEBUG = "lightblack"
INFO = "cyan"
SUCCESS = "green"
WARNING = "yellow"

File diff suppressed because it is too large Load Diff

View File

@@ -35,10 +35,9 @@ from .markdown_generation_strategy import (
)
from .deep_crawling import DeepCrawlDecorator
from .async_logger import AsyncLogger, AsyncLoggerBase
from .async_configs import BrowserConfig, CrawlerRunConfig, ProxyConfig, SeedingConfig
from .async_configs import BrowserConfig, CrawlerRunConfig, ProxyConfig
from .async_dispatcher import * # noqa: F403
from .async_dispatcher import BaseDispatcher, MemoryAdaptiveDispatcher, RateLimiter
from .async_url_seeder import AsyncUrlSeeder
from .utils import (
sanitize_input_encode,
@@ -164,8 +163,6 @@ class AsyncWebCrawler:
# Decorate arun method with deep crawling capabilities
self._deep_handler = DeepCrawlDecorator(self)
self.arun = self._deep_handler(self.arun)
self.url_seeder: Optional[AsyncUrlSeeder] = None
async def start(self):
"""
@@ -747,94 +744,3 @@ class AsyncWebCrawler:
else:
_results = await dispatcher.run_urls(crawler=self, urls=urls, config=config)
return [transform_result(res) for res in _results]
async def aseed_urls(
self,
domain_or_domains: Union[str, List[str]],
config: Optional[SeedingConfig] = None,
**kwargs
) -> Union[List[str], Dict[str, List[Union[str, Dict[str, Any]]]]]:
"""
Discovers, filters, and optionally validates URLs for a given domain(s)
using sitemaps and Common Crawl archives.
Args:
domain_or_domains: A single domain string (e.g., "iana.org") or a list of domains.
config: A SeedingConfig object to control the seeding process.
Parameters passed directly via kwargs will override those in 'config'.
**kwargs: Additional parameters (e.g., `source`, `live_check`, `extract_head`,
`pattern`, `concurrency`, `hits_per_sec`, `force_refresh`, `verbose`)
that will be used to construct or update the SeedingConfig.
Returns:
If `extract_head` is False:
- For a single domain: `List[str]` of discovered URLs.
- For multiple domains: `Dict[str, List[str]]` mapping each domain to its URLs.
If `extract_head` is True:
- For a single domain: `List[Dict[str, Any]]` where each dict contains 'url'
and 'head_data' (parsed <head> metadata).
- For multiple domains: `Dict[str, List[Dict[str, Any]]]` mapping each domain
to a list of URL data dictionaries.
Raises:
ValueError: If `domain_or_domains` is not a string or a list of strings.
Exception: Any underlying exceptions from AsyncUrlSeeder or network operations.
Example:
>>> # Discover URLs from sitemap with live check for 'example.com'
>>> result = await crawler.aseed_urls("example.com", source="sitemap", live_check=True, hits_per_sec=10)
>>> # Discover URLs from Common Crawl, extract head data for 'example.com' and 'python.org'
>>> multi_domain_result = await crawler.aseed_urls(
>>> ["example.com", "python.org"],
>>> source="cc", extract_head=True, concurrency=200, hits_per_sec=50
>>> )
"""
# Initialize AsyncUrlSeeder here if it hasn't been already
if not self.url_seeder:
# Pass the crawler's base_directory for seeder's cache management
# Pass the crawler's logger for consistent logging
self.url_seeder = AsyncUrlSeeder(
base_directory=self.crawl4ai_folder,
logger=self.logger
)
# Merge config object with direct kwargs, giving kwargs precedence
seeding_config = config.clone(**kwargs) if config else SeedingConfig.from_kwargs(kwargs)
# Ensure base_directory is set for the seeder's cache
seeding_config.base_directory = seeding_config.base_directory or self.crawl4ai_folder
# Ensure the seeder uses the crawler's logger (if not already set)
if not self.url_seeder.logger:
self.url_seeder.logger = self.logger
# Pass verbose setting if explicitly provided in SeedingConfig or kwargs
if seeding_config.verbose is not None:
self.url_seeder.logger.verbose = seeding_config.verbose
else: # Default to crawler's verbose setting
self.url_seeder.logger.verbose = self.logger.verbose
if isinstance(domain_or_domains, str):
self.logger.info(
message="Starting URL seeding for domain: {domain}",
tag="SEED",
params={"domain": domain_or_domains}
)
return await self.url_seeder.urls(
domain_or_domains,
seeding_config
)
elif isinstance(domain_or_domains, (list, tuple)):
self.logger.info(
message="Starting URL seeding for {count} domains",
tag="SEED",
params={"count": len(domain_or_domains)}
)
# AsyncUrlSeeder.many_urls directly accepts a list of domains and individual params.
return await self.url_seeder.many_urls(
domain_or_domains,
seeding_config
)
else:
raise ValueError("`domain_or_domains` must be a string or a list of strings.")

View File

@@ -2,7 +2,7 @@ import re
from itertools import chain
from abc import ABC, abstractmethod
from typing import Dict, Any, Optional
from bs4 import BeautifulSoup
# from bs4 import BeautifulSoup
import asyncio
import requests
from .config import (
@@ -13,12 +13,12 @@ from .config import (
IMPORTANT_ATTRS,
SOCIAL_MEDIA_DOMAINS,
)
from bs4 import NavigableString, Comment
from bs4 import PageElement, Tag
# from bs4 import NavigableString, Comment
# from bs4 import PageElement, Tag
from urllib.parse import urljoin
from requests.exceptions import InvalidSchema
from .utils import (
extract_metadata,
# extract_metadata,
normalize_url,
is_external_url,
get_base_domain,
@@ -96,20 +96,16 @@ class ContentScrapingStrategy(ABC):
pass
class WebScrapingStrategy(ContentScrapingStrategy):
"""
Class for web content scraping. Perhaps the most important class.
How it works:
1. Extract content from HTML using BeautifulSoup.
2. Clean the extracted content using a content cleaning strategy.
3. Filter the cleaned content using a content filtering strategy.
4. Generate markdown content from the filtered content.
5. Return the markdown content.
"""
class LXMLWebScrapingStrategy(ContentScrapingStrategy):
def __init__(self, logger=None):
self.logger = logger
self.DIMENSION_REGEX = re.compile(r"(\d+)(\D*)")
self.BASE64_PATTERN = re.compile(r'data:image/[^;]+;base64,([^"]+)')
# Constants for image processing
self.classes_to_check = frozenset(["button", "icon", "logo"])
self.tags_to_check = frozenset(["button", "input"])
self.image_formats = frozenset(["jpg", "jpeg", "png", "webp", "avif", "gif"])
def _log(self, level, message, tag="SCRAPE", **kwargs):
"""Helper method to safely use logger."""
@@ -130,7 +126,8 @@ class WebScrapingStrategy(ContentScrapingStrategy):
ScrapingResult: A structured result containing the scraped content.
"""
actual_url = kwargs.get("redirected_url", url)
raw_result = self._scrap(actual_url, html, is_async=False, **kwargs)
raw_result = self._scrap(actual_url, html, **kwargs)
if raw_result is None:
return ScrapingResult(
cleaned_html="",
@@ -194,388 +191,15 @@ class WebScrapingStrategy(ContentScrapingStrategy):
Returns:
ScrapingResult: A structured result containing the scraped content.
"""
return await asyncio.to_thread(self._scrap, url, html, **kwargs)
return await asyncio.to_thread(self.scrap, url, html, **kwargs)
def is_data_table(self, table: Tag, **kwargs) -> bool:
"""
Determine if a table element is a data table (not a layout table).
Args:
table (Tag): BeautifulSoup Tag representing a table element
**kwargs: Additional keyword arguments including table_score_threshold
Returns:
bool: True if the table is a data table, False otherwise
"""
score = 0
# Check for thead and tbody
has_thead = len(table.select('thead')) > 0
has_tbody = len(table.select('tbody')) > 0
if has_thead:
score += 2
if has_tbody:
score += 1
# Check for th elements
th_count = len(table.select('th'))
if th_count > 0:
score += 2
if has_thead or len(table.select('tr:first-child th')) > 0:
score += 1
# Check for nested tables
if len(table.select('table')) > 0:
score -= 3
# Role attribute check
role = table.get('role', '').lower()
if role in {'presentation', 'none'}:
score -= 3
# Column consistency
rows = table.select('tr')
if not rows:
return False
col_counts = [len(row.select('td, th')) for row in rows]
avg_cols = sum(col_counts) / len(col_counts)
variance = sum((c - avg_cols)**2 for c in col_counts) / len(col_counts)
if variance < 1:
score += 2
# Caption and summary
if table.select('caption'):
score += 2
if table.has_attr('summary') and table['summary']:
score += 1
# Text density
total_text = sum(len(cell.get_text().strip()) for row in rows for cell in row.select('td, th'))
total_tags = sum(1 for _ in table.descendants if isinstance(_, Tag))
text_ratio = total_text / (total_tags + 1e-5)
if text_ratio > 20:
score += 3
elif text_ratio > 10:
score += 2
# Data attributes
data_attrs = sum(1 for attr in table.attrs if attr.startswith('data-'))
score += data_attrs * 0.5
# Size check
if avg_cols >= 2 and len(rows) >= 2:
score += 2
threshold = kwargs.get('table_score_threshold', 7)
return score >= threshold
def extract_table_data(self, table: Tag) -> dict:
"""
Extract structured data from a table element.
Args:
table (Tag): BeautifulSoup Tag representing a table element
Returns:
dict: Dictionary containing table data (headers, rows, caption, summary)
"""
caption_elem = table.select_one('caption')
caption = caption_elem.get_text().strip() if caption_elem else ""
summary = table.get('summary', '').strip()
# Extract headers with colspan handling
headers = []
thead_rows = table.select('thead tr')
if thead_rows:
header_cells = thead_rows[0].select('th')
for cell in header_cells:
text = cell.get_text().strip()
colspan = int(cell.get('colspan', 1))
headers.extend([text] * colspan)
else:
first_row = table.select('tr:first-child')
if first_row:
for cell in first_row[0].select('th, td'):
text = cell.get_text().strip()
colspan = int(cell.get('colspan', 1))
headers.extend([text] * colspan)
# Extract rows with colspan handling
rows = []
all_rows = table.select('tr')
thead = table.select_one('thead')
tbody_rows = []
if thead:
thead_rows = thead.select('tr')
tbody_rows = [row for row in all_rows if row not in thead_rows]
else:
if all_rows and all_rows[0].select('th'):
tbody_rows = all_rows[1:]
else:
tbody_rows = all_rows
for row in tbody_rows:
# for row in table.select('tr:not(:has(ancestor::thead))'):
row_data = []
for cell in row.select('td'):
text = cell.get_text().strip()
colspan = int(cell.get('colspan', 1))
row_data.extend([text] * colspan)
if row_data:
rows.append(row_data)
# Align rows with headers
max_columns = len(headers) if headers else (max(len(row) for row in rows) if rows else 0)
aligned_rows = []
for row in rows:
aligned = row[:max_columns] + [''] * (max_columns - len(row))
aligned_rows.append(aligned)
if not headers:
headers = [f"Column {i+1}" for i in range(max_columns)]
return {
"headers": headers,
"rows": aligned_rows,
"caption": caption,
"summary": summary,
}
def flatten_nested_elements(self, node):
"""
Flatten nested elements in a HTML tree.
Args:
node (Tag): The root node of the HTML tree.
Returns:
Tag: The flattened HTML tree.
"""
if isinstance(node, NavigableString):
return node
if (
len(node.contents) == 1
and isinstance(node.contents[0], Tag)
and node.contents[0].name == node.name
):
return self.flatten_nested_elements(node.contents[0])
node.contents = [self.flatten_nested_elements(child) for child in node.contents]
return node
def find_closest_parent_with_useful_text(self, tag, **kwargs):
"""
Find the closest parent with useful text.
Args:
tag (Tag): The starting tag to search from.
**kwargs: Additional keyword arguments.
Returns:
Tag: The closest parent with useful text, or None if not found.
"""
image_description_min_word_threshold = kwargs.get(
"image_description_min_word_threshold", IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD
)
current_tag = tag
while current_tag:
current_tag = current_tag.parent
# Get the text content of the parent tag
if current_tag:
text_content = current_tag.get_text(separator=" ", strip=True)
# Check if the text content has at least word_count_threshold
if len(text_content.split()) >= image_description_min_word_threshold:
return text_content
return None
def remove_unwanted_attributes(
self, element, important_attrs, keep_data_attributes=False
):
"""
Remove unwanted attributes from an HTML element.
Args:
element (Tag): The HTML element to remove attributes from.
important_attrs (list): List of important attributes to keep.
keep_data_attributes (bool): Whether to keep data attributes.
Returns:
None
"""
attrs_to_remove = []
for attr in element.attrs:
if attr not in important_attrs:
if keep_data_attributes:
if not attr.startswith("data-"):
attrs_to_remove.append(attr)
else:
attrs_to_remove.append(attr)
for attr in attrs_to_remove:
del element[attr]
def process_image(self, img, url, index, total_images, **kwargs):
"""
Process an image element.
How it works:
1. Check if the image has valid display and inside undesired html elements.
2. Score an image for it's usefulness.
3. Extract image file metadata to extract size and extension.
4. Generate a dictionary with the processed image information.
5. Return the processed image information.
Args:
img (Tag): The image element to process.
url (str): The URL of the page containing the image.
index (int): The index of the image in the list of images.
total_images (int): The total number of images in the list.
**kwargs: Additional keyword arguments.
Returns:
dict: A dictionary containing the processed image information.
"""
# parse_srcset = lambda s: [{'url': u.strip().split()[0], 'width': u.strip().split()[-1].rstrip('w')
# if ' ' in u else None}
# for u in [f"http{p}" for p in s.split("http") if p]]
# Constants for checks
classes_to_check = frozenset(["button", "icon", "logo"])
tags_to_check = frozenset(["button", "input"])
image_formats = frozenset(["jpg", "jpeg", "png", "webp", "avif", "gif"])
# Pre-fetch commonly used attributes
style = img.get("style", "")
alt = img.get("alt", "")
src = img.get("src", "")
data_src = img.get("data-src", "")
srcset = img.get("srcset", "")
data_srcset = img.get("data-srcset", "")
width = img.get("width")
height = img.get("height")
parent = img.parent
parent_classes = parent.get("class", [])
# Quick validation checks
if (
"display:none" in style
or parent.name in tags_to_check
or any(c in cls for c in parent_classes for cls in classes_to_check)
or any(c in src for c in classes_to_check)
or any(c in alt for c in classes_to_check)
):
return None
# Quick score calculation
score = 0
if width and width.isdigit():
width_val = int(width)
score += 1 if width_val > 150 else 0
if height and height.isdigit():
height_val = int(height)
score += 1 if height_val > 150 else 0
if alt:
score += 1
score += index / total_images < 0.5
# image_format = ''
# if "data:image/" in src:
# image_format = src.split(',')[0].split(';')[0].split('/')[1].split(';')[0]
# else:
# image_format = os.path.splitext(src)[1].lower().strip('.').split('?')[0]
# if image_format in ('jpg', 'png', 'webp', 'avif'):
# score += 1
# Check for image format in all possible sources
def has_image_format(url):
return any(fmt in url.lower() for fmt in image_formats)
# Score for having proper image sources
if any(has_image_format(url) for url in [src, data_src, srcset, data_srcset]):
score += 1
if srcset or data_srcset:
score += 1
if img.find_parent("picture"):
score += 1
# Detect format from any available source
detected_format = None
for url in [src, data_src, srcset, data_srcset]:
if url:
format_matches = [fmt for fmt in image_formats if fmt in url.lower()]
if format_matches:
detected_format = format_matches[0]
break
if score <= kwargs.get("image_score_threshold", IMAGE_SCORE_THRESHOLD):
return None
# Use set for deduplication
unique_urls = set()
image_variants = []
# Generate a unique group ID for this set of variants
group_id = index
# Base image info template
base_info = {
"alt": alt,
"desc": self.find_closest_parent_with_useful_text(img, **kwargs),
"score": score,
"type": "image",
"group_id": group_id, # Group ID for this set of variants
"format": detected_format,
}
# Inline function for adding variants
def add_variant(src, width=None):
if src and not src.startswith("data:") and src not in unique_urls:
unique_urls.add(src)
image_variants.append({**base_info, "src": src, "width": width})
# Process all sources
add_variant(src)
add_variant(data_src)
# Handle srcset and data-srcset in one pass
for attr in ("srcset", "data-srcset"):
if value := img.get(attr):
for source in parse_srcset(value):
add_variant(source["url"], source["width"])
# Quick picture element check
if picture := img.find_parent("picture"):
for source in picture.find_all("source"):
if srcset := source.get("srcset"):
for src in parse_srcset(srcset):
add_variant(src["url"], src["width"])
# Framework-specific attributes in one pass
for attr, value in img.attrs.items():
if (
attr.startswith("data-")
and ("src" in attr or "srcset" in attr)
and "http" in value
):
add_variant(value)
return image_variants if image_variants else None
def process_element(self, url, element: PageElement, **kwargs) -> Dict[str, Any]:
def process_element(self, url: str, element: lhtml.HtmlElement, **kwargs) -> Dict[str, Any]:
"""
Process an HTML element.
How it works:
1. Check if the element is an image, video, or audio.
2. Extract the element's attributes and content.
3. Process the element based on its type.
4. Return the processed element information.
Args:
url (str): The URL of the page containing the element.
element (Tag): The HTML element to process.
element (lhtml.HtmlElement): The HTML element to process.
**kwargs: Additional keyword arguments.
Returns:
@@ -584,451 +208,40 @@ class WebScrapingStrategy(ContentScrapingStrategy):
media = {"images": [], "videos": [], "audios": [], "tables": []}
internal_links_dict = {}
external_links_dict = {}
self._process_element(
url, element, media, internal_links_dict, external_links_dict, **kwargs
)
return {
"media": media,
"internal_links_dict": internal_links_dict,
"external_links_dict": external_links_dict,
}
def _process_element(
self,
url,
element: PageElement,
media: Dict[str, Any],
internal_links_dict: Dict[str, Any],
external_links_dict: Dict[str, Any],
**kwargs,
) -> bool:
def remove_unwanted_attributes(self, element: lhtml.HtmlElement, important_attrs: List[str], keep_data_attributes: bool = False):
"""
Process an HTML element.
"""
try:
if isinstance(element, NavigableString):
if isinstance(element, Comment):
element.extract()
return False
# if element.name == 'img':
# process_image(element, url, 0, 1)
# return True
base_domain = kwargs.get("base_domain", get_base_domain(url))
if element.name in ["script", "style", "link", "meta", "noscript"]:
element.decompose()
return False
keep_element = False
# Special case for table elements - always preserve structure
if element.name in ["tr", "td", "th"]:
keep_element = True
exclude_domains = kwargs.get("exclude_domains", [])
# exclude_social_media_domains = kwargs.get('exclude_social_media_domains', set(SOCIAL_MEDIA_DOMAINS))
# exclude_social_media_domains = SOCIAL_MEDIA_DOMAINS + kwargs.get('exclude_social_media_domains', [])
# exclude_social_media_domains = list(set(exclude_social_media_domains))
try:
if element.name == "a" and element.get("href"):
href = element.get("href", "").strip()
if not href: # Skip empty hrefs
return False
# url_base = url.split("/")[2]
# Normalize the URL
try:
normalized_href = normalize_url(href, url)
except ValueError:
# logging.warning(f"Invalid URL format: {href}, Error: {str(e)}")
return False
link_data = {
"href": normalized_href,
"text": element.get_text().strip(),
"title": element.get("title", "").strip(),
"base_domain": base_domain,
}
is_external = is_external_url(normalized_href, base_domain)
keep_element = True
# Handle external link exclusions
if is_external:
link_base_domain = get_base_domain(normalized_href)
link_data["base_domain"] = link_base_domain
if kwargs.get("exclude_external_links", False):
element.decompose()
return False
# elif kwargs.get('exclude_social_media_links', False):
# if link_base_domain in exclude_social_media_domains:
# element.decompose()
# return False
# if any(domain in normalized_href.lower() for domain in exclude_social_media_domains):
# element.decompose()
# return False
elif exclude_domains:
if link_base_domain in exclude_domains:
element.decompose()
return False
# if any(domain in normalized_href.lower() for domain in kwargs.get('exclude_domains', [])):
# element.decompose()
# return False
if is_external:
if normalized_href not in external_links_dict:
external_links_dict[normalized_href] = link_data
else:
if kwargs.get("exclude_internal_links", False):
element.decompose()
return False
if normalized_href not in internal_links_dict:
internal_links_dict[normalized_href] = link_data
except Exception as e:
raise Exception(f"Error processing links: {str(e)}")
try:
if element.name == "img":
potential_sources = [
"src",
"data-src",
"srcset" "data-lazy-src",
"data-original",
]
src = element.get("src", "")
while not src and potential_sources:
src = element.get(potential_sources.pop(0), "")
if not src:
element.decompose()
return False
# If it is srcset pick up the first image
if "srcset" in element.attrs:
src = element.attrs["srcset"].split(",")[0].split(" ")[0]
# If image src is internal, then skip
if not is_external_url(src, base_domain):
return True
image_src_base_domain = get_base_domain(src)
# Check flag if we should remove external images
if kwargs.get("exclude_external_images", False):
element.decompose()
return False
# src_url_base = src.split('/')[2]
# url_base = url.split('/')[2]
# if url_base not in src_url_base:
# element.decompose()
# return False
# if kwargs.get('exclude_social_media_links', False):
# if image_src_base_domain in exclude_social_media_domains:
# element.decompose()
# return False
# src_url_base = src.split('/')[2]
# url_base = url.split('/')[2]
# if any(domain in src for domain in exclude_social_media_domains):
# element.decompose()
# return False
# Handle exclude domains
if exclude_domains:
if image_src_base_domain in exclude_domains:
element.decompose()
return False
# if any(domain in src for domain in kwargs.get('exclude_domains', [])):
# element.decompose()
# return False
return True # Always keep image elements
except Exception:
raise "Error processing images"
# Check if flag to remove all forms is set
if kwargs.get("remove_forms", False) and element.name == "form":
element.decompose()
return False
if element.name in ["video", "audio"]:
media[f"{element.name}s"].append(
{
"src": element.get("src"),
"alt": element.get("alt"),
"type": element.name,
"description": self.find_closest_parent_with_useful_text(
element, **kwargs
),
}
)
source_tags = element.find_all("source")
for source_tag in source_tags:
media[f"{element.name}s"].append(
{
"src": source_tag.get("src"),
"alt": element.get("alt"),
"type": element.name,
"description": self.find_closest_parent_with_useful_text(
element, **kwargs
),
}
)
return True # Always keep video and audio elements
if element.name in ONLY_TEXT_ELIGIBLE_TAGS:
if kwargs.get("only_text", False):
element.replace_with(element.get_text())
try:
self.remove_unwanted_attributes(
element, IMPORTANT_ATTRS + kwargs.get("keep_attrs", []) , kwargs.get("keep_data_attributes", False)
)
except Exception as e:
# print('Error removing unwanted attributes:', str(e))
self._log(
"error",
message="Error removing unwanted attributes: {error}",
tag="SCRAPE",
params={"error": str(e)},
)
# Process children
for child in list(element.children):
if isinstance(child, NavigableString) and not isinstance(
child, Comment
):
if len(child.strip()) > 0:
keep_element = True
else:
if self._process_element(
url,
child,
media,
internal_links_dict,
external_links_dict,
**kwargs,
):
keep_element = True
# Check word count
word_count_threshold = kwargs.get(
"word_count_threshold", MIN_WORD_THRESHOLD
)
if not keep_element:
word_count = len(element.get_text(strip=True).split())
keep_element = word_count >= word_count_threshold
if not keep_element:
element.decompose()
return keep_element
except Exception as e:
# print('Error processing element:', str(e))
self._log(
"error",
message="Error processing element: {error}",
tag="SCRAPE",
params={"error": str(e)},
)
return False
def _scrap(
self,
url: str,
html: str,
word_count_threshold: int = MIN_WORD_THRESHOLD,
css_selector: str = None,
target_elements: List[str] = None,
**kwargs,
) -> Dict[str, Any]:
"""
Extract content from HTML using BeautifulSoup.
Remove unwanted attributes from an HTML element.
Args:
url (str): The URL of the page to scrape.
html (str): The HTML content of the page to scrape.
word_count_threshold (int): The minimum word count threshold for content extraction.
css_selector (str): The CSS selector to use for content extraction.
**kwargs: Additional keyword arguments.
element (lhtml.HtmlElement): The HTML element to remove attributes from.
important_attrs (List[str]): List of important attributes to keep.
keep_data_attributes (bool): Whether to keep data attributes.
Returns:
dict: A dictionary containing the extracted content.
None
"""
success = True
if not html:
return None
attrs_to_remove = []
for attr in element.attrib:
if attr not in important_attrs:
if keep_data_attributes:
if not attr.startswith("data-"):
attrs_to_remove.append(attr)
else:
attrs_to_remove.append(attr)
parser_type = kwargs.get("parser", "lxml")
soup = BeautifulSoup(html, parser_type)
body = soup.body
if body is None:
raise Exception("'<body>' tag is not found in fetched html. Consider adding wait_for=\"css:body\" to wait for body tag to be loaded into DOM.")
base_domain = get_base_domain(url)
# Early removal of all images if exclude_all_images is set
# This happens before any processing to minimize memory usage
if kwargs.get("exclude_all_images", False):
for img in body.find_all('img'):
img.decompose()
try:
meta = extract_metadata("", soup)
except Exception as e:
self._log(
"error",
message="Error extracting metadata: {error}",
tag="SCRAPE",
params={"error": str(e)},
)
meta = {}
# Handle tag-based removal first - faster than CSS selection
excluded_tags = set(kwargs.get("excluded_tags", []) or [])
if excluded_tags:
for element in body.find_all(lambda tag: tag.name in excluded_tags):
element.extract()
# Handle CSS selector-based removal
excluded_selector = kwargs.get("excluded_selector", "")
if excluded_selector:
is_single_selector = (
"," not in excluded_selector and " " not in excluded_selector
)
if is_single_selector:
while element := body.select_one(excluded_selector):
element.extract()
else:
for element in body.select(excluded_selector):
element.extract()
content_element = None
if target_elements:
try:
for_content_targeted_element = []
for target_element in target_elements:
for_content_targeted_element.extend(body.select(target_element))
content_element = soup.new_tag("div")
for el in for_content_targeted_element:
content_element.append(copy.deepcopy(el))
except Exception as e:
self._log("error", f"Error with target element detection: {str(e)}", "SCRAPE")
return None
else:
content_element = body
kwargs["exclude_social_media_domains"] = set(
kwargs.get("exclude_social_media_domains", []) + SOCIAL_MEDIA_DOMAINS
)
kwargs["exclude_domains"] = set(kwargs.get("exclude_domains", []))
if kwargs.get("exclude_social_media_links", False):
kwargs["exclude_domains"] = kwargs["exclude_domains"].union(
kwargs["exclude_social_media_domains"]
)
result_obj = self.process_element(
url,
body,
word_count_threshold=word_count_threshold,
base_domain=base_domain,
**kwargs,
)
links = {"internal": [], "external": []}
media = result_obj["media"]
internal_links_dict = result_obj["internal_links_dict"]
external_links_dict = result_obj["external_links_dict"]
# Update the links dictionary with unique links
links["internal"] = list(internal_links_dict.values())
links["external"] = list(external_links_dict.values())
# # Process images using ThreadPoolExecutor
imgs = body.find_all("img")
media["images"] = [
img
for result in (
self.process_image(img, url, i, len(imgs), **kwargs)
for i, img in enumerate(imgs)
)
if result is not None
for img in result
]
# Process tables if not excluded
excluded_tags = set(kwargs.get("excluded_tags", []) or [])
if 'table' not in excluded_tags:
tables = body.find_all('table')
for table in tables:
if self.is_data_table(table, **kwargs):
table_data = self.extract_table_data(table)
media["tables"].append(table_data)
body = self.flatten_nested_elements(body)
base64_pattern = re.compile(r'data:image/[^;]+;base64,([^"]+)')
for img in imgs:
src = img.get("src", "")
if base64_pattern.match(src):
# Replace base64 data with empty string
img["src"] = base64_pattern.sub("", src)
str_body = ""
try:
str_body = content_element.encode_contents().decode("utf-8")
except Exception:
# Reset body to the original HTML
success = False
body = BeautifulSoup(html, "html.parser")
# Create a new div with a special ID
error_div = body.new_tag("div", id="crawl4ai_error_message")
error_div.string = """
Crawl4AI Error: This page is not fully supported.
Possible reasons:
1. The page may have restrictions that prevent crawling.
2. The page might not be fully loaded.
Suggestions:
- Try calling the crawl function with these parameters:
magic=True,
- Set headless=False to visualize what's happening on the page.
If the issue persists, please check the page's structure and any potential anti-crawling measures.
"""
# Append the error div to the body
body.append(error_div)
str_body = body.encode_contents().decode("utf-8")
print(
"[LOG] 😧 Error: After processing the crawled HTML and removing irrelevant tags, nothing was left in the page. Check the markdown for further details."
)
self._log(
"error",
message="After processing the crawled HTML and removing irrelevant tags, nothing was left in the page. Check the markdown for further details.",
tag="SCRAPE",
)
cleaned_html = str_body.replace("\n\n", "\n").replace(" ", " ")
return {
"cleaned_html": cleaned_html,
"success": success,
"media": media,
"links": links,
"metadata": meta,
}
class LXMLWebScrapingStrategy(WebScrapingStrategy):
def __init__(self, logger=None):
super().__init__(logger)
self.DIMENSION_REGEX = re.compile(r"(\d+)(\D*)")
self.BASE64_PATTERN = re.compile(r'data:image/[^;]+;base64,([^"]+)')
for attr in attrs_to_remove:
del element.attrib[attr]
def _process_element(
self,
@@ -1190,7 +403,7 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
return None
parent = img.getparent()
if parent.tag in ["button", "input"]:
if parent.tag in self.tags_to_check:
return None
parent_classes = parent.get("class", "").split()
@@ -1200,8 +413,8 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
return None
# If src is in class or alt, likely an icon
if (src and any(c in src for c in ["button", "icon", "logo"])) or (
alt and any(c in alt for c in ["button", "icon", "logo"])
if (src and any(c in src for c in self.classes_to_check)) or (
alt and any(c in alt for c in self.classes_to_check)
):
return None
@@ -1216,11 +429,10 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
score += index / total_images < 0.5
# Check formats in all possible sources
image_formats = {"jpg", "jpeg", "png", "webp", "avif", "gif"}
detected_format = None
for url in [src, data_src, srcset, data_srcset]:
if url:
format_matches = [fmt for fmt in image_formats if fmt in url.lower()]
format_matches = [fmt for fmt in self.image_formats if fmt in url.lower()]
if format_matches:
detected_format = format_matches[0]
score += 1
@@ -1484,6 +696,13 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
success = True
try:
# Extract metadata FIRST from the original HTML to avoid issues with modified content.
try:
meta = extract_metadata_using_lxml(html, None) # Pass the original HTML
except Exception as e:
self._log("error", f"Error extracting metadata: {str(e)}", "SCRAPE")
meta = {}
doc = lhtml.document_fromstring(html)
# Match BeautifulSoup's behavior of using body or full doc
# body = doc.xpath('//body')[0] if doc.xpath('//body') else doc
@@ -1524,14 +743,14 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
"error", f"Error with excluded CSS selector: {str(e)}", "SCRAPE"
)
# Extract metadata before any content filtering
try:
meta = extract_metadata_using_lxml(
"", doc
) # Using same function as BeautifulSoup version
except Exception as e:
self._log("error", f"Error extracting metadata: {str(e)}", "SCRAPE")
meta = {}
# # Extract metadata before any content filtering
# try:
# meta = extract_metadata_using_lxml(
# "", doc
# ) # Using same function as BeautifulSoup version
# except Exception as e:
# self._log("error", f"Error extracting metadata: {str(e)}", "SCRAPE")
# meta = {}
content_element = None
if target_elements:
@@ -1611,7 +830,9 @@ class LXMLWebScrapingStrategy(WebScrapingStrategy):
# Remove unneeded attributes
self.remove_unwanted_attributes_fast(
body, keep_data_attributes=kwargs.get("keep_data_attributes", False)
body,
important_attrs=IMPORTANT_ATTRS + kwargs.get("keep_attrs", []),
keep_data_attributes=kwargs.get("keep_data_attributes", False)
)
# Generate output HTML

View File

@@ -1054,525 +1054,4 @@ Your output must:
5. Include all required fields
6. Use valid XPath selectors
</output_requirements>
"""
GENERATE_SCRIPT_PROMPT = """You are a world-class browser automation specialist. Your sole purpose is to convert a natural language objective and a snippet of HTML into the most **efficient, robust, and simple** script possible to prepare a web page for data extraction.
Your scripts run **before the crawl** to handle dynamic content, user interactions, and other obstacles. You are a master of two tools: raw **JavaScript** and the high-level **Crawl4ai Script (c4a)**.
────────────────────────────────────────────────────────
## Your Core Philosophy: "Efficiency, Robustness, Simplicity"
This is your mantra. Every line of code you write must adhere to it.
1. **Efficiency (Shortest Path):** Generate the absolute minimum number of steps to achieve the goal. Do not include redundant actions. If a `CLICK` on one button achieves the goal, don't also scroll and wait unnecessarily.
2. **Robustness (Will Not Break):** Prioritize selectors and methods that are resistant to cosmetic site changes. `data-*` attributes are gold. Dynamic, auto-generated class names (`.class-a8B_x3`) are poison. Always prefer waiting for a state change (`WAIT \`#results\``) over a blind delay (`WAIT 5`).
3. **Simplicity (Right Tool for the Job):** Use the simplest tool that works. Prefer a direct `c4a` command over `EVAL` with JavaScript. Only use `EVAL` when the task is impossible with standard commands (e.g., accessing Shadow DOM, complex array filtering).
────────────────────────────────────────────────────────
## Output Mode Selection Logic
Your choice of output mode is a critical strategic decision.
* **Use `crawl4ai_script` for:**
* Standard, sequential browser actions: login forms, clicking "next page," simple "load more" buttons, accepting cookie banners.
* When the user's goal maps clearly to the available `c4a` commands.
* When you need to define reusable macros with `PROC`.
* **Use `javascript` for:**
* Complex DOM manipulation that has no `c4a` equivalent (e.g., transforming data, complex filtering).
* Interacting with web components inside **Shadow DOM** or **iFrames**.
* Implementing sophisticated logic like custom scrolling patterns or handling non-standard events.
* When the goal is a fine-grained DOM tweak, not a full user journey.
**If the user specifies a mode, you MUST respect it.** If not, you must choose the mode that best embodies your core philosophy.
────────────────────────────────────────────────────────
## Available Crawl4ai Commands
| Command | Arguments / Notes |
|------------------------|--------------------------------------------------------------|
| GO `<url>` | Navigate to absolute URL |
| RELOAD | Hard refresh |
| BACK / FORWARD | Browser history nav |
| WAIT `<seconds>` | **Avoid!** Passive delay. Use only as a last resort. |
| WAIT \`<css>\` `<t>` | **Preferred wait.** Poll selector until found, timeout in seconds. |
| WAIT "<text>" `<t>` | Poll page text until found, timeout in seconds. |
| CLICK \`<css>\` | Single click on element |
| CLICK `<x>` `<y>` | Viewport click |
| DOUBLE_CLICK … | Two rapid clicks |
| RIGHT_CLICK … | Context-menu click |
| MOVE `<x>` `<y>` | Mouse move |
| DRAG `<x1>` `<y1>` `<x2>` `<y2>` | Click-drag gesture |
| SCROLL UP|DOWN|LEFT|RIGHT `[px]` | Viewport scroll |
| TYPE "<text>" | Type into focused element |
| CLEAR \`<css>\` | Empty input |
| SET \`<css>\` "<val>" | Set element value and dispatch events |
| PRESS `<Key>` | Keydown + keyup |
| KEY_DOWN `<Key>` / KEY_UP `<Key>` | Separate key events |
| EVAL \`<js>\` | **Your fallback.** Run JS when no direct command exists. |
| SETVAR $name = <val> | Store constant for reuse |
| PROC name … ENDPROC | Define macro |
| IF / ELSE / REPEAT | Flow control |
| USE "<file.c4a>" | Include another script, avoid circular includes |
────────────────────────────────────────────────────────
## Strategic Principles & Anti-Patterns
These are your commandments. Do not deviate.
1. **Selector Quality is Paramount:**
* **GOOD:** `[data-testid="submit-button"]`, `#main-content`, `[aria-label="Close dialog"]`
* **BAD:** `div > span:nth-child(3)`, `.button-gR3xY_s`, `//div[contains(@class, 'button')]`
2. **Wait for State, Not for Time:**
* **DO:** `CLICK \`#load-more\`` followed by `WAIT \`div.new-item\` 10`. This waits for the *result* of the action.
* **DON'T:** `CLICK \`#load-more\`` followed by `WAIT 5`. This is a guess and it will fail.
3. **Target the Action, Not the Artifact:** If you need to reveal content, click the button that reveals it. Don't try to manually change CSS `display` properties, as this can break the page's internal state.
4. **DOM-Awareness is Non-Negotiable:**
* **Shadow DOM:** `c4a` commands CANNOT pierce the Shadow DOM. If you see a `#shadow-root (open)` in the HTML, you MUST use `EVAL` and `element.shadowRoot.querySelector(...)`.
* **iFrames:** Likewise, you MUST use `EVAL` and `iframe.contentDocument.querySelector(...)` to interact with elements inside an iframe.
5. **Be Idempotent:** Your script must be harmless if run multiple times. Use `IF EXISTS` to check for states before acting (e.g., don't try to log in if already logged in).
6. **Forbidden Techniques:** Never use `document.write()`. It is destructive. Avoid overly complex JS in `EVAL` that could be simplified into a few `c4a` commands.
────────────────────────────────────────────────────────
## From Vague Goals to Robust Scripts: Your Duty to Infer and Ensure Reliability
This is your most important responsibility. Users are not automation experts. They will provide incomplete or vague instructions. Your job is to be the expert—to infer their true goal and build a script that is reliable by default. You must add the "invisible scaffolding" of checks and waits to ensure the page is stable and ready for the crawler. **A vague user prompt must still result in a robust, complete script.**
Study these examples. No matter which query is given, your output must be the single, robust solution.
### 1. Scenario: Basic Search Query
* **High Detail Query:** "Find the search box and search button. Wait for the search box to be visible, click it, clear it, type 'r2d2', click the search button, and then wait for the search results to appear."
* **Medium Detail Query:** "Find the search box and search for 'r2d2', click the search button until you get a list of items."
* **Low Detail Query:** "Search for r2d2."
**THE CORRECT, ROBUST OUTPUT (for all three queries):**
```
WAIT `input[type="search"]` 10
SET `input[type="search"]` "r2d2"
CLICK `button[aria-label="Search"]`
WAIT `div.search-results-container` 15
```
**Rationale:** You correctly infer the need to `WAIT` for the input first. You use the more efficient `SET` command. Most importantly, you **infer the crucial final step**: waiting for a results container to appear, confirming the search action was successful.
### 2. Scenario: Clicking a "Load More" Button
* **High Detail Query:** "Click the button with the text 'Load More'. Afterward, wait for a new item with the class '.product-tile' to show up on the page."
* **Medium Detail Query:** "Click the load more button to see more products."
* **Low Detail Query:** "Load more items."
**THE CORRECT, ROBUST OUTPUT:**
```
IF EXISTS `button.load-more` THEN
CLICK `button.load-more`
WAIT `div.new-item-indicator` 8
ENDIF
```
**Rationale:** You wrap the action in `IF EXISTS` to prevent errors if the button is not present (e.g., on the last page). You correctly infer the need to wait for the *consequence* of the click—a new item appearing—rather than a blind `WAIT 2`.
### 3. Scenario: Applying a Filter from a Dropdown
* **High Detail Query:** "First, click the dropdown with id 'color-filter'. Then, from the open menu, click the option that says 'Blue'. Finally, wait for the product grid to update."
* **Medium Detail Query:** "Filter the products by the color Blue."
* **Low Detail Query:** "Show blue products."
**THE CORRECT, ROBUST OUTPUT:**
```
CLICK `#color-filter`
WAIT `[data-value="blue"]` 3
CLICK `[data-value="blue"]`
WAIT `#product-grid[data-status="updated"]` 10
```
**Rationale:** You infer the need for two waits: one for the menu options to appear after the first click, and a second for the main content to update after the filter is applied. This prevents race conditions.
### 4. Scenario: User Authentication (Login)
* **High Detail Query:** "Fill username with 'USER_EMAIL', fill password with 'USER_PASS', click login, and wait for the dashboard to appear."
* **Medium Detail Query:** "Log in as USER_EMAIL with password USER_PASS."
* **Low Detail Query:** "Log in."
**THE CORRECT, ROBUST OUTPUT:**
```
IF EXISTS `[data-testid="logout-button"]` THEN
EVAL `console.log("Already logged in.")`
ELSE
WAIT `input[name="username"]` 10
SET `input[name="username"]` "USER_EMAIL"
SET `input[name="password"]` "USER_PASS"
CLICK `button[type="submit"]`
WAIT `[data-testid="user-dashboard"]` 15
ENDIF
```
**Rationale:** You build an **idempotent** script. You first check if the user is *already* logged in. If not, you proceed with the login and then, critically, `WAIT` for a post-login element to confirm success. You use placeholders when credentials are not provided in low-detail queries.
### 5. Scenario: Dismissing an Interstitial Modal
* **High Detail Query:** "Check if a popup with id '#promo-modal' exists. If it does, click the close button inside it with class '.close-x'."
* **Medium Detail Query:** "Close the promotional popup."
* **Low Detail Query:** "Get rid of the popup."
**THE CORRECT, ROBUST OUTPUT:**
```
IF EXISTS `div#promo-modal` THEN
CLICK `div#promo-modal button.close-x`
ENDIF
```
**Rationale:** You correctly identify this as a conditional action. The script must not fail if the popup doesn't appear. The `IF EXISTS` block is the perfect, robust way to handle this optional interaction.
────────────────────────────────────────────────────────
## Advanced Scenarios & Master-Level Examples
Study these solutions. Understand the *why* behind each choice.
### Scenario: Interacting with a Web Component (Shadow DOM)
**Goal:** Click a button inside a custom element `<user-card>`.
**HTML Snippet:** `<user-card><#shadow-root (open)><button>Details</button></#shadow-root></user-card>`
**Correct Mode:** `javascript` (or `c4a` with `EVAL`)
**Rationale:** Standard selectors can't cross the shadow boundary. JavaScript is mandatory.
```javascript
// Solution in pure JS mode
const card = document.querySelector('user-card');
if (card && card.shadowRoot) {
const button = card.shadowRoot.querySelector('button');
if (button) button.click();
}
```
```
# Solution in c4a mode (using EVAL as the weapon of choice)
EVAL `
const card = document.querySelector('user-card');
if (card && card.shadowRoot) {
const button = card.shadowRoot.querySelector('button');
if (button) button.click();
}
`
```
### Scenario: Handling a Cookie Banner
**Goal:** Accept the cookies to dismiss the modal.
**HTML Snippet:** `<div id="cookie-consent-modal"><button id="accept-cookies">Accept All</button></div>`
**Correct Mode:** `crawl4ai_script`
**Rationale:** A simple, direct action. `c4a` is cleaner and more declarative.
```
# The most efficient solution
IF EXISTS `#cookie-consent-modal` THEN
CLICK `#accept-cookies`
WAIT `div.content-loaded` 5
ENDIF
```
### Scenario: Infinite Scroll Page
**Goal:** Scroll down 5 times to load more content.
**HTML Snippet:** `(A page with a long body and no "load more" button)`
**Correct Mode:** `crawl4ai_script`
**Rationale:** `REPEAT` is designed for exactly this. It's more readable than a JS loop for this simple task.
```
REPEAT (
SCROLL DOWN 1000,
5
)
WAIT 2
```
### Scenario: Hover-to-Reveal Menu
**Goal:** Hover over "Products" to open the menu, then click "Laptops".
**HTML Snippet:** `<a href="/products" id="products-menu">Products</a> <div class="menu-dropdown"><a href="/laptops">Laptops</a></div>`
**Correct Mode:** `crawl4ai_script` (with `EVAL`)
**Rationale:** `c4a` has no `HOVER` command. `EVAL` is the perfect tool to dispatch the `mouseover` event.
```
EVAL `document.querySelector('#products-menu').dispatchEvent(new MouseEvent('mouseover', { bubbles: true }))`
WAIT `div.menu-dropdown a[href="/laptops"]` 3
CLICK `div.menu-dropdown a[href="/laptops"]`
```
### Scenario: Login Form
**Goal:** Fill and submit a login form.
**HTML Snippet:** `<form><input name="email"><input name="password" type="password"><button type="submit"></button></form>`
**Correct Mode:** `crawl4ai_script`
**Rationale:** This is the canonical use case for `c4a`. The commands map 1:1 to the user journey.
```
WAIT `form` 10
SET `input[name="email"]` "USER_EMAIL"
SET `input[name="password"]` "USER_PASS"
CLICK `button[type="submit"]`
WAIT `[data-testid="user-dashboard"]` 12
```
────────────────────────────────────────────────────────
## Final Output Mandate
1. **CODE ONLY.** Your entire response must be the script body.
2. **NO CHAT.** Do not say "Here is the script" or "This should work."
3. **NO MARKDOWN.** Do not wrap your code in ` ``` ` fences.
4. **NO COMMENTS.** Do not add comments to the final code output.
5. **SYNTACTICALLY PERFECT.** The script must be immediately executable.
6. **UTF-8, STANDARD QUOTES.** Use `"` for string literals, not `“` or `”`.
You are an engine of automation. Now, receive the user's request and produce the optimal script."""
GENERATE_JS_SCRIPT_PROMPT = """# The World-Class JavaScript Automation Scripter
You are a world-class browser automation specialist. Your sole purpose is to convert a natural language objective and a snippet of HTML into the most **efficient, robust, and simple** pure JavaScript script possible to prepare a web page for data extraction.
Your scripts will be executed directly in the browser (e.g., via Playwright's `page.evaluate()`) to handle dynamic content, user interactions, and other obstacles before the page is crawled. You are a master of browser-native JavaScript APIs.
────────────────────────────────────────────────────────
## Your Core Philosophy: "Efficiency, Robustness, Simplicity"
This is your mantra. Every line of JavaScript you write must adhere to it.
1. **Efficiency (Shortest Path):** Generate the absolute minimum number of steps to achieve the goal. Do not include redundant actions. Your code should be concise and direct.
2. **Robustness (Will Not Break):** Prioritize selectors that are resistant to cosmetic site changes. `data-*` attributes are gold. Dynamic, auto-generated class names (`.class-a8B_x3`) are poison. Always prefer waiting for a state change over a blind `setTimeout`.
3. **Simplicity (Right Tool for the Job):** Use simple, direct DOM methods (`.querySelector`, `.click()`) whenever possible. Avoid overly complex or fragile logic when a simpler approach exists.
────────────────────────────────────────────────────────
## Essential JavaScript Automation Patterns & Toolkit
All code should be wrapped in an `async` Immediately Invoked Function Expression `(async () => { ... })();` to allow for top-level `await` and to avoid polluting the global scope.
| Task | Best-Practice JavaScript Implementation |
| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Wait for Element** | Create and use a robust `waitForElement` helper function. This is your most important tool. <br> `const waitForElement = (selector, timeout = 10000) => new Promise((resolve, reject) => { const el = document.querySelector(selector); if (el) return resolve(el); const observer = new MutationObserver(() => { const el = document.querySelector(selector); if (el) { observer.disconnect(); resolve(el); } }); observer.observe(document.body, { childList: true, subtree: true }); setTimeout(() => { observer.disconnect(); reject(new Error(`Timeout waiting for ${selector}`)); }, timeout); });` |
| **Click Element** | `const el = await waitForElement('selector'); if (el) el.click();` |
| **Set Input Value** | `const input = await waitForElement('selector'); if (input) { input.value = 'new value'; input.dispatchEvent(new Event('input', { bubbles: true })); input.dispatchEvent(new Event('change', { bubbles: true })); }` <br> *Crucially, always dispatch `input` and `change` events to trigger framework reactivity.* |
| **Check Existence** | `const el = document.querySelector('selector'); if (el) { /* ... it exists */ }` |
| **Scroll** | `window.scrollBy(0, window.innerHeight);` |
| **Deal with Time** | Use `await new Promise(r => setTimeout(r, 500));` for short, unavoidable pauses after an action. **Avoid long, blind waits.** |
REMEMBER: Make sure to generate very deterministic css selector. If you refer to a specific button, then be specific, otherwise you may capture elements you do not need, be very specific about the element you want to interact with.
────────────────────────────────────────────────────────
## The Art of High-Specificity Selectors: Your Defense Against Ambiguity
This is your most critical skill for ensuring robustness. **You must assume the provided HTML is only a small fragment of the entire page.** A selector that looks unique in the fragment could be disastrously generic on the full page. Your primary defense is to **anchor your selectors to the most specific, stable parent element available in the given HTML context.**
Think of it as creating a "sandbox" for your selectors.
**Your Guiding Principle:** Start from a unique parent, then find the child.
### Scenario: Selecting a Submit Button within a Login Form
**HTML Snippet Provided:**
```html
<div class="user-auth-module" id="login-widget">
<h2>Member Login</h2>
<form action="/login">
<input name="email" type="email">
<input name="password" type="password">
<button type="submit">Sign In</button>
</form>
</div>
```
* **TERRIBLE (High Risk):** `button[type="submit"]`
* **Why it's bad:** There could be dozens of other forms on the full page (e.g., a newsletter signup, a search bar in the header). This selector is a shot in the dark.
* **BETTER (Lower Risk):** `#login-widget button[type="submit"]`
* **Why it's better:** It's anchored to a unique ID (`#login-widget`). This dramatically reduces the chance of ambiguity.
* **EXCELLENT (Minimal Risk):** `div[id="login-widget"] form button[type="submit"]`
* **Why it's best:** This is a highly specific, descriptive path. It says, "Find the login widget, then the form inside it, and then the submit button inside *that* form." It is virtually guaranteed to be unique and is resilient to minor layout changes within the form.
### Scenario: Selecting a "Add to Cart" Button
**HTML Snippet Provided:**
```html
<section data-testid="product-details-main">
<h1>Awesome T-Shirt</h1>
<div class="product-actions">
<button class="add-to-cart-btn">Add to Cart</button>
</div>
</section>
```
* **TERRIBLE (High Risk):** `.add-to-cart-btn`
* **Why it's bad:** A "related products" section outside this snippet might also use the same class name.
* **EXCELLENT (Minimal Risk):** `[data-testid="product-details-main"] .add-to-cart-btn`
* **Why it's best:** It uses the stable `data-testid` attribute of the parent section as an anchor. This is the most robust pattern.
**Your Mandate:** Always examine the provided HTML for a stable, unique parent (like an element with an `id`, a `data-testid`, or a highly specific combination of classes) and use it as the root of your selectors. **NEVER generate a generic, un-anchored selector if a better, more specific parent is available in the context.**
────────────────────────────────────────────────────────
## Strategic Principles & Anti-Patterns
These are your commandments. Do not deviate.
1. **Selector Quality is Paramount:**
* **GOOD:** `[data-testid="submit-button"]`, `#main-content`, `[aria-label="Close dialog"]`
* **BAD:** `div > span:nth-child(3)`, `.button-gR3xY_s`, `//div[contains(@class, 'button')]`
2. **Wait for State, Not for Time:**
* **DO:** `(await waitForElement('#load-more')).click(); await waitForElement('div.new-item');` This waits for the *result* of the action.
* **DON'T:** `document.querySelector('#load-more').click(); await new Promise(r => setTimeout(r, 5000));` This is a guess and it will fail.
3. **Target the Action, Not the Artifact:** If you need to reveal content, click the button that reveals it. Don't try to manually change CSS `display` properties, as this can break the page's internal state.
4. **DOM-Awareness is Non-Negotiable:**
* **Shadow DOM:** You MUST use `element.shadowRoot.querySelector(...)` to access elements inside a `#shadow-root (open)`.
* **iFrames:** You MUST use `iframe.contentDocument.querySelector(...)` to interact with elements inside an iframe.
5. **Be Idempotent:** Your script must be harmless if run multiple times. Use `if (document.querySelector(...))` checks to avoid re-doing actions unnecessarily.
6. **Forbidden Techniques:** Never use `document.write()`. It is destructive.
────────────────────────────────────────────────────────
## From Vague Goals to Robust Scripts: Your Duty to Infer and Ensure Reliability
This is your most important responsibility. Users are not automation experts. They will provide incomplete or vague instructions. Your job is to be the expert—to infer their true goal and build a script that is reliable by default. **A vague user prompt must still result in a robust, complete script.**
Study these examples. No matter which query is given, your output must be the single, robust solution.
### 1. Scenario: Basic Search Query
* **High Detail Query:** "Find the search box and search button. Wait for the search box to be visible, click it, clear it, type 'r2d2', click the search button, and then wait for the search results to appear."
* **Medium Detail Query:** "Find the search box and search for 'r2d2'."
* **Low Detail Query:** "Search for r2d2."
**THE CORRECT, ROBUST JAVASCRIPT OUTPUT (for all three queries):**
```javascript
(async () => {
const waitForElement = (selector, timeout = 10000) => new Promise((resolve, reject) => { const el = document.querySelector(selector); if (el) return resolve(el); const observer = new MutationObserver(() => { const el = document.querySelector(selector); if (el) { observer.disconnect(); resolve(el); } }); observer.observe(document.body, { childList: true, subtree: true }); setTimeout(() => { observer.disconnect(); reject(new Error(`Timeout waiting for ${selector}`)); }, timeout); });
try {
const searchInput = await waitForElement('input[type="search"], input[aria-label*="search"]');
searchInput.value = 'r2d2';
searchInput.dispatchEvent(new Event('input', { bubbles: true }));
const searchButton = await waitForElement('button[type="submit"], button[aria-label*="search"]');
searchButton.click();
await waitForElement('div.search-results-container, #search-results');
} catch (e) {
console.error('Search script failed:', e.message);
}
})();
```
### 2. Scenario: Clicking a "Load More" Button
* **High Detail Query:** "Click the button with the text 'Load More'. Afterward, wait for a new item with the class '.product-tile' to show up."
* **Medium Detail Query:** "Click the load more button."
* **Low Detail Query:** "Load more items."
**THE CORRECT, ROBUST JAVASCRIPT OUTPUT:**
```javascript
(async () => {
const loadMoreButton = document.querySelector('button.load-more, [data-testid="load-more"]');
if (loadMoreButton) {
const initialItemCount = document.querySelectorAll('.product-tile').length;
loadMoreButton.click();
const waitForNewItem = (timeout = 8000) => new Promise((resolve, reject) => { const t0 = Date.now(); const check = () => { if (document.querySelectorAll('.product-tile').length > initialItemCount) return resolve(); if (Date.now() - t0 > timeout) return reject(new Error('Timeout waiting for new items to load.')); setTimeout(check, 200); }; check(); });
await waitForNewItem();
}
})();
```
### 3. Scenario: User Authentication (Login)
* **High Detail Query:** "Fill username with 'USER_EMAIL', password with 'USER_PASS', click login, and wait for the dashboard."
* **Medium Detail Query:** "Log in as USER_EMAIL."
* **Low Detail Query:** "Log in."
**THE CORRECT, ROBUST JAVASCRIPT OUTPUT:**
```javascript
(async () => {
if (document.querySelector('[data-testid="logout-button"]')) {
console.log('Already logged in.');
return;
}
const waitForElement = (selector, timeout = 10000) => new Promise((resolve, reject) => { const el = document.querySelector(selector); if (el) return resolve(el); const observer = new MutationObserver(() => { const el = document.querySelector(selector); if (el) { observer.disconnect(); resolve(el); } }); observer.observe(document.body, { childList: true, subtree: true }); setTimeout(() => { observer.disconnect(); reject(new Error(`Timeout waiting for ${selector}`)); }, timeout); });
try {
const userInput = await waitForElement('input[name*="user"], input[name*="email"]');
userInput.value = 'USER_EMAIL';
userInput.dispatchEvent(new Event('input', { bubbles: true }));
const passInput = await waitForElement('input[name*="pass"], input[type="password"]');
passInput.value = 'USER_PASS';
passInput.dispatchEvent(new Event('input', { bubbles: true }));
const submitButton = await waitForElement('button[type="submit"]');
submitButton.click();
await waitForElement('[data-testid="user-dashboard"], #dashboard, .account-page');
} catch (e) {
console.error('Login script failed:', e.message);
}
})();
```
────────────────────────────────────────────────────────
## The Art of High-Specificity Selectors: Your Defense Against Ambiguity
This is your most critical skill for ensuring robustness. **You must assume the provided HTML is only a small fragment of the entire page.** A selector that looks unique in the fragment could be disastrously generic on the full page. Your primary defense is to **anchor your selectors to the most specific, stable parent element available in the given HTML context.**
Think of it as creating a "sandbox" for your selectors.
**Your Guiding Principle:** Start from a unique parent, then find the child.
### Scenario: Selecting a Submit Button within a Login Form
**HTML Snippet Provided:**
```html
<div class="user-auth-module" id="login-widget">
<h2>Member Login</h2>
<form action="/login">
<input name="email" type="email">
<input name="password" type="password">
<button type="submit">Sign In</button>
</form>
</div>
```
* **TERRIBLE (High Risk):** `button[type="submit"]`
* **Why it's bad:** There could be dozens of other forms on the full page (e.g., a newsletter signup, a search bar in the header). This selector is a shot in the dark.
* **BETTER (Lower Risk):** `#login-widget button[type="submit"]`
* **Why it's better:** It's anchored to a unique ID (`#login-widget`). This dramatically reduces the chance of ambiguity.
* **EXCELLENT (Minimal Risk):** `div[id="login-widget"] form button[type="submit"]`
* **Why it's best:** This is a highly specific, descriptive path. It says, "Find the login widget, then the form inside it, and then the submit button inside *that* form." It is virtually guaranteed to be unique and is resilient to minor layout changes within the form.
### Scenario: Selecting a "Add to Cart" Button
**HTML Snippet Provided:**
```html
<section data-testid="product-details-main">
<h1>Awesome T-Shirt</h1>
<div class="product-actions">
<button class="add-to-cart-btn">Add to Cart</button>
</div>
</section>
```
* **TERRIBLE (High Risk):** `.add-to-cart-btn`
* **Why it's bad:** A "related products" section outside this snippet might also use the same class name.
* **EXCELLENT (Minimal Risk):** `[data-testid="product-details-main"] .add-to-cart-btn`
* **Why it's best:** It uses the stable `data-testid` attribute of the parent section as an anchor. This is the most robust pattern.
**Your Mandate:** Always examine the provided HTML for a stable, unique parent (like an element with an `id`, a `data-testid`, or a highly specific combination of classes) and use it as the root of your selectors. **NEVER generate a generic, un-anchored selector if a better, more specific parent is available in the context.**
────────────────────────────────────────────────────────
## Final Output Mandate
1. **CODE ONLY.** Your entire response must be the script body.
2. **NO CHAT.** Do not say "Here is the script" or "This should work."
3. **NO MARKDOWN.** Do not wrap your code in ` ``` ` fences.
4. **NO COMMENTS.** Do not add comments to the final code output, except within the logic where it's a best practice.
5. **SYNTACTICALLY PERFECT.** The script must be a single, self-contained block, immediately executable. Wrap it in `(async () => { ... })();`.
6. **UTF-8, STANDARD QUOTES.** Use `'` for string literals, not `“` or `”`.
You are an engine of automation. Now, receive the user's request and produce the optimal JavaScript."""
"""

View File

@@ -1,35 +0,0 @@
"""
C4A-Script: A domain-specific language for web automation in Crawl4AI
"""
from .c4a_compile import C4ACompiler, compile, validate, compile_file
from .c4a_result import (
CompilationResult,
ValidationResult,
ErrorDetail,
WarningDetail,
ErrorType,
Severity,
Suggestion
)
__all__ = [
# Main compiler
"C4ACompiler",
# Convenience functions
"compile",
"validate",
"compile_file",
# Result types
"CompilationResult",
"ValidationResult",
"ErrorDetail",
"WarningDetail",
# Enums
"ErrorType",
"Severity",
"Suggestion"
]

View File

@@ -1,398 +0,0 @@
"""
Clean C4A-Script API with Result pattern
No exceptions - always returns results
"""
from __future__ import annotations
import pathlib
import re
from typing import Union, List, Optional
# JSON_SCHEMA_BUILDER is still used elsewhere,
# but we now also need the new script-builder prompt.
from ..prompts import GENERATE_JS_SCRIPT_PROMPT, GENERATE_SCRIPT_PROMPT
import logging
import re
from .c4a_result import (
CompilationResult, ValidationResult, ErrorDetail, WarningDetail,
ErrorType, Severity, Suggestion
)
from .c4ai_script import Compiler
from lark.exceptions import UnexpectedToken, UnexpectedCharacters, VisitError
from ..async_configs import LLMConfig
from ..utils import perform_completion_with_backoff
class C4ACompiler:
"""Main compiler with result-based API"""
# Error code mapping
ERROR_CODES = {
"missing_then": "E001",
"missing_paren": "E002",
"missing_comma": "E003",
"missing_endproc": "E004",
"undefined_proc": "E005",
"missing_backticks": "E006",
"invalid_command": "E007",
"syntax_error": "E999"
}
@classmethod
def compile(cls, script: Union[str, List[str]], root: Optional[pathlib.Path] = None) -> CompilationResult:
"""
Compile C4A-Script to JavaScript
Args:
script: C4A-Script as string or list of lines
root: Root directory for includes
Returns:
CompilationResult with success status and JS code or errors
"""
# Normalize input
if isinstance(script, list):
script_text = '\n'.join(script)
script_lines = script
else:
script_text = script
script_lines = script.split('\n')
try:
# Try compilation
compiler = Compiler(root)
js_code = compiler.compile(script_text)
# Success!
result = CompilationResult(
success=True,
js_code=js_code,
metadata={
"lineCount": len(script_lines),
"statementCount": len(js_code)
}
)
# Add any warnings (future feature)
# result.warnings = cls._check_warnings(script_text)
return result
except Exception as e:
# Convert exception to ErrorDetail
error = cls._exception_to_error(e, script_lines)
return CompilationResult(
success=False,
errors=[error],
metadata={
"lineCount": len(script_lines)
}
)
@classmethod
def validate(cls, script: Union[str, List[str]]) -> ValidationResult:
"""
Validate script syntax without generating code
Args:
script: C4A-Script to validate
Returns:
ValidationResult with validity status and any errors
"""
result = cls.compile(script)
return ValidationResult(
valid=result.success,
errors=result.errors,
warnings=result.warnings
)
@classmethod
def compile_file(cls, path: Union[str, pathlib.Path]) -> CompilationResult:
"""
Compile a C4A-Script file
Args:
path: Path to the file
Returns:
CompilationResult
"""
path = pathlib.Path(path)
if not path.exists():
error = ErrorDetail(
type=ErrorType.RUNTIME,
code="E100",
severity=Severity.ERROR,
message=f"File not found: {path}",
line=0,
column=0,
source_line=""
)
return CompilationResult(success=False, errors=[error])
try:
script = path.read_text()
return cls.compile(script, root=path.parent)
except Exception as e:
error = ErrorDetail(
type=ErrorType.RUNTIME,
code="E101",
severity=Severity.ERROR,
message=f"Error reading file: {str(e)}",
line=0,
column=0,
source_line=""
)
return CompilationResult(success=False, errors=[error])
@classmethod
def _exception_to_error(cls, exc: Exception, script_lines: List[str]) -> ErrorDetail:
"""Convert an exception to ErrorDetail"""
if isinstance(exc, UnexpectedToken):
return cls._handle_unexpected_token(exc, script_lines)
elif isinstance(exc, UnexpectedCharacters):
return cls._handle_unexpected_chars(exc, script_lines)
elif isinstance(exc, ValueError):
return cls._handle_value_error(exc, script_lines)
else:
# Generic error
return ErrorDetail(
type=ErrorType.SYNTAX,
code=cls.ERROR_CODES["syntax_error"],
severity=Severity.ERROR,
message=str(exc),
line=1,
column=1,
source_line=script_lines[0] if script_lines else ""
)
@classmethod
def _handle_unexpected_token(cls, exc: UnexpectedToken, script_lines: List[str]) -> ErrorDetail:
"""Handle UnexpectedToken errors"""
line = exc.line
column = exc.column
# Get context lines
source_line = script_lines[line - 1] if 0 < line <= len(script_lines) else ""
line_before = script_lines[line - 2] if line > 1 and line <= len(script_lines) + 1 else None
line_after = script_lines[line] if 0 < line < len(script_lines) else None
# Determine error type and suggestions
if exc.token.type == 'CLICK' and 'THEN' in str(exc.expected):
code = cls.ERROR_CODES["missing_then"]
message = "Missing 'THEN' keyword after IF condition"
suggestions = [
Suggestion(
"Add 'THEN' after the condition",
source_line.replace("CLICK", "THEN CLICK") if source_line else None
)
]
elif exc.token.type == '$END':
code = cls.ERROR_CODES["missing_endproc"]
message = "Unexpected end of script"
suggestions = [
Suggestion("Check for missing ENDPROC"),
Suggestion("Ensure all procedures are properly closed")
]
elif 'RPAR' in str(exc.expected):
code = cls.ERROR_CODES["missing_paren"]
message = "Missing closing parenthesis ')'"
suggestions = [
Suggestion("Add closing parenthesis at the end of the condition")
]
elif 'COMMA' in str(exc.expected):
code = cls.ERROR_CODES["missing_comma"]
message = "Missing comma ',' in command"
suggestions = [
Suggestion("Add comma between arguments")
]
else:
# Check if this might be missing backticks
if exc.token.type == 'NAME' and 'BACKTICK_STRING' in str(exc.expected):
code = cls.ERROR_CODES["missing_backticks"]
message = "Selector must be wrapped in backticks"
suggestions = [
Suggestion(
"Wrap the selector in backticks",
f"`{exc.token.value}`"
)
]
else:
code = cls.ERROR_CODES["syntax_error"]
message = f"Unexpected '{exc.token.value}'"
if exc.expected:
expected_list = [str(e) for e in exc.expected if not str(e).startswith('_')][:3]
if expected_list:
message += f". Expected: {', '.join(expected_list)}"
suggestions = []
return ErrorDetail(
type=ErrorType.SYNTAX,
code=code,
severity=Severity.ERROR,
message=message,
line=line,
column=column,
source_line=source_line,
line_before=line_before,
line_after=line_after,
suggestions=suggestions
)
@classmethod
def _handle_unexpected_chars(cls, exc: UnexpectedCharacters, script_lines: List[str]) -> ErrorDetail:
"""Handle UnexpectedCharacters errors"""
line = exc.line
column = exc.column
source_line = script_lines[line - 1] if 0 < line <= len(script_lines) else ""
# Check for missing backticks
if "CLICK" in source_line and column > source_line.find("CLICK"):
code = cls.ERROR_CODES["missing_backticks"]
message = "Selector must be wrapped in backticks"
suggestions = [
Suggestion(
"Wrap the selector in backticks",
re.sub(r'CLICK\s+([^\s]+)', r'CLICK `\1`', source_line)
)
]
else:
code = cls.ERROR_CODES["syntax_error"]
message = f"Invalid character at position {column}"
suggestions = []
return ErrorDetail(
type=ErrorType.SYNTAX,
code=code,
severity=Severity.ERROR,
message=message,
line=line,
column=column,
source_line=source_line,
suggestions=suggestions
)
@classmethod
def _handle_value_error(cls, exc: ValueError, script_lines: List[str]) -> ErrorDetail:
"""Handle ValueError (runtime errors)"""
message = str(exc)
# Check for undefined procedure
if "Unknown procedure" in message:
proc_match = re.search(r"'([^']+)'", message)
if proc_match:
proc_name = proc_match.group(1)
# Find the line with the procedure call
for i, line in enumerate(script_lines):
if proc_name in line and not line.strip().startswith('PROC'):
return ErrorDetail(
type=ErrorType.RUNTIME,
code=cls.ERROR_CODES["undefined_proc"],
severity=Severity.ERROR,
message=f"Undefined procedure '{proc_name}'",
line=i + 1,
column=line.find(proc_name) + 1,
source_line=line,
suggestions=[
Suggestion(
f"Define the procedure before using it",
f"PROC {proc_name}\n # commands here\nENDPROC"
)
]
)
# Generic runtime error
return ErrorDetail(
type=ErrorType.RUNTIME,
code="E999",
severity=Severity.ERROR,
message=message,
line=1,
column=1,
source_line=script_lines[0] if script_lines else ""
)
@staticmethod
def generate_script(
html: str,
query: str | None = None,
mode: str = "c4a",
llm_config: LLMConfig | None = None,
**completion_kwargs,
) -> str:
"""
One-shot helper that calls the LLM exactly once to convert a
natural-language goal + HTML snippet into either:
1. raw JavaScript (`mode="js"`)
2. Crawl4ai DSL (`mode="c4a"`)
The returned string is guaranteed to be free of markdown wrappers
or explanatory text, ready for direct execution.
"""
if llm_config is None:
llm_config = LLMConfig() # falls back to env vars / defaults
# Build the user chunk
user_prompt = "\n".join(
[
"## GOAL",
"<<goael>>",
(query or "Prepare the page for crawling."),
"<</goal>>",
"",
"## HTML",
"<<html>>",
html[:100000], # guardrail against token blast
"<</html>>",
"",
"## MODE",
mode,
]
)
# Call the LLM with retry/back-off logic
full_prompt = f"{GENERATE_SCRIPT_PROMPT}\n\n{user_prompt}" if mode == "c4a" else f"{GENERATE_JS_SCRIPT_PROMPT}\n\n{user_prompt}"
response = perform_completion_with_backoff(
provider=llm_config.provider,
prompt_with_variables=full_prompt,
api_token=llm_config.api_token,
json_response=False,
base_url=getattr(llm_config, 'base_url', None),
**completion_kwargs,
)
# Extract content from the response
raw_response = response.choices[0].message.content.strip()
# Strip accidental markdown fences (```js … ```)
clean = re.sub(r"^```(?:[a-zA-Z0-9_-]+)?\s*|```$", "", raw_response, flags=re.MULTILINE).strip()
if not clean:
raise RuntimeError("LLM returned empty script.")
return clean
# Convenience functions for direct use
def compile(script: Union[str, List[str]], root: Optional[pathlib.Path] = None) -> CompilationResult:
"""Compile C4A-Script to JavaScript"""
return C4ACompiler.compile(script, root)
def validate(script: Union[str, List[str]]) -> ValidationResult:
"""Validate C4A-Script syntax"""
return C4ACompiler.validate(script)
def compile_file(path: Union[str, pathlib.Path]) -> CompilationResult:
"""Compile C4A-Script file"""
return C4ACompiler.compile_file(path)

View File

@@ -1,219 +0,0 @@
"""
Result classes for C4A-Script compilation
Clean API design with no exceptions
"""
from __future__ import annotations
from dataclasses import dataclass, field
from enum import Enum
from typing import List, Dict, Any, Optional
import json
class ErrorType(Enum):
SYNTAX = "syntax"
SEMANTIC = "semantic"
RUNTIME = "runtime"
class Severity(Enum):
ERROR = "error"
WARNING = "warning"
INFO = "info"
@dataclass
class Suggestion:
"""A suggestion for fixing an error"""
message: str
fix: Optional[str] = None
def to_dict(self) -> dict:
return {
"message": self.message,
"fix": self.fix
}
@dataclass
class ErrorDetail:
"""Detailed information about a compilation error"""
# Core info
type: ErrorType
code: str # E001, E002, etc.
severity: Severity
message: str
# Location
line: int
column: int
# Context
source_line: str
# Optional fields with defaults
end_line: Optional[int] = None
end_column: Optional[int] = None
line_before: Optional[str] = None
line_after: Optional[str] = None
# Help
suggestions: List[Suggestion] = field(default_factory=list)
documentation_url: Optional[str] = None
def to_dict(self) -> dict:
"""Convert to dictionary for JSON serialization"""
return {
"type": self.type.value,
"code": self.code,
"severity": self.severity.value,
"message": self.message,
"location": {
"line": self.line,
"column": self.column,
"endLine": self.end_line,
"endColumn": self.end_column
},
"context": {
"sourceLine": self.source_line,
"lineBefore": self.line_before,
"lineAfter": self.line_after,
"marker": {
"start": self.column - 1,
"length": (self.end_column - self.column) if self.end_column else 1
}
},
"suggestions": [s.to_dict() for s in self.suggestions],
"documentationUrl": self.documentation_url
}
def to_json(self) -> str:
"""Convert to JSON string"""
return json.dumps(self.to_dict(), indent=2)
@property
def formatted_message(self) -> str:
"""Returns the nice text format for terminals"""
lines = []
lines.append(f"\n{'='*60}")
lines.append(f"{self.type.value.title()} Error [{self.code}]")
lines.append(f"{'='*60}")
lines.append(f"Location: Line {self.line}, Column {self.column}")
lines.append(f"Error: {self.message}")
if self.source_line:
marker = " " * (self.column - 1) + "^"
if self.end_column:
marker += "~" * (self.end_column - self.column - 1)
lines.append(f"\nCode:")
if self.line_before:
lines.append(f" {self.line - 1: >3} | {self.line_before}")
lines.append(f" {self.line: >3} | {self.source_line}")
lines.append(f" | {marker}")
if self.line_after:
lines.append(f" {self.line + 1: >3} | {self.line_after}")
if self.suggestions:
lines.append("\nSuggestions:")
for i, suggestion in enumerate(self.suggestions, 1):
lines.append(f" {i}. {suggestion.message}")
if suggestion.fix:
lines.append(f" Fix: {suggestion.fix}")
lines.append("="*60)
return "\n".join(lines)
@property
def simple_message(self) -> str:
"""Returns just the error message without formatting"""
return f"Line {self.line}: {self.message}"
@dataclass
class WarningDetail:
"""Information about a compilation warning"""
code: str
message: str
line: int
column: int
def to_dict(self) -> dict:
return {
"code": self.code,
"message": self.message,
"line": self.line,
"column": self.column
}
@dataclass
class CompilationResult:
"""Result of C4A-Script compilation"""
success: bool
js_code: Optional[List[str]] = None
errors: List[ErrorDetail] = field(default_factory=list)
warnings: List[WarningDetail] = field(default_factory=list)
metadata: Dict[str, Any] = field(default_factory=dict)
def to_dict(self) -> dict:
"""Convert to dictionary for JSON serialization"""
return {
"success": self.success,
"jsCode": self.js_code,
"errors": [e.to_dict() for e in self.errors],
"warnings": [w.to_dict() for w in self.warnings],
"metadata": self.metadata
}
def to_json(self) -> str:
"""Convert to JSON string"""
return json.dumps(self.to_dict(), indent=2)
@property
def has_errors(self) -> bool:
"""Check if there are any errors"""
return len(self.errors) > 0
@property
def has_warnings(self) -> bool:
"""Check if there are any warnings"""
return len(self.warnings) > 0
@property
def first_error(self) -> Optional[ErrorDetail]:
"""Get the first error if any"""
return self.errors[0] if self.errors else None
def __str__(self) -> str:
"""String representation for debugging"""
if self.success:
msg = f"✓ Compilation successful"
if self.js_code:
msg += f" - {len(self.js_code)} statements generated"
if self.warnings:
msg += f" ({len(self.warnings)} warnings)"
return msg
else:
return f"✗ Compilation failed - {len(self.errors)} error(s)"
@dataclass
class ValidationResult:
"""Result of script validation"""
valid: bool
errors: List[ErrorDetail] = field(default_factory=list)
warnings: List[WarningDetail] = field(default_factory=list)
def to_dict(self) -> dict:
return {
"valid": self.valid,
"errors": [e.to_dict() for e in self.errors],
"warnings": [w.to_dict() for w in self.warnings]
}
def to_json(self) -> str:
return json.dumps(self.to_dict(), indent=2)
@property
def first_error(self) -> Optional[ErrorDetail]:
return self.errors[0] if self.errors else None

View File

@@ -1,690 +0,0 @@
"""
2025-06-03
By Unclcode:
C4A-Script Language Documentation
Feeds Crawl4AI via CrawlerRunConfig(js_code=[ ... ]) no core modifications.
"""
from __future__ import annotations
import pathlib, re, sys, textwrap
from dataclasses import dataclass
from typing import Any, Dict, List, Union
from lark import Lark, Transformer, v_args
from lark.exceptions import UnexpectedToken, UnexpectedCharacters, VisitError
# --------------------------------------------------------------------------- #
# Custom Error Classes
# --------------------------------------------------------------------------- #
class C4AScriptError(Exception):
"""Custom error class for C4A-Script compilation errors"""
def __init__(self, message: str, line: int = None, column: int = None,
error_type: str = "Syntax Error", details: str = None):
self.message = message
self.line = line
self.column = column
self.error_type = error_type
self.details = details
super().__init__(self._format_message())
def _format_message(self) -> str:
"""Format a clear error message"""
lines = [f"\n{'='*60}"]
lines.append(f"C4A-Script {self.error_type}")
lines.append(f"{'='*60}")
if self.line:
lines.append(f"Location: Line {self.line}" + (f", Column {self.column}" if self.column else ""))
lines.append(f"Error: {self.message}")
if self.details:
lines.append(f"\nDetails: {self.details}")
lines.append("="*60)
return "\n".join(lines)
@classmethod
def from_exception(cls, exc: Exception, script: Union[str, List[str]]) -> 'C4AScriptError':
"""Create C4AScriptError from another exception"""
script_text = script if isinstance(script, str) else '\n'.join(script)
script_lines = script_text.split('\n')
if isinstance(exc, UnexpectedToken):
# Extract line and column from UnexpectedToken
line = exc.line
column = exc.column
# Get the problematic line
if 0 < line <= len(script_lines):
problem_line = script_lines[line - 1]
marker = " " * (column - 1) + "^"
details = f"\nCode:\n {problem_line}\n {marker}\n"
# Improve error message based on context
if exc.token.type == 'CLICK' and 'THEN' in str(exc.expected):
message = "Missing 'THEN' keyword after IF condition"
elif exc.token.type == '$END':
message = "Unexpected end of script. Check for missing ENDPROC or incomplete commands"
elif 'RPAR' in str(exc.expected):
message = "Missing closing parenthesis ')'"
elif 'COMMA' in str(exc.expected):
message = "Missing comma ',' in command"
else:
message = f"Unexpected '{exc.token}'"
if exc.expected:
expected_list = [str(e) for e in exc.expected if not e.startswith('_')]
if expected_list:
message += f". Expected: {', '.join(expected_list[:3])}"
details += f"Token: {exc.token.type} ('{exc.token.value}')"
else:
message = str(exc)
details = None
return cls(message, line, column, "Syntax Error", details)
elif isinstance(exc, UnexpectedCharacters):
# Extract line and column
line = exc.line
column = exc.column
if 0 < line <= len(script_lines):
problem_line = script_lines[line - 1]
marker = " " * (column - 1) + "^"
details = f"\nCode:\n {problem_line}\n {marker}\n"
message = f"Invalid character or unexpected text at position {column}"
else:
message = str(exc)
details = None
return cls(message, line, column, "Syntax Error", details)
elif isinstance(exc, ValueError):
# Handle runtime errors like undefined procedures
message = str(exc)
# Try to find which line caused the error
if "Unknown procedure" in message:
proc_name = re.search(r"'([^']+)'", message)
if proc_name:
proc_name = proc_name.group(1)
for i, line in enumerate(script_lines, 1):
if proc_name in line and not line.strip().startswith('PROC'):
details = f"\nCode:\n {line.strip()}\n\nMake sure the procedure '{proc_name}' is defined with PROC...ENDPROC"
return cls(f"Undefined procedure '{proc_name}'", i, None, "Runtime Error", details)
return cls(message, None, None, "Runtime Error", None)
else:
# Generic error
return cls(str(exc), None, None, "Compilation Error", None)
# --------------------------------------------------------------------------- #
# 1. Grammar
# --------------------------------------------------------------------------- #
GRAMMAR = r"""
start : line*
?line : command | proc_def | include | comment
command : wait | nav | click_cmd | double_click | right_click | move | drag | scroll
| type | clear | set_input | press | key_down | key_up
| eval_cmd | setvar | proc_call | if_cmd | repeat_cmd
wait : "WAIT" (ESCAPED_STRING|BACKTICK_STRING|NUMBER) NUMBER? -> wait_cmd
nav : "GO" URL -> go
| "RELOAD" -> reload
| "BACK" -> back
| "FORWARD" -> forward
click_cmd : "CLICK" (BACKTICK_STRING|NUMBER NUMBER) -> click
double_click : "DOUBLE_CLICK" (BACKTICK_STRING|NUMBER NUMBER) -> double_click
right_click : "RIGHT_CLICK" (BACKTICK_STRING|NUMBER NUMBER) -> right_click
move : "MOVE" coords -> move
drag : "DRAG" coords coords -> drag
scroll : "SCROLL" DIR NUMBER? -> scroll
type : "TYPE" (ESCAPED_STRING | NAME) -> type
clear : "CLEAR" BACKTICK_STRING -> clear
set_input : "SET" BACKTICK_STRING (ESCAPED_STRING | BACKTICK_STRING | NAME) -> set_input
press : "PRESS" WORD -> press
key_down : "KEY_DOWN" WORD -> key_down
key_up : "KEY_UP" WORD -> key_up
eval_cmd : "EVAL" BACKTICK_STRING -> eval_cmd
setvar : "SETVAR" NAME "=" value -> setvar
proc_call : NAME -> proc_call
proc_def : "PROC" NAME line* "ENDPROC" -> proc_def
include : "USE" ESCAPED_STRING -> include
comment : /#.*/ -> comment
if_cmd : "IF" "(" condition ")" "THEN" command ("ELSE" command)? -> if_cmd
repeat_cmd : "REPEAT" "(" command "," repeat_count ")" -> repeat_cmd
condition : not_cond | exists_cond | js_cond
not_cond : "NOT" condition -> not_cond
exists_cond : "EXISTS" BACKTICK_STRING -> exists_cond
js_cond : BACKTICK_STRING -> js_cond
repeat_count : NUMBER | BACKTICK_STRING
coords : NUMBER NUMBER
value : ESCAPED_STRING | BACKTICK_STRING | NUMBER
DIR : /(UP|DOWN|LEFT|RIGHT)/i
REST : /[^\n]+/
URL : /(http|https):\/\/[^\s]+/
NAME : /\$?[A-Za-z_][A-Za-z0-9_]*/
WORD : /[A-Za-z0-9+]+/
BACKTICK_STRING : /`[^`]*`/
%import common.NUMBER
%import common.ESCAPED_STRING
%import common.WS_INLINE
%import common.NEWLINE
%ignore WS_INLINE
%ignore NEWLINE
"""
# --------------------------------------------------------------------------- #
# 2. IR dataclasses
# --------------------------------------------------------------------------- #
@dataclass
class Cmd:
op: str
args: List[Any]
@dataclass
class Proc:
name: str
body: List[Cmd]
# --------------------------------------------------------------------------- #
# 3. AST → IR
# --------------------------------------------------------------------------- #
@v_args(inline=True)
class ASTBuilder(Transformer):
# helpers
def _strip(self, s):
if s.startswith('"') and s.endswith('"'):
return s[1:-1]
elif s.startswith('`') and s.endswith('`'):
return s[1:-1]
return s
def start(self,*i): return list(i)
def line(self,i): return i
def command(self,i): return i
# WAIT
def wait_cmd(self, rest, timeout=None):
rest_str = str(rest)
# Check if it's a number (including floats)
try:
num_val = float(rest_str)
payload = (num_val, "seconds")
except ValueError:
if rest_str.startswith('"') and rest_str.endswith('"'):
payload = (self._strip(rest_str), "text")
elif rest_str.startswith('`') and rest_str.endswith('`'):
payload = (self._strip(rest_str), "selector")
else:
payload = (rest_str, "selector")
return Cmd("WAIT", [payload, int(timeout) if timeout else None])
# NAV
def go(self,u): return Cmd("GO",[str(u)])
def reload(self): return Cmd("RELOAD",[])
def back(self): return Cmd("BACK",[])
def forward(self): return Cmd("FORWARD",[])
# CLICK, DOUBLE_CLICK, RIGHT_CLICK
def click(self, *args):
return self._handle_click("CLICK", args)
def double_click(self, *args):
return self._handle_click("DBLCLICK", args)
def right_click(self, *args):
return self._handle_click("RIGHTCLICK", args)
def _handle_click(self, op, args):
if len(args) == 1:
# Single argument - backtick string
target = self._strip(str(args[0]))
return Cmd(op, [("selector", target)])
else:
# Two arguments - coordinates
x, y = args
return Cmd(op, [("coords", int(x), int(y))])
# MOVE / DRAG / SCROLL
def coords(self,x,y): return ("coords",int(x),int(y))
def move(self,c): return Cmd("MOVE",[c])
def drag(self,c1,c2): return Cmd("DRAG",[c1,c2])
def scroll(self,dir_tok,amt=None):
return Cmd("SCROLL",[dir_tok.upper(), int(amt) if amt else 500])
# KEYS
def type(self,tok): return Cmd("TYPE",[self._strip(str(tok))])
def clear(self,sel): return Cmd("CLEAR",[self._strip(str(sel))])
def set_input(self,sel,val): return Cmd("SET",[self._strip(str(sel)), self._strip(str(val))])
def press(self,w): return Cmd("PRESS",[str(w)])
def key_down(self,w): return Cmd("KEYDOWN",[str(w)])
def key_up(self,w): return Cmd("KEYUP",[str(w)])
# FLOW
def eval_cmd(self,txt): return Cmd("EVAL",[self._strip(str(txt))])
def setvar(self,n,v):
# v might be a Token or a Tree, extract value properly
if hasattr(v, 'value'):
value = v.value
elif hasattr(v, 'children') and len(v.children) > 0:
value = v.children[0].value
else:
value = str(v)
return Cmd("SETVAR",[str(n), self._strip(value)])
def proc_call(self,n): return Cmd("CALL",[str(n)])
def proc_def(self,n,*body): return Proc(str(n),[b for b in body if isinstance(b,Cmd)])
def include(self,p): return Cmd("INCLUDE",[self._strip(p)])
def comment(self,*_): return Cmd("NOP",[])
# IF-THEN-ELSE and EXISTS
def if_cmd(self, condition, then_cmd, else_cmd=None):
return Cmd("IF", [condition, then_cmd, else_cmd])
def condition(self, cond):
return cond
def not_cond(self, cond):
return ("NOT", cond)
def exists_cond(self, selector):
return ("EXISTS", self._strip(str(selector)))
def js_cond(self, expr):
return ("JS", self._strip(str(expr)))
# REPEAT
def repeat_cmd(self, cmd, count):
return Cmd("REPEAT", [cmd, count])
def repeat_count(self, value):
return str(value)
# --------------------------------------------------------------------------- #
# 4. Compiler
# --------------------------------------------------------------------------- #
class Compiler:
def __init__(self, root: pathlib.Path|None=None):
self.parser = Lark(GRAMMAR,start="start",parser="lalr")
self.root = pathlib.Path(root or ".").resolve()
self.vars: Dict[str,Any] = {}
self.procs: Dict[str,Proc]= {}
def compile(self, text: Union[str, List[str]]) -> List[str]:
# Handle list input by joining with newlines
if isinstance(text, list):
text = '\n'.join(text)
ir = self._parse_with_includes(text)
ir = self._collect_procs(ir)
ir = self._inline_calls(ir)
ir = self._apply_set_vars(ir)
return [self._emit_js(c) for c in ir if isinstance(c,Cmd) and c.op!="NOP"]
# passes
def _parse_with_includes(self,txt,seen=None):
seen=seen or set()
cmds=ASTBuilder().transform(self.parser.parse(txt))
out=[]
for c in cmds:
if isinstance(c,Cmd) and c.op=="INCLUDE":
p=(self.root/c.args[0]).resolve()
if p in seen: raise ValueError(f"Circular include {p}")
seen.add(p); out+=self._parse_with_includes(p.read_text(),seen)
else: out.append(c)
return out
def _collect_procs(self,ir):
out=[]
for i in ir:
if isinstance(i,Proc): self.procs[i.name]=i
else: out.append(i)
return out
def _inline_calls(self,ir):
out=[]
for c in ir:
if isinstance(c,Cmd) and c.op=="CALL":
if c.args[0] not in self.procs:
raise ValueError(f"Unknown procedure {c.args[0]!r}")
out+=self._inline_calls(self.procs[c.args[0]].body)
else: out.append(c)
return out
def _apply_set_vars(self,ir):
def sub(s): return re.sub(r"\$(\w+)",lambda m:str(self.vars.get(m.group(1),m.group(0))) ,s) if isinstance(s,str) else s
out=[]
for c in ir:
if isinstance(c,Cmd):
if c.op=="SETVAR":
# Store variable
self.vars[c.args[0].lstrip('$')]=c.args[1]
else:
# Apply variable substitution to commands that use them
if c.op in("TYPE","EVAL","SET"): c.args=[sub(a) for a in c.args]
out.append(c)
return out
# JS emitter
def _emit_js(self, cmd: Cmd) -> str:
op, a = cmd.op, cmd.args
if op == "GO": return f"window.location.href = '{a[0]}';"
if op == "RELOAD": return "window.location.reload();"
if op == "BACK": return "window.history.back();"
if op == "FORWARD": return "window.history.forward();"
if op == "WAIT":
arg, kind = a[0]
timeout = a[1] or 10
if kind == "seconds":
return f"await new Promise(r=>setTimeout(r,{arg}*1000));"
if kind == "selector":
sel = arg.replace("\\","\\\\").replace("'","\\'")
return textwrap.dedent(f"""
await new Promise((res,rej)=>{{
const max = {timeout*1000}, t0 = performance.now();
const id = setInterval(()=>{{
if(document.querySelector('{sel}')){{clearInterval(id);res();}}
else if(performance.now()-t0>max){{clearInterval(id);rej('WAIT selector timeout');}}
}},100);
}});
""").strip()
if kind == "text":
txt = arg.replace('`', '\\`')
return textwrap.dedent(f"""
await new Promise((res,rej)=>{{
const max={timeout*1000},t0=performance.now();
const id=setInterval(()=>{{
if(document.body.innerText.includes(`{txt}`)){{clearInterval(id);res();}}
else if(performance.now()-t0>max){{clearInterval(id);rej('WAIT text timeout');}}
}},100);
}});
""").strip()
# click-style helpers
def _js_click(sel, evt="click", button=0, detail=1):
sel = sel.replace("'", "\\'")
return textwrap.dedent(f"""
(()=>{{
const el=document.querySelector('{sel}');
if(el){{
el.focus&&el.focus();
el.dispatchEvent(new MouseEvent('{evt}',{{bubbles:true,button:{button},detail:{detail}}}));
}}
}})();
""").strip()
def _js_click_xy(x, y, evt="click", button=0, detail=1):
return textwrap.dedent(f"""
(()=>{{
const el=document.elementFromPoint({x},{y});
if(el){{
el.focus&&el.focus();
el.dispatchEvent(new MouseEvent('{evt}',{{bubbles:true,button:{button},detail:{detail}}}));
}}
}})();
""").strip()
if op in ("CLICK", "DBLCLICK", "RIGHTCLICK"):
evt = {"CLICK":"click","DBLCLICK":"dblclick","RIGHTCLICK":"contextmenu"}[op]
btn = 2 if op=="RIGHTCLICK" else 0
det = 2 if op=="DBLCLICK" else 1
kind,*rest = a[0]
return _js_click_xy(*rest) if kind=="coords" else _js_click(rest[0],evt,btn,det)
if op == "MOVE":
_, x, y = a[0]
return textwrap.dedent(f"""
document.dispatchEvent(new MouseEvent('mousemove',{{clientX:{x},clientY:{y},bubbles:true}}));
""").strip()
if op == "DRAG":
(_, x1, y1), (_, x2, y2) = a
return textwrap.dedent(f"""
(()=>{{
const s=document.elementFromPoint({x1},{y1});
if(!s) return;
s.dispatchEvent(new MouseEvent('mousedown',{{bubbles:true,clientX:{x1},clientY:{y1}}}));
document.dispatchEvent(new MouseEvent('mousemove',{{bubbles:true,clientX:{x2},clientY:{y2}}}));
document.dispatchEvent(new MouseEvent('mouseup', {{bubbles:true,clientX:{x2},clientY:{y2}}}));
}})();
""").strip()
if op == "SCROLL":
dir_, amt = a
dx, dy = {"UP":(0,-amt),"DOWN":(0,amt),"LEFT":(-amt,0),"RIGHT":(amt,0)}[dir_]
return f"window.scrollBy({dx},{dy});"
if op == "TYPE":
txt = a[0].replace("'", "\\'")
return textwrap.dedent(f"""
(()=>{{
const el=document.activeElement;
if(el){{
el.value += '{txt}';
el.dispatchEvent(new Event('input',{{bubbles:true}}));
}}
}})();
""").strip()
if op == "CLEAR":
sel = a[0].replace("'", "\\'")
return textwrap.dedent(f"""
(()=>{{
const el=document.querySelector('{sel}');
if(el && 'value' in el){{
el.value = '';
el.dispatchEvent(new Event('input',{{bubbles:true}}));
el.dispatchEvent(new Event('change',{{bubbles:true}}));
}}
}})();
""").strip()
if op == "SET" and len(a) == 2:
# This is SET for input fields (SET `#field` "value")
sel = a[0].replace("'", "\\'")
val = a[1].replace("'", "\\'")
return textwrap.dedent(f"""
(()=>{{
const el=document.querySelector('{sel}');
if(el && 'value' in el){{
el.value = '';
el.focus&&el.focus();
el.value = '{val}';
el.dispatchEvent(new Event('input',{{bubbles:true}}));
el.dispatchEvent(new Event('change',{{bubbles:true}}));
}}
}})();
""").strip()
if op in ("PRESS","KEYDOWN","KEYUP"):
key = a[0]
evs = {"PRESS":("keydown","keyup"),"KEYDOWN":("keydown",),"KEYUP":("keyup",)}[op]
return ";".join([f"document.dispatchEvent(new KeyboardEvent('{e}',{{key:'{key}',bubbles:true}}))" for e in evs]) + ";"
if op == "EVAL":
return textwrap.dedent(f"""
(()=>{{
try {{
{a[0]};
}} catch (e) {{
console.error('C4A-Script EVAL error:', e);
}}
}})();
""").strip()
if op == "IF":
condition, then_cmd, else_cmd = a
# Generate condition JavaScript
js_condition = self._emit_condition(condition)
# Generate commands - handle both regular commands and procedure calls
then_js = self._handle_cmd_or_proc(then_cmd)
else_js = self._handle_cmd_or_proc(else_cmd) if else_cmd else ""
if else_cmd:
return textwrap.dedent(f"""
if ({js_condition}) {{
{then_js}
}} else {{
{else_js}
}}
""").strip()
else:
return textwrap.dedent(f"""
if ({js_condition}) {{
{then_js}
}}
""").strip()
if op == "REPEAT":
cmd, count = a
# Handle the count - could be number or JS expression
if count.isdigit():
# Simple number
repeat_js = self._handle_cmd_or_proc(cmd)
return textwrap.dedent(f"""
for (let _i = 0; _i < {count}; _i++) {{
{repeat_js}
}}
""").strip()
else:
# JS expression (from backticks)
count_expr = count[1:-1] if count.startswith('`') and count.endswith('`') else count
repeat_js = self._handle_cmd_or_proc(cmd)
return textwrap.dedent(f"""
(()=>{{
const _count = {count_expr};
if (typeof _count === 'number') {{
for (let _i = 0; _i < _count; _i++) {{
{repeat_js}
}}
}} else if (_count) {{
{repeat_js}
}}
}})();
""").strip()
raise ValueError(f"Unhandled op {op}")
def _emit_condition(self, condition):
"""Convert a condition tuple to JavaScript"""
cond_type = condition[0]
if cond_type == "EXISTS":
return f"!!document.querySelector('{condition[1]}')"
elif cond_type == "NOT":
# Recursively handle the negated condition
inner_condition = self._emit_condition(condition[1])
return f"!({inner_condition})"
else: # JS condition
return condition[1]
def _handle_cmd_or_proc(self, cmd):
"""Handle a command that might be a regular command or a procedure call"""
if not cmd:
return ""
if isinstance(cmd, Cmd):
if cmd.op == "CALL":
# Inline the procedure
if cmd.args[0] not in self.procs:
raise ValueError(f"Unknown procedure {cmd.args[0]!r}")
proc_body = self.procs[cmd.args[0]].body
return "\n".join([self._emit_js(c) for c in proc_body if c.op != "NOP"])
else:
return self._emit_js(cmd)
return ""
# --------------------------------------------------------------------------- #
# 5. Helpers + demo
# --------------------------------------------------------------------------- #
def compile_string(script: Union[str, List[str]], *, root: Union[pathlib.Path, None] = None) -> List[str]:
"""Compile C4A-Script from string or list of strings to JavaScript.
Args:
script: C4A-Script as a string or list of command strings
root: Root directory for resolving includes (optional)
Returns:
List of JavaScript command strings
Raises:
C4AScriptError: When compilation fails with detailed error information
"""
try:
return Compiler(root).compile(script)
except Exception as e:
# Wrap the error with better formatting
raise C4AScriptError.from_exception(e, script)
def compile_file(path: pathlib.Path) -> List[str]:
"""Compile C4A-Script from file to JavaScript.
Args:
path: Path to C4A-Script file
Returns:
List of JavaScript command strings
"""
return compile_string(path.read_text(), root=path.parent)
def compile_lines(lines: List[str], *, root: Union[pathlib.Path, None] = None) -> List[str]:
"""Compile C4A-Script from list of lines to JavaScript.
Args:
lines: List of C4A-Script command lines
root: Root directory for resolving includes (optional)
Returns:
List of JavaScript command strings
"""
return compile_string(lines, root=root)
DEMO = """
# quick sanity demo
PROC login
SET `input[name="username"]` $user
SET `input[name="password"]` $pass
CLICK `button.submit`
ENDPROC
SETVAR user = "tom@crawl4ai.com"
SETVAR pass = "hunter2"
GO https://example.com/login
WAIT `input[name="username"]` 10
login
WAIT 3
EVAL `console.log('logged in')`
"""
if __name__ == "__main__":
if len(sys.argv) == 2:
for js in compile_file(pathlib.Path(sys.argv[1])):
print(js)
else:
print("=== DEMO ===")
for js in compile_string(DEMO):
print(js)

View File

@@ -10,20 +10,16 @@ CacheMode = Union['CacheModeType']
CrawlResult = Union['CrawlResultType']
CrawlerHub = Union['CrawlerHubType']
BrowserProfiler = Union['BrowserProfilerType']
# NEW: Add AsyncUrlSeederType
AsyncUrlSeeder = Union['AsyncUrlSeederType']
# Configuration types
BrowserConfig = Union['BrowserConfigType']
CrawlerRunConfig = Union['CrawlerRunConfigType']
HTTPCrawlerConfig = Union['HTTPCrawlerConfigType']
LLMConfig = Union['LLMConfigType']
# NEW: Add SeedingConfigType
SeedingConfig = Union['SeedingConfigType']
# Content scraping types
ContentScrapingStrategy = Union['ContentScrapingStrategyType']
WebScrapingStrategy = Union['WebScrapingStrategyType']
# WebScrapingStrategy = Union['WebScrapingStrategyType']
LXMLWebScrapingStrategy = Union['LXMLWebScrapingStrategyType']
# Proxy types
@@ -98,8 +94,6 @@ if TYPE_CHECKING:
from .models import CrawlResult as CrawlResultType
from .hub import CrawlerHub as CrawlerHubType
from .browser_profiler import BrowserProfiler as BrowserProfilerType
# NEW: Import AsyncUrlSeeder for type checking
from .async_url_seeder import AsyncUrlSeeder as AsyncUrlSeederType
# Configuration imports
from .async_configs import (
@@ -107,14 +101,12 @@ if TYPE_CHECKING:
CrawlerRunConfig as CrawlerRunConfigType,
HTTPCrawlerConfig as HTTPCrawlerConfigType,
LLMConfig as LLMConfigType,
# NEW: Import SeedingConfig for type checking
SeedingConfig as SeedingConfigType,
)
# Content scraping imports
from .content_scraping_strategy import (
ContentScrapingStrategy as ContentScrapingStrategyType,
WebScrapingStrategy as WebScrapingStrategyType,
# WebScrapingStrategy as WebScrapingStrategyType,
LXMLWebScrapingStrategy as LXMLWebScrapingStrategyType,
)
@@ -192,4 +184,4 @@ if TYPE_CHECKING:
def create_llm_config(*args, **kwargs) -> 'LLMConfigType':
from .async_configs import LLMConfig
return LLMConfig(*args, **kwargs)
return LLMConfig(*args, **kwargs)

View File

@@ -1487,8 +1487,29 @@ def extract_metadata_using_lxml(html, doc=None):
head = head[0]
# Title - using XPath
# title = head.xpath(".//title/text()")
# metadata["title"] = title[0].strip() if title else None
# === Title Extraction - New Approach ===
# Attempt to extract <title> using XPath
title = head.xpath(".//title/text()")
metadata["title"] = title[0].strip() if title else None
title = title[0] if title else None
# Fallback: Use .find() in case XPath fails due to malformed HTML
if not title:
title_el = doc.find(".//title")
title = title_el.text if title_el is not None else None
# Final fallback: Use OpenGraph or Twitter title if <title> is missing or empty
if not title:
title_candidates = (
doc.xpath("//meta[@property='og:title']/@content") or
doc.xpath("//meta[@name='twitter:title']/@content")
)
title = title_candidates[0] if title_candidates else None
# Strip and assign title
metadata["title"] = title.strip() if title else None
# Meta description - using XPath with multiple attribute conditions
description = head.xpath('.//meta[@name="description"]/@content')

File diff suppressed because one or more lines are too long

File diff suppressed because it is too large Load Diff

File diff suppressed because one or more lines are too long

View File

@@ -447,7 +447,10 @@
dragNodes: true,
dragView: true,
zoomView: true,
zoomSpeed: 0.15 // Reduced from default 1.0
mouseWheel: {
speed: 0.15, // Reduced from default 1.0
smooth: true // Enable smooth zooming
}
},
nodes: {
font: {

View File

@@ -1,171 +0,0 @@
# Amazon R2D2 Product Search Example
A real-world demonstration of Crawl4AI's multi-step crawling with LLM-generated automation scripts.
## 🎯 What This Example Shows
This example demonstrates advanced Crawl4AI features:
- **LLM-Generated Scripts**: Automatically create C4A-Script from HTML snippets
- **Multi-Step Crawling**: Navigate through multiple pages using session persistence
- **Structured Data Extraction**: Extract product data using JSON CSS schemas
- **Visual Automation**: Watch the browser perform the search (headless=False)
## 🚀 How It Works
### 1. **Script Generation Phase**
The example uses `C4ACompiler.generate_script()` to analyze Amazon's HTML and create:
- **Search Script**: Automates filling the search box and clicking search
- **Extraction Schema**: Defines how to extract product information
### 2. **Crawling Workflow**
```
Homepage → Execute Search Script → Extract Products → Save Results
```
All steps use the same `session_id` to maintain browser state.
### 3. **Data Extraction**
Products are extracted with:
- Title, price, rating, reviews
- Delivery information
- Sponsored/Small Business badges
- Direct product URLs
## 📁 Files
- `amazon_r2d2_search.py` - Main example script
- `header.html` - Amazon search bar HTML (provided)
- `product.html` - Product card HTML (provided)
- **Generated files:**
- `generated_search_script.c4a` - Auto-generated search automation
- `generated_product_schema.json` - Auto-generated extraction rules
- `extracted_products.json` - Final scraped data
- `search_results_screenshot.png` - Visual proof of results
## 🏃 Running the Example
1. **Prerequisites**
```bash
# Ensure Crawl4AI is installed
pip install crawl4ai
# Set up LLM API key (for script generation)
export OPENAI_API_KEY="your-key-here"
```
2. **Run the scraper**
```bash
python amazon_r2d2_search.py
```
3. **Watch the magic!**
- Browser window opens (not headless)
- Navigates to Amazon.com
- Searches for "r2d2"
- Extracts all products
- Saves results to JSON
## 📊 Sample Output
```json
[
{
"title": "Death Star BB8 R2D2 Golf Balls with 20 Printed tees",
"price": "29.95",
"rating": "4.7",
"reviews_count": "184",
"delivery": "FREE delivery Thu, Jun 19",
"url": "https://www.amazon.com/Death-Star-R2D2-Balls-Printed/dp/B081XSYZMS",
"is_sponsored": true,
"small_business": true
},
...
]
```
## 🔍 Key Features Demonstrated
### Session Persistence
```python
# Same session_id across multiple arun() calls
config = CrawlerRunConfig(
session_id="amazon_r2d2_session",
# ... other settings
)
```
### LLM Script Generation
```python
# Generate automation from natural language + HTML
script = C4ACompiler.generate_script(
html=header_html,
query="Find search box, type 'r2d2', click search",
mode="c4a"
)
```
### JSON CSS Extraction
```python
# Structured data extraction with CSS selectors
schema = {
"baseSelector": "[data-component-type='s-search-result']",
"fields": [
{"name": "title", "selector": "h2 a span", "type": "text"},
{"name": "price", "selector": ".a-price-whole", "type": "text"}
]
}
```
## 🛠️ Customization
### Search Different Products
Change the search term in the script generation:
```python
search_goal = """
...
3. Type "star wars lego" into the search box
...
"""
```
### Extract More Data
Add fields to the extraction schema:
```python
"fields": [
# ... existing fields
{"name": "prime", "selector": ".s-prime", "type": "exists"},
{"name": "image_url", "selector": "img.s-image", "type": "attribute", "attribute": "src"}
]
```
### Use Different Sites
Adapt the approach for other e-commerce sites by:
1. Providing their HTML snippets
2. Adjusting the search goals
3. Updating the extraction schema
## 🎓 Learning Points
1. **No Manual Scripting**: LLM generates all automation code
2. **Session Management**: Maintain state across page navigations
3. **Robust Extraction**: Handle dynamic content and multiple products
4. **Error Handling**: Graceful fallbacks if generation fails
## 🐛 Troubleshooting
- **"No products found"**: Check if Amazon's HTML structure changed
- **"Script generation failed"**: Ensure LLM API key is configured
- **"Page timeout"**: Increase wait times in the config
- **"Session lost"**: Ensure same session_id is used consistently
## 📚 Next Steps
- Try searching for different products
- Add pagination to get more results
- Extract product details pages
- Compare prices across different sellers
- Build a price monitoring system
---
This example shows the power of combining LLM intelligence with web automation. The scripts adapt to HTML changes and natural language instructions make automation accessible to everyone!

View File

@@ -1,202 +0,0 @@
#!/usr/bin/env python3
"""
Amazon R2D2 Product Search Example using Crawl4AI
This example demonstrates:
1. Using LLM to generate C4A-Script from HTML snippets
2. Multi-step crawling with session persistence
3. JSON CSS extraction for structured product data
4. Complete workflow: homepage → search → extract products
Requirements:
- Crawl4AI with generate_script support
- LLM API key (configured in environment)
"""
import asyncio
import json
import os
from pathlib import Path
from typing import List, Dict, Any
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
from crawl4ai.script.c4a_compile import C4ACompiler
class AmazonR2D2Scraper:
def __init__(self):
self.base_dir = Path(__file__).parent
self.search_script_path = self.base_dir / "generated_search_script.js"
self.schema_path = self.base_dir / "generated_product_schema.json"
self.results_path = self.base_dir / "extracted_products.json"
self.session_id = "amazon_r2d2_session"
async def generate_search_script(self) -> str:
"""Generate JavaScript for Amazon search interaction"""
print("🔧 Generating search script from header.html...")
# Check if already generated
if self.search_script_path.exists():
print("✅ Using cached search script")
return self.search_script_path.read_text()
# Read the header HTML
header_html = (self.base_dir / "header.html").read_text()
# Generate script using LLM
search_goal = """
Find the search box and search button, then:
1. Wait for the search box to be visible
2. Click on the search box to focus it
3. Clear any existing text
4. Type "r2d2" into the search box
5. Click the search submit button
6. Wait for navigation to complete and search results to appear
"""
try:
script = C4ACompiler.generate_script(
html=header_html,
query=search_goal,
mode="js"
)
# Save for future use
self.search_script_path.write_text(script)
print("✅ Search script generated and saved!")
print(f"📄 Script:\n{script}")
return script
except Exception as e:
print(f"❌ Error generating search script: {e}")
async def generate_product_schema(self) -> Dict[str, Any]:
"""Generate JSON CSS extraction schema from product HTML"""
print("\n🔧 Generating product extraction schema...")
# Check if already generated
if self.schema_path.exists():
print("✅ Using cached extraction schema")
return json.loads(self.schema_path.read_text())
# Read the product HTML
product_html = (self.base_dir / "product.html").read_text()
# Generate extraction schema using LLM
schema_goal = """
Create a JSON CSS extraction schema to extract:
- Product title (from the h2 element)
- Price (the dollar amount)
- Rating (star rating value)
- Number of reviews
- Delivery information
- Product URL (from the main product link)
- Whether it's sponsored
- Small business badge if present
The schema should handle multiple products on a search results page.
"""
try:
# Generate JavaScript that returns the schema
schema = JsonCssExtractionStrategy.generate_schema(
html=product_html,
query=schema_goal,
)
# Save for future use
self.schema_path.write_text(json.dumps(schema, indent=2))
print("✅ Extraction schema generated and saved!")
print(f"📄 Schema fields: {[f['name'] for f in schema['fields']]}")
return schema
except Exception as e:
print(f"❌ Error generating schema: {e}")
async def crawl_amazon(self):
"""Main crawling logic with 2 calls using same session"""
print("\n🚀 Starting Amazon R2D2 product search...")
# Generate scripts and schemas
search_script = await self.generate_search_script()
product_schema = await self.generate_product_schema()
# Configure browser (headless=False to see the action)
browser_config = BrowserConfig(
headless=False,
verbose=True,
viewport_width=1920,
viewport_height=1080
)
async with AsyncWebCrawler(config=browser_config) as crawler:
print("\n📍 Step 1: Navigate to Amazon and search for R2D2")
# FIRST CALL: Navigate to Amazon and execute search
search_config = CrawlerRunConfig(
session_id=self.session_id,
js_code= f"(() => {{ {search_script} }})()", # Execute generated JS
wait_for=".s-search-results", # Wait for search results
extraction_strategy=JsonCssExtractionStrategy(schema=product_schema),
delay_before_return_html=3.0 # Give time for results to load
)
results = await crawler.arun(
url="https://www.amazon.com",
config=search_config
)
if not results.success:
print("❌ Failed to search Amazon")
print(f"Error: {results.error_message}")
return
print("✅ Search completed successfully!")
print("✅ Product extraction completed!")
# Extract and save results
print("\n📍 Extracting product data")
if results[0].extracted_content:
products = json.loads(results[0].extracted_content)
print(f"🔍 Found {len(products)} products in search results")
print(f"✅ Extracted {len(products)} R2D2 products")
# Save results
self.results_path.write_text(
json.dumps(products, indent=2)
)
print(f"💾 Results saved to: {self.results_path}")
# Print sample results
print("\n📊 Sample Results:")
for i, product in enumerate(products[:3], 1):
print(f"\n{i}. {product['title'][:60]}...")
print(f" Price: ${product['price']}")
print(f" Rating: {product['rating']} ({product['number_of_reviews']} reviews)")
print(f" {'🏪 Small Business' if product['small_business_badge'] else ''}")
print(f" {'📢 Sponsored' if product['sponsored'] else ''}")
else:
print("❌ No products extracted")
async def main():
"""Run the Amazon scraper"""
scraper = AmazonR2D2Scraper()
await scraper.crawl_amazon()
print("\n🎉 Amazon R2D2 search example completed!")
print("Check the generated files:")
print(" - generated_search_script.js")
print(" - generated_product_schema.json")
print(" - extracted_products.json")
print(" - search_results_screenshot.png")
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -1,114 +0,0 @@
[
{
"title": "Death Star BB8 R2D2 Golf Balls with 20 Printed tees \u2022 Great Gift IDEA from Moms, DADS and Kids -",
"price": "$29.95",
"rating": "4.7 out of 5 stars",
"number_of_reviews": "184",
"delivery_info": "FREE delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1",
"sponsored": "Sponsored",
"small_business_badge": "Small Business"
},
{
"title": "TEENKON French Press Insulated 304 Stainless Steel Coffee Maker, 32 Oz Robot R2D2 Hand Home Coffee Presser, with Filter Screen for Brew Coffee and Tea (White)",
"price": "$49.99",
"rating": "4.3 out of 5 stars",
"number_of_reviews": "82",
"delivery_info": "Delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDAzNzc4Njg4MDAwMjo6MDo6&url=%2FTEENKON-French-Insulated-Stainless-Presser%2Fdp%2FB0CD3HH5PN%2Fref%3Dsr_1_17_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-17-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored"
},
{
"title": "3D Illusion LED Night Light,7 Colors Gradual Changing Touch Switch USB Table Lamp for Holiday Gifts or Home Decorations (R2-D2)",
"price": "$9.97",
"rating": "4.3 out of 5 stars",
"number_of_reviews": "235",
"delivery_info": "Delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDA0NjMwMTQwODA4MTo6MDo6&url=%2FIllusion-Gradual-Changing-Holiday-Decorations%2Fdp%2FB089NMBKF2%2Fref%3Dsr_1_18_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-18-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored"
},
{
"title": "Paladone Star Wars R2-D2 Headlamp with Droid Sounds, Officially Licensed Disney Star Wars Head Lamp and Reading Light",
"price": "$21.99",
"rating": "4.1 out of 5 stars",
"number_of_reviews": "66",
"delivery_info": "FREE delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDI1NjA0MDQwMTUwMjo6MDo6&url=%2FSounds-Officially-Licensed-Headlamp-Flashlight%2Fdp%2FB09RTDZF8J%2Fref%3Dsr_1_19_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-19-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored"
},
{
"title": "4 Pcs Set Star Wars Kylo Ren BB8 Stormtrooper R2D2 Silicone Travel Luggage Baggage Identification Labels ID Tag for Bag Suitcase Plane Cruise Ships with Belt Strap",
"price": "$16.99",
"rating": "4.7 out of 5 stars",
"number_of_reviews": "3,414",
"delivery_info": "FREE delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDAyMzk3ODkwMzIxMTo6MDo6&url=%2FFinex-Set-Suitcase-Adjustable-Stormtrooper%2Fdp%2FB01D1CBFJS%2Fref%3Dsr_1_24_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-24-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored",
"small_business_badge": "Small Business"
},
{
"title": "Papyrus Star Wars Birthday Card Assortment, Darth Vader, Storm Trooper, and R2-D2 (3-Count)",
"price": "$23.16",
"rating": "4.8 out of 5 stars",
"number_of_reviews": "328",
"delivery_info": "FREE delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDcwNzI4MjA1MzcwMjo6MDo6&url=%2FPapyrus-Birthday-Assortment-Characters-3-Count%2Fdp%2FB07YT2ZPKX%2Fref%3Dsr_1_25_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-25-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored"
},
{
"title": "STAR WARS R2-D2 Artoo 3D Top Motion Lamp, Mood Light | 18 Inches",
"price": "$69.99",
"rating": "4.5 out of 5 stars",
"number_of_reviews": "520",
"delivery_info": "FREE delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDA5NDc3MzczMTQ0MTo6MDo6&url=%2FR2-D2-Artoo-Motion-Light-Inches%2Fdp%2FB08MCWPHQR%2Fref%3Dsr_1_26_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-26-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored"
},
{
"title": "Saturday Park Star Wars Droids Full Sheet Set - 4 Piece 100% Organic Cotton Sheets Features R2-D2 & BB-8 - GOTS & Oeko-TEX Certified (Star Wars Official)",
"price": "$70.00",
"rating": "4.5 out of 5 stars",
"number_of_reviews": "388",
"delivery_info": "FREE delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDAyMzI0NDI5MDQwMjo6MDo6&url=%2FSaturday-Park-Star-Droids-Sheet%2Fdp%2FB0BBSFX4J2%2Fref%3Dsr_1_27_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-27-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored",
"small_business_badge": "1 sustainability feature"
},
{
"title": "AQUARIUS Star Wars R2D2 Action Figure Funky Chunky Novelty Magnet for Refrigerator, Locker, Whiteboard & Game Room Officially Licensed Merchandise & Collectibles",
"price": "$11.94",
"rating": "4.3 out of 5 stars",
"number_of_reviews": "10",
"delivery_info": "FREE delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDA5MDMwMzY5NjEwMjo6MDo6&url=%2FAQUARIUS-Refrigerator-Whiteboard-Merchandise-Collectibles%2Fdp%2FB09W8VKXGC%2Fref%3Dsr_1_32_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-32-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored"
},
{
"title": "STAR WARS C-3PO and R2-D2 Men's Crew Socks 2 Pair Pack",
"price": "$11.95",
"rating": "4.7 out of 5 stars",
"number_of_reviews": "1,272",
"delivery_info": "Delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDAxMDk5NDkyMTg2MTo6MDo6&url=%2FStar-Wars-R2-D2-C-3PO-Socks%2Fdp%2FB0178IU1GY%2Fref%3Dsr_1_33_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-33-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored"
},
{
"title": "Buckle-Down Belt Women's Cinch Star Wars R2D2 Bounding Parts3 White Black Blue Gray Available In Adjustable Sizes",
"price": "$24.95",
"rating": "4.3 out of 5 stars",
"number_of_reviews": "32",
"delivery_info": "FREE delivery",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjMwMDY1OTQ5NTQ4MzkwMjo6MDo6&url=%2FWomens-Cinch-Bounding-Parts3-Inches%2Fdp%2FB07WK7RG4D%2Fref%3Dsr_1_34_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-34-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored",
"small_business_badge": "Small Business"
},
{
"title": "Star Wars R2D2 Metal Head Vintage Disney+ T-Shirt",
"price": "$22.99",
"rating": "4.8 out of 5 stars",
"number_of_reviews": "869",
"product_url": "/sspa/click?ie=UTF8&spc=MToxNDMzMjA0MzA4MzEzMjAxOjE3NDkzMDI3NDY6c3BfbXRmOjIwMDA1OTUyMzgzNDMyMTo6MDo6&url=%2FStar-Wars-Vintage-Graphic-T-Shirt%2Fdp%2FB07H9PSNXS%2Fref%3Dsr_1_35_sspa%3Fdib%3DeyJ2IjoiMSJ9.iiJYY01upNMdD4BNNt8CYLZEIMXulNkcBlKEMJlr_U_h9eSGqChxwcIiCKUbJeEO_plLkXZvB7Yx-v4UDOCdiUFI-sHFgcTznXrP7tdD8xHpRaMKmaBDWMCAFwzPmVcgK_6Q9qIRoN4sp8tunKX26j5EC_8LiK-D5QximGkE8i8f-R5GhSUo__DaSkAP1cnzxUtSESfA8fYfewsZ1iSol9_zohE6r1ZZeawnWHPmDTkLqzCW3uK44EnvJbPFvzMlpiKcs9p9Eh9w5Rc5rrumMihdaWkC63B0cz5jU-S2Ieg._D8d5nv3hOExHPbZ04L-vaC7YwJjEZM-vu5AED5sz0U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749302746%26sr%3D8-35-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9tdGY%26psc%3D1",
"sponsored": "Sponsored",
"small_business_badge": "1 sustainability feature"
}
]

View File

@@ -1,47 +0,0 @@
{
"name": "Amazon Product Search Results",
"baseSelector": "div[data-component-type='s-impression-counter']",
"fields": [
{
"name": "title",
"selector": "h2.a-size-base-plus.a-spacing-none.a-color-base.a-text-normal span",
"type": "text"
},
{
"name": "price",
"selector": "span.a-price > span.a-offscreen",
"type": "text"
},
{
"name": "rating",
"selector": "i.a-icon-star-small span.a-icon-alt",
"type": "text"
},
{
"name": "number_of_reviews",
"selector": "a.a-link-normal.s-underline-text span.a-size-base",
"type": "text"
},
{
"name": "delivery_info",
"selector": "div[data-cy='delivery-recipe'] span.a-color-base",
"type": "text"
},
{
"name": "product_url",
"selector": "a.a-link-normal.s-no-outline",
"type": "attribute",
"attribute": "href"
},
{
"name": "sponsored",
"selector": "span.puis-label-popover-default span.a-color-secondary",
"type": "text"
},
{
"name": "small_business_badge",
"selector": "span.a-size-base.a-color-base",
"type": "text"
}
]
}

View File

@@ -1,9 +0,0 @@
const searchBox = document.querySelector('#twotabsearchtextbox');
const searchButton = document.querySelector('#nav-search-submit-button');
if (searchBox && searchButton) {
searchBox.focus();
searchBox.value = '';
searchBox.value = 'r2d2';
searchButton.click();
}

View File

@@ -1,214 +0,0 @@
<div id="nav-belt" style="width: 100%;">
<div class="nav-left">
<script type="text/javascript">window.navmet.tmp = +new Date();</script>
<div id="nav-logo">
<a href="/ref=nav_logo" id="nav-logo-sprites" class="nav-logo-link nav-progressive-attribute"
aria-label="Amazon" lang="en">
<span class="nav-sprite nav-logo-base"></span>
<span id="logo-ext" class="nav-sprite nav-logo-ext nav-progressive-content"></span>
<span class="nav-logo-locale">.us</span>
</a>
</div>
<script
type="text/javascript">window.navmet.push({ key: 'Logo', end: +new Date(), begin: window.navmet.tmp });</script>
<div id="nav-global-location-slot">
<span id="nav-global-location-data-modal-action" class="a-declarative nav-progressive-attribute"
data-a-modal="{&quot;width&quot;:375, &quot;closeButton&quot;:&quot;true&quot;,&quot;popoverLabel&quot;:&quot;Choose your location&quot;, &quot;ajaxHeaders&quot;:{&quot;anti-csrftoken-a2z&quot;:&quot;hHBwllskaYQrylaW9ifYQIdmqBZOtGdKro0TWb5kDoPKAAAAAGhEMhsAAAAB&quot;}, &quot;name&quot;:&quot;glow-modal&quot;, &quot;url&quot;:&quot;/portal-migration/hz/glow/get-rendered-address-selections?deviceType=desktop&amp;pageType=Gateway&amp;storeContext=NoStoreName&amp;actionSource=desktop-modal&quot;, &quot;footer&quot;:&quot;<span class=\&quot;a-declarative\&quot; data-action=\&quot;a-popover-close\&quot; data-a-popover-close=\&quot;{}\&quot;><span class=\&quot;a-button a-button-primary\&quot;><span class=\&quot;a-button-inner\&quot;><button name=\&quot;glowDoneButton\&quot; class=\&quot;a-button-text\&quot; type=\&quot;button\&quot;>Done</button></span></span></span>&quot;,&quot;header&quot;:&quot;Choose your location&quot;}"
data-action="a-modal">
<a id="nav-global-location-popover-link" role="button" tabindex="0"
class="nav-a nav-a-2 a-popover-trigger a-declarative nav-progressive-attribute" href="">
<div class="nav-sprite nav-progressive-attribute" id="nav-packard-glow-loc-icon"></div>
<div id="glow-ingress-block">
<span class="nav-line-1 nav-progressive-content" id="glow-ingress-line1">
Deliver to
</span>
<span class="nav-line-2 nav-progressive-content" id="glow-ingress-line2">
Malaysia
</span>
</div>
</a>
</span>
<input data-addnewaddress="add-new" id="unifiedLocation1ClickAddress" name="dropdown-selection"
type="hidden" value="add-new" class="nav-progressive-attribute">
<input data-addnewaddress="add-new" id="ubbShipTo" name="dropdown-selection-ubb" type="hidden"
value="add-new" class="nav-progressive-attribute">
<input id="glowValidationToken" name="glow-validation-token" type="hidden"
value="hHBwllskaYQrylaW9ifYQIdmqBZOtGdKro0TWb5kDoPKAAAAAGhEMhsAAAAB" class="nav-progressive-attribute">
<input id="glowDestinationType" name="glow-destination-type" type="hidden" value="COUNTRY"
class="nav-progressive-attribute">
</div>
<div id="nav-global-location-toaster-script-container" class="nav-progressive-content">
<!-- NAVYAAN-GLOW-NAV-TOASTER -->
<script>
P.when('glow-toaster-strings').execute(function (S) {
S.load({ "glow-toaster-address-change-error": "An error has occurred and the address has not been updated. Please try again.", "glow-toaster-unknown-error": "An error has occurred. Please try again." });
});
</script>
<script>
P.when('glow-toaster-manager').execute(function (M) {
M.create({ "pageType": "Gateway", "aisTransitionState": null, "rancorLocationSource": "REALM_DEFAULT" })
});
</script>
</div>
</div>
<div class="nav-fill" id="nav-fill-search">
<script type="text/javascript">window.navmet.tmp = +new Date();</script>
<div id="nav-search">
<div id="nav-bar-left"></div>
<form id="nav-search-bar-form" accept-charset="utf-8" action="/s/ref=nb_sb_noss_1"
class="nav-searchbar nav-progressive-attribute" method="GET" name="site-search" role="search">
<div class="nav-left">
<div id="nav-search-dropdown-card">
<div class="nav-search-scope nav-sprite">
<div class="nav-search-facade" data-value="search-alias=aps">
<span id="nav-search-label-id" class="nav-search-label nav-progressive-content"
style="width: auto;">All</span>
<i class="nav-icon"></i>
</div>
<label id="searchDropdownDescription" for="searchDropdownBox"
class="nav-progressive-attribute" style="display:none">Select the department you want to
search in</label>
<select aria-describedby="searchDropdownDescription"
class="nav-search-dropdown searchSelect nav-progressive-attrubute nav-progressive-search-dropdown"
data-nav-digest="k+fyIAyB82R9jVEmroQ0OWwSW3A=" data-nav-selected="0"
id="searchDropdownBox" name="url" style="display: block; top: 2.5px;" tabindex="0"
title="Search in">
<option selected="selected" value="search-alias=aps">All Departments</option>
<option value="search-alias=arts-crafts-intl-ship">Arts &amp; Crafts</option>
<option value="search-alias=automotive-intl-ship">Automotive</option>
<option value="search-alias=baby-products-intl-ship">Baby</option>
<option value="search-alias=beauty-intl-ship">Beauty &amp; Personal Care</option>
<option value="search-alias=stripbooks-intl-ship">Books</option>
<option value="search-alias=fashion-boys-intl-ship">Boys' Fashion</option>
<option value="search-alias=computers-intl-ship">Computers</option>
<option value="search-alias=deals-intl-ship">Deals</option>
<option value="search-alias=digital-music">Digital Music</option>
<option value="search-alias=electronics-intl-ship">Electronics</option>
<option value="search-alias=fashion-girls-intl-ship">Girls' Fashion</option>
<option value="search-alias=hpc-intl-ship">Health &amp; Household</option>
<option value="search-alias=kitchen-intl-ship">Home &amp; Kitchen</option>
<option value="search-alias=industrial-intl-ship">Industrial &amp; Scientific</option>
<option value="search-alias=digital-text">Kindle Store</option>
<option value="search-alias=luggage-intl-ship">Luggage</option>
<option value="search-alias=fashion-mens-intl-ship">Men's Fashion</option>
<option value="search-alias=movies-tv-intl-ship">Movies &amp; TV</option>
<option value="search-alias=music-intl-ship">Music, CDs &amp; Vinyl</option>
<option value="search-alias=pets-intl-ship">Pet Supplies</option>
<option value="search-alias=instant-video">Prime Video</option>
<option value="search-alias=software-intl-ship">Software</option>
<option value="search-alias=sporting-intl-ship">Sports &amp; Outdoors</option>
<option value="search-alias=tools-intl-ship">Tools &amp; Home Improvement</option>
<option value="search-alias=toys-and-games-intl-ship">Toys &amp; Games</option>
<option value="search-alias=videogames-intl-ship">Video Games</option>
<option value="search-alias=fashion-womens-intl-ship">Women's Fashion</option>
</select>
</div>
</div>
</div>
<div class="nav-fill">
<div class="nav-search-field ">
<label for="twotabsearchtextbox" style="display: none;">Search Amazon</label>
<input type="text" id="twotabsearchtextbox" value="" name="field-keywords" autocomplete="off"
placeholder="Search Amazon" class="nav-input nav-progressive-attribute" dir="auto"
tabindex="0" aria-label="Search Amazon" role="searchbox" aria-autocomplete="list"
aria-controls="sac-autocomplete-results-container" aria-expanded="false"
aria-haspopup="grid" spellcheck="false">
</div>
<div id="nav-iss-attach"></div>
</div>
<div class="nav-right">
<div class="nav-search-submit nav-sprite">
<span id="nav-search-submit-text"
class="nav-search-submit-text nav-sprite nav-progressive-attribute" aria-label="Go">
<input id="nav-search-submit-button" type="submit"
class="nav-input nav-progressive-attribute" value="Go" tabindex="0">
</span>
</div>
</div>
<input type="hidden" id="isscrid" name="crid" value="15O5T5OCG5OZE"><input type="hidden" id="issprefix"
name="sprefix" value="r2d2,aps,588">
</form>
</div>
<script
type="text/javascript">window.navmet.push({ key: 'Search', end: +new Date(), begin: window.navmet.tmp });</script>
</div>
<div class="nav-right">
<script type="text/javascript">window.navmet.tmp = +new Date();</script>
<div id="nav-tools" class="layoutToolbarPadding">
<div class="nav-div" id="icp-nav-flyout">
<a href="/customer-preferences/edit?ie=UTF8&amp;preferencesReturnUrl=%2F&amp;ref_=topnav_lang_ais"
class="nav-a nav-a-2 icp-link-style-2" aria-label="Choose a language for shopping in Amazon United States. The current selection is English (EN).
">
<span class="icp-nav-link-inner">
<span class="nav-line-1">
</span>
<span class="nav-line-2">
<span class="icp-nav-flag icp-nav-flag-us icp-nav-flag-lop" role="img"
aria-label="United States"></span>
<div>EN</div>
</span>
</span>
</a>
<button class="nav-flyout-button nav-icon nav-arrow" aria-label="Expand to Change Language or Country"
tabindex="0" style="visibility: visible;"></button>
</div>
<div class="nav-div" id="nav-link-accountList">
<a href="https://www.amazon.com/ap/signin?openid.pape.max_auth_age=0&amp;openid.return_to=https%3A%2F%2Fwww.amazon.com%2F%3Fref_%3Dnav_ya_signin&amp;openid.identity=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&amp;openid.assoc_handle=usflex&amp;openid.mode=checkid_setup&amp;openid.claimed_id=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&amp;openid.ns=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0"
class="nav-a nav-a-2 nav-progressive-attribute" data-nav-ref="nav_ya_signin"
data-nav-role="signin" data-ux-jq-mouseenter="true" tabindex="0" data-csa-c-type="link"
data-csa-c-slot-id="nav-link-accountList" data-csa-c-content-id="nav_ya_signin"
aria-controls="nav-flyout-accountList" data-csa-c-id="37vs0l-z575id-52hnw3-x34ncp">
<div class="nav-line-1-container"><span id="nav-link-accountList-nav-line-1"
class="nav-line-1 nav-progressive-content">Hello, sign in</span></div>
<span class="nav-line-2 ">Account &amp; Lists
</span>
</a>
<button class="nav-flyout-button nav-icon nav-arrow" aria-label="Expand Account and Lists" tabindex="0"
style="visibility: visible;"></button>
</div>
<a href="/gp/css/order-history?ref_=nav_orders_first" class="nav-a nav-a-2 nav-progressive-attribute"
id="nav-orders" tabindex="0">
<span class="nav-line-1">Returns</span>
<span class="nav-line-2">&amp; Orders<span class="nav-icon nav-arrow"></span></span>
</a>
<a href="/gp/cart/view.html?ref_=nav_cart" aria-label="0 items in cart"
class="nav-a nav-a-2 nav-progressive-attribute" id="nav-cart">
<div id="nav-cart-count-container">
<span id="nav-cart-count" aria-hidden="true"
class="nav-cart-count nav-cart-0 nav-progressive-attribute nav-progressive-content">0</span>
<span class="nav-cart-icon nav-sprite"></span>
</div>
<div id="nav-cart-text-container" class=" nav-progressive-attribute">
<span aria-hidden="true" class="nav-line-1">
</span>
<span aria-hidden="true" class="nav-line-2">
Cart
<span class="nav-icon nav-arrow"></span>
</span>
</div>
</a>
</div>
<script
type="text/javascript">window.navmet.push({ key: 'Tools', end: +new Date(), begin: window.navmet.tmp });</script>
</div>
</div>

View File

@@ -1,206 +0,0 @@
<div class="sg-col-inner">
<div cel_widget_id="MAIN-SEARCH_RESULTS-2"
class="s-widget-container s-spacing-small s-widget-container-height-small celwidget slot=MAIN template=SEARCH_RESULTS widgetId=search-results_1"
data-csa-c-pos="1" data-csa-c-item-id="amzn1.asin.1.B081XSYZMS" data-csa-op-log-render="" data-csa-c-type="item"
data-csa-c-id="dp9zuy-vyww1v-brlmmq-fmgitb" data-cel-widget="MAIN-SEARCH_RESULTS-2">
<div data-component-type="s-impression-logger"
data-component-props="{&quot;percentageShownToFire&quot;:&quot;50&quot;,&quot;batchable&quot;:true,&quot;requiredElementSelector&quot;:&quot;.s-image:visible&quot;,&quot;url&quot;:&quot;https://unagi-na.amazon.com/1/events/com.amazon.eel.SponsoredProductsEventTracking.prod?qualifier=1749299833&amp;id=1740514893473797&amp;widgetName=sp_atf&amp;adId=200067648802798&amp;eventType=1&amp;adIndex=0&quot;}"
class="rush-component s-expand-height" data-component-id="6">
<div data-component-type="s-impression-counter"
data-component-props="{&quot;presenceCounterName&quot;:&quot;sp_delivered&quot;,&quot;testElementSelector&quot;:&quot;.s-image&quot;,&quot;hiddenCounterName&quot;:&quot;sp_hidden&quot;}"
class="rush-component s-featured-result-item s-expand-height" data-component-id="7">
<span class="a-declarative" data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw" data-action="puis-card-container-declarative"
data-csa-c-func-deps="aui-da-puis-card-container-declarative"
data-csa-c-item-id="amzn1.asin.B081XSYZMS" data-csa-c-posx="1" data-csa-c-type="item"
data-csa-c-owner="puis" data-csa-c-id="88w0j1-kcbf5g-80v4i9-96cv88">
<div class="puis-card-container s-card-container s-overflow-hidden aok-relative puis-expand-height puis-include-content-margin puis puis-v2dwi5hq8xzthf26x0gg1mcl2oj s-latency-cf-section puis-card-border"
data-cy="asin-faceout-container">
<div class="a-section a-spacing-base">
<div class="s-product-image-container aok-relative s-text-center s-image-overlay-grey puis-image-overlay-grey s-padding-left-small s-padding-right-small puis-spacing-small s-height-equalized puis puis-v2dwi5hq8xzthf26x0gg1mcl2oj"
data-cy="image-container" style="padding-top: 0px !important;"><span
data-component-type="s-product-image" class="rush-component"
data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw"><a aria-hidden="true"
class="a-link-normal s-no-outline" tabindex="-1"
href="/sspa/click?ie=UTF8&amp;spc=MToxNzQwNTE0ODkzNDczNzk3OjE3NDkyOTk4MzM6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&amp;url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fcrid%3D3C1EXMXN59Q9G%26dib%3DeyJ2IjoiMSJ9.7tBl5bhZh59L9qIPZUe9SLa2fy_HvzboxuQxvrRcAc0VUXayi9fxQFsMLyFplDE9vMkIJbP76AVpa-5-fxhNza3DqhX4tss4NlB49WPi_dA00Hw6O8qK5pDzdetYlhGgOyXOLBe7mTG9oJ5W0wcvQhEVoX9mpJk_SGeqRLWGA0dBSjYCZtiyrY8_B-DP53S7fbYwiSYtq-g7sQDXKVadRpGvUyKq7yxA0SLsU42uvoqSGb0qcd6udL1wbnTEkKmwNjNSb7xIUb-8PyE7DTPMt1ScJksn70sFQMJNkM2aK5M.x9_jYvKPnSibV1d0umUStZBxlSTSXrzVIFKqFzS8c-U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749299833%26sprefix%3Dr2d2%252Caps%252C548%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1">
<div class="a-section aok-relative s-image-square-aspect"><img class="s-image"
src="https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL320_.jpg"
srcset="https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL320_.jpg 1x, https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL480_FMwebp_QL65_.jpg 1.5x, https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL640_FMwebp_QL65_.jpg 2x, https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL800_FMwebp_QL65_.jpg 2.5x, https://m.media-amazon.com/images/I/61kAC69zQUL._AC_UL960_FMwebp_QL65_.jpg 3x"
alt="Sponsored Ad - Death Star BB8 R2D2 Golf Balls with 20 Printed tees • Great Gift IDEA from Moms, DADS and Kids -"
aria-hidden="true" data-image-index="1" data-image-load=""
data-image-latency="s-product-image" data-image-source-density="1">
</div>
</a></span></div>
<div class="a-section a-spacing-small puis-padding-left-small puis-padding-right-small">
<div data-cy="title-recipe"
class="a-section a-spacing-none a-spacing-top-small s-title-instructions-style">
<div class="a-row a-spacing-micro"><span class="a-declarative"
data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw" data-action="a-popover"
data-csa-c-func-deps="aui-da-a-popover"
data-a-popover="{&quot;name&quot;:&quot;sp-info-popover-B081XSYZMS&quot;,&quot;position&quot;:&quot;triggerVertical&quot;,&quot;popoverLabel&quot;:&quot;View Sponsored information or leave ad feedback&quot;,&quot;closeButtonLabel&quot;:&quot;Close popup&quot;,&quot;closeButton&quot;:&quot;true&quot;,&quot;dataStrategy&quot;:&quot;preload&quot;}"
data-csa-c-type="widget" data-csa-c-id="wqddan-z1l67e-lissct-rciw65"><a
href="javascript:void(0)" role="button" style="text-decoration: none;"
class="puis-label-popover puis-sponsored-label-text"><span
class="puis-label-popover-default"><span
aria-label="View Sponsored information or leave ad feedback"
class="a-color-secondary">Sponsored</span></span><span
class="puis-label-popover-hover"><span aria-hidden="true"
class="a-color-base">Sponsored</span></span> <span
class="aok-inline-block puis-sponsored-label-info-icon"></span></a></span>
<div class="a-popover-preload" id="a-popover-sp-info-popover-B081XSYZMS">
<div class="puis puis-v2dwi5hq8xzthf26x0gg1mcl2oj"><span>Youre seeing this
ad based on the products relevance to your search query.</span>
<div class="a-row"><span class="a-declarative"
data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw"
data-action="s-safe-ajax-modal-trigger"
data-csa-c-func-deps="aui-da-s-safe-ajax-modal-trigger"
data-s-safe-ajax-modal-trigger="{&quot;header&quot;:&quot;Leave feedback&quot;,&quot;dataStrategy&quot;:&quot;ajax&quot;,&quot;ajaxUrl&quot;:&quot;/af/sp-loom/feedback-form?pl=%7B%22adPlacementMetaData%22%3A%7B%22searchTerms%22%3A%22cjJkMg%3D%3D%22%2C%22pageType%22%3A%22Search%22%2C%22feedbackType%22%3A%22sponsoredProductsLoom%22%2C%22slotName%22%3A%22TOP%22%7D%2C%22adCreativeMetaData%22%3A%7B%22adProgramId%22%3A1024%2C%22adCreativeDetails%22%3A%5B%7B%22asin%22%3A%22B081XSYZMS%22%2C%22title%22%3A%22Death+Star+BB8+R2D2+Golf+Balls+with+20+Printed+tees+%E2%80%A2+Great+Gift+IDEA+from+Moms%2C+DADS+and+Kids+-%22%2C%22priceInfo%22%3A%7B%22amount%22%3A29.95%2C%22currencyCode%22%3A%22USD%22%7D%2C%22sku%22%3A%22starwars3pk20tees%22%2C%22adId%22%3A%22A03790291PREH7M3Q3SVS%22%2C%22campaignId%22%3A%22A01050612Q0SQZ2PTMGO9%22%2C%22advertiserIdNS%22%3Anull%2C%22selectionSignals%22%3Anull%7D%5D%7D%7D&quot;}"
data-csa-c-type="widget"
data-csa-c-id="ygslsp-ir23ei-7k9x6z-73l1tp"><a
class="a-link-normal s-underline-text s-underline-link-text s-link-style"
href="#"><span>Leave ad feedback</span> </a> </span></div>
</div>
</div>
</div><a class="a-link-normal s-line-clamp-4 s-link-style a-text-normal"
href="/sspa/click?ie=UTF8&amp;spc=MToxNzQwNTE0ODkzNDczNzk3OjE3NDkyOTk4MzM6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&amp;url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fcrid%3D3C1EXMXN59Q9G%26dib%3DeyJ2IjoiMSJ9.7tBl5bhZh59L9qIPZUe9SLa2fy_HvzboxuQxvrRcAc0VUXayi9fxQFsMLyFplDE9vMkIJbP76AVpa-5-fxhNza3DqhX4tss4NlB49WPi_dA00Hw6O8qK5pDzdetYlhGgOyXOLBe7mTG9oJ5W0wcvQhEVoX9mpJk_SGeqRLWGA0dBSjYCZtiyrY8_B-DP53S7fbYwiSYtq-g7sQDXKVadRpGvUyKq7yxA0SLsU42uvoqSGb0qcd6udL1wbnTEkKmwNjNSb7xIUb-8PyE7DTPMt1ScJksn70sFQMJNkM2aK5M.x9_jYvKPnSibV1d0umUStZBxlSTSXrzVIFKqFzS8c-U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749299833%26sprefix%3Dr2d2%252Caps%252C548%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1">
<h2 aria-label="Sponsored Ad - Death Star BB8 R2D2 Golf Balls with 20 Printed tees • Great Gift IDEA from Moms, DADS and Kids -"
class="a-size-base-plus a-spacing-none a-color-base a-text-normal">
<span>Death Star BB8 R2D2 Golf Balls with 20 Printed tees • Great Gift IDEA
from Moms, DADS and Kids -</span></h2>
</a>
</div>
<div data-cy="reviews-block" class="a-section a-spacing-none a-spacing-top-micro">
<div class="a-row a-size-small"><span class="a-declarative"
data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw" data-action="a-popover"
data-csa-c-func-deps="aui-da-a-popover"
data-a-popover="{&quot;position&quot;:&quot;triggerBottom&quot;,&quot;popoverLabel&quot;:&quot;4.7 out of 5 stars, rating details&quot;,&quot;url&quot;:&quot;/review/widgets/average-customer-review/popover/ref=acr_search__popover?ie=UTF8&amp;asin=B081XSYZMS&amp;ref_=acr_search__popover&amp;contextId=search&quot;,&quot;closeButton&quot;:true,&quot;closeButtonLabel&quot;:&quot;&quot;}"
data-csa-c-type="widget" data-csa-c-id="oykdvt-8s1ebj-2kegf2-7ii7tp"><a
aria-label="4.7 out of 5 stars, rating details"
href="javascript:void(0)" role="button"
class="a-popover-trigger a-declarative"><i
data-cy="reviews-ratings-slot" aria-hidden="true"
class="a-icon a-icon-star-small a-star-small-4-5"><span
class="a-icon-alt">4.7 out of 5 stars</span></i><i
class="a-icon a-icon-popover"></i></a></span> <span
data-component-type="s-client-side-analytics" class="rush-component"
data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw" data-component-id="8">
<div style="display: inline-block"
class="s-csa-instrumentation-wrapper alf-search-csa-instrumentation-wrapper"
data-csa-c-type="alf-af-component"
data-csa-c-content-id="alf-customer-ratings-count-component"
data-csa-c-slot-id="alf-reviews" data-csa-op-log-render=""
data-csa-c-layout="GRID" data-csa-c-asin="B081XSYZMS"
data-csa-c-id="6l5wc4-ngelan-hd9x4t-d4a2k7"><a aria-label="184 ratings"
class="a-link-normal s-underline-text s-underline-link-text s-link-style"
href="/sspa/click?ie=UTF8&amp;spc=MToxNzQwNTE0ODkzNDczNzk3OjE3NDkyOTk4MzM6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&amp;url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fcrid%3D3C1EXMXN59Q9G%26dib%3DeyJ2IjoiMSJ9.7tBl5bhZh59L9qIPZUe9SLa2fy_HvzboxuQxvrRcAc0VUXayi9fxQFsMLyFplDE9vMkIJbP76AVpa-5-fxhNza3DqhX4tss4NlB49WPi_dA00Hw6O8qK5pDzdetYlhGgOyXOLBe7mTG9oJ5W0wcvQhEVoX9mpJk_SGeqRLWGA0dBSjYCZtiyrY8_B-DP53S7fbYwiSYtq-g7sQDXKVadRpGvUyKq7yxA0SLsU42uvoqSGb0qcd6udL1wbnTEkKmwNjNSb7xIUb-8PyE7DTPMt1ScJksn70sFQMJNkM2aK5M.x9_jYvKPnSibV1d0umUStZBxlSTSXrzVIFKqFzS8c-U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749299833%26sprefix%3Dr2d2%252Caps%252C548%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1#customerReviews"><span
aria-hidden="true"
class="a-size-base s-underline-text">184</span> </a> </div>
</span></div>
<div class="a-row a-size-base"><span class="a-size-base a-color-secondary">50+
bought in past month</span></div>
</div>
<div data-cy="price-recipe"
class="a-section a-spacing-none a-spacing-top-small s-price-instructions-style">
<div class="a-row a-size-base a-color-base">
<div class="a-row"><span id="price-link" class="aok-offscreen">Price, product
page</span><a aria-describedby="price-link"
class="a-link-normal s-no-hover s-underline-text s-underline-link-text s-link-style a-text-normal"
href="/sspa/click?ie=UTF8&amp;spc=MToxNzQwNTE0ODkzNDczNzk3OjE3NDkyOTk4MzM6c3BfYXRmOjIwMDA2NzY0ODgwMjc5ODo6MDo6&amp;url=%2FDeath-Star-R2D2-Balls-Printed%2Fdp%2FB081XSYZMS%2Fref%3Dsr_1_1_sspa%3Fcrid%3D3C1EXMXN59Q9G%26dib%3DeyJ2IjoiMSJ9.7tBl5bhZh59L9qIPZUe9SLa2fy_HvzboxuQxvrRcAc0VUXayi9fxQFsMLyFplDE9vMkIJbP76AVpa-5-fxhNza3DqhX4tss4NlB49WPi_dA00Hw6O8qK5pDzdetYlhGgOyXOLBe7mTG9oJ5W0wcvQhEVoX9mpJk_SGeqRLWGA0dBSjYCZtiyrY8_B-DP53S7fbYwiSYtq-g7sQDXKVadRpGvUyKq7yxA0SLsU42uvoqSGb0qcd6udL1wbnTEkKmwNjNSb7xIUb-8PyE7DTPMt1ScJksn70sFQMJNkM2aK5M.x9_jYvKPnSibV1d0umUStZBxlSTSXrzVIFKqFzS8c-U%26dib_tag%3Dse%26keywords%3Dr2d2%26qid%3D1749299833%26sprefix%3Dr2d2%252Caps%252C548%26sr%3D8-1-spons%26sp_csd%3Dd2lkZ2V0TmFtZT1zcF9hdGY%26psc%3D1"><span
class="a-price" data-a-size="xl" data-a-color="base"><span
class="a-offscreen">$29.95</span><span aria-hidden="true"><span
class="a-price-symbol">$</span><span
class="a-price-whole">29<span
class="a-price-decimal">.</span></span><span
class="a-price-fraction">95</span></span></span></a></div>
<div class="a-row"></div>
</div>
</div>
<div data-cy="delivery-recipe" class="a-section a-spacing-none a-spacing-top-micro">
<div class="a-row a-size-base a-color-secondary s-align-children-center"><span
aria-label="FREE delivery Thu, Jun 19 to Malaysia on $49 of eligible items"><span
class="a-color-base">FREE delivery </span><span
class="a-color-base a-text-bold">Thu, Jun 19 </span><span
class="a-color-base">to Malaysia on $49 of eligible items</span></span>
</div>
</div>
<div data-cy="certification-recipe"
class="a-section a-spacing-none a-spacing-top-micro">
<div class="a-row">
<div class="a-section a-spacing-none s-align-children-center">
<div class="a-section a-spacing-none s-pc-faceout-container">
<div>
<div class="s-align-children-center"><span class="a-declarative"
data-version-id="v2dwi5hq8xzthf26x0gg1mcl2oj"
data-render-id="r3o8bgr5zt3kmy2jv4su6fn4kyw"
data-action="s-pc-sidesheet-open"
data-csa-c-func-deps="aui-da-s-pc-sidesheet-open"
data-s-pc-sidesheet-open="{&quot;preloadDomId&quot;:&quot;pc-side-sheet-B081XSYZMS&quot;,&quot;popoverLabel&quot;:&quot;Product certifications&quot;,&quot;interactLoggingMetricsList&quot;:[&quot;provenanceCertifications_desktop_sbe_badge&quot;],&quot;closeButtonLabel&quot;:&quot;Close popup&quot;,&quot;dwellMetric&quot;:&quot;provenanceCertifications_desktop_sbe_badge_t&quot;}"
data-csa-c-type="widget"
data-csa-c-id="hdfxi6-bjlgup-5dql15-88t9ao"><a
data-cy="s-pc-faceout-badge"
class="a-link-normal s-no-underline s-pc-badge s-align-children-center aok-block"
href="javascript:void(0)" role="button">
<div
class="a-section s-pc-attribute-pill-text s-margin-bottom-none s-margin-bottom-none aok-block s-pc-certification-faceout">
<span class="faceout-image-view"></span><img alt=""
src="https://m.media-amazon.com/images/I/111mHoVK0kL._SS200_.png"
class="s-image" height="18px" width="18px">
<span class="a-size-base a-color-base">Small
Business</span>
<div
class="s-margin-bottom-none s-pc-sidesheet-chevron aok-nowrap">
<i class="a-icon a-icon-popover aok-align-center"
role="presentation"></i></div>
</div>
</a></span></div>
</div>
</div>
</div>
<div id="pc-side-sheet-B081XSYZMS"
class="a-section puis puis-v2dwi5hq8xzthf26x0gg1mcl2oj aok-hidden">
<div class="a-section s-pc-container-side-sheet">
<div class="s-align-children-center a-spacing-small">
<div class="s-align-children-center s-pc-certification"
role="heading" aria-level="2"><span
class="faceout-image-view"></span>
<div alt="" style="height: 24px; width: 24px;"
class="a-image-wrapper a-lazy-loaded a-manually-loaded s-image"
data-a-image-source="https://m.media-amazon.com/images/I/111mHoVK0kL._SS200_.png">
<noscript><img alt=""
src="https://m.media-amazon.com/images/I/111mHoVK0kL._SS200_.png"
height="24px" width="24px" /></noscript></div> <span
class="a-size-medium-plus a-color-base a-text-bold">Small
Business</span>
</div>
</div>
<div class="a-spacing-medium s-pc-link-container"><span
class="a-size-base a-color-secondary">Shop products from small
business brands sold in Amazons store. Discover more about the
small businesses partnering with Amazon and Amazons commitment
to empowering them.</span> <a
class="a-size-base a-link-normal s-link-style"
href="https://www.amazon.com/b/ref=s9_acss_bw_cg_sbp22c_1e1_w/ref=SBE_navbar_5?pf_rd_r=6W5X52VNZRB7GK1E1VX2&amp;pf_rd_p=56621c3d-cff4-45e1-9bf4-79bbeb8006fc&amp;pf_rd_m=ATVPDKIKX0DER&amp;pf_rd_s=merchandised-search-top-3&amp;pf_rd_t=30901&amp;pf_rd_i=17879387011&amp;node=18018208011">Learn
more</a> </div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</span>
</div>
</div>
</div>
</div>

View File

@@ -1,217 +0,0 @@
"""
C4A-Script API Usage Examples
Shows how to use the new Result-based API in various scenarios
"""
from c4a_compile import compile, validate, compile_file
from c4a_result import CompilationResult, ValidationResult
import json
print("C4A-Script API Usage Examples")
print("=" * 80)
# Example 1: Basic compilation
print("\n1. Basic Compilation")
print("-" * 40)
script = """
GO https://example.com
WAIT 2
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
REPEAT (SCROLL DOWN 300, 3)
"""
result = compile(script)
print(f"Success: {result.success}")
print(f"Statements generated: {len(result.js_code) if result.js_code else 0}")
# Example 2: Error handling
print("\n\n2. Error Handling")
print("-" * 40)
error_script = """
GO https://example.com
IF (EXISTS `.modal`) CLICK `.close`
undefined_procedure
"""
result = compile(error_script)
if not result.success:
# Access error details
error = result.first_error
print(f"Error on line {error.line}: {error.message}")
print(f"Error code: {error.code}")
# Show suggestions if available
if error.suggestions:
print("Suggestions:")
for suggestion in error.suggestions:
print(f" - {suggestion.message}")
# Example 3: Validation only
print("\n\n3. Validation (no code generation)")
print("-" * 40)
validation_script = """
PROC validate_form
IF (EXISTS `#email`) THEN TYPE "test@example.com"
PRESS Tab
ENDPROC
validate_form
"""
validation = validate(validation_script)
print(f"Valid: {validation.valid}")
if validation.errors:
print(f"Errors found: {len(validation.errors)}")
# Example 4: JSON output for UI
print("\n\n4. JSON Output for UI Integration")
print("-" * 40)
ui_script = """
CLICK button.submit
"""
result = compile(ui_script)
if not result.success:
# Get JSON for UI
error_json = result.to_dict()
print("Error data for UI:")
print(json.dumps(error_json["errors"][0], indent=2))
# Example 5: File compilation
print("\n\n5. File Compilation")
print("-" * 40)
# Create a test file
test_file = "test_script.c4a"
with open(test_file, "w") as f:
f.write("""
GO https://example.com
WAIT `.content` 5
CLICK `.main-button`
""")
result = compile_file(test_file)
print(f"File compilation: {'Success' if result.success else 'Failed'}")
if result.success:
print(f"Generated {len(result.js_code)} JavaScript statements")
# Clean up
import os
os.remove(test_file)
# Example 6: Batch processing
print("\n\n6. Batch Processing Multiple Scripts")
print("-" * 40)
scripts = [
"GO https://example1.com\nCLICK `.button`",
"GO https://example2.com\nWAIT 2",
"GO https://example3.com\nINVALID_CMD"
]
results = []
for i, script in enumerate(scripts, 1):
result = compile(script)
results.append(result)
status = "" if result.success else ""
print(f"Script {i}: {status}")
# Summary
successful = sum(1 for r in results if r.success)
print(f"\nBatch result: {successful}/{len(scripts)} successful")
# Example 7: Custom error formatting
print("\n\n7. Custom Error Formatting")
print("-" * 40)
def format_error_for_ide(error):
"""Format error for IDE integration"""
return f"{error.source_line}:{error.line}:{error.column}: {error.type.value}: {error.message} [{error.code}]"
error_script = "IF EXISTS `.button` THEN CLICK `.button`"
result = compile(error_script)
if not result.success:
error = result.first_error
print("IDE format:", format_error_for_ide(error))
print("Simple format:", error.simple_message)
print("Full format:", error.formatted_message)
# Example 8: Working with warnings (future feature)
print("\n\n8. Handling Warnings")
print("-" * 40)
# In the future, we might have warnings
result = compile("GO https://example.com\nWAIT 100") # Very long wait
print(f"Success: {result.success}")
print(f"Warnings: {len(result.warnings)}")
# Example 9: Metadata usage
print("\n\n9. Using Metadata")
print("-" * 40)
complex_script = """
PROC helper1
CLICK `.btn1`
ENDPROC
PROC helper2
CLICK `.btn2`
ENDPROC
GO https://example.com
helper1
helper2
"""
result = compile(complex_script)
if result.success:
print(f"Script metadata:")
for key, value in result.metadata.items():
print(f" {key}: {value}")
# Example 10: Integration patterns
print("\n\n10. Integration Patterns")
print("-" * 40)
# Web API endpoint simulation
def api_compile(request_body):
"""Simulate API endpoint"""
script = request_body.get("script", "")
result = compile(script)
response = {
"status": "success" if result.success else "error",
"data": result.to_dict()
}
return response
# CLI tool simulation
def cli_compile(script, output_format="text"):
"""Simulate CLI tool"""
result = compile(script)
if output_format == "json":
return result.to_json()
elif output_format == "simple":
if result.success:
return f"OK: {len(result.js_code)} statements"
else:
return f"ERROR: {result.first_error.simple_message}"
else:
return str(result)
# Test the patterns
api_response = api_compile({"script": "GO https://example.com"})
print(f"API response status: {api_response['status']}")
cli_output = cli_compile("WAIT 2", "simple")
print(f"CLI output: {cli_output}")
print("\n" + "=" * 80)
print("All examples completed successfully!")

View File

@@ -1,53 +0,0 @@
"""
C4A-Script Hello World
A concise example showing how to use the C4A-Script compiler
"""
from c4a_compile import compile
# Define your C4A-Script
script = """
GO https://example.com
WAIT `#content` 5
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
CLICK `button.submit`
"""
# Compile the script
result = compile(script)
# Check if compilation was successful
if result.success:
# Success! Use the generated JavaScript
print("✅ Compilation successful!")
print(f"Generated {len(result.js_code)} JavaScript statements:\n")
for i, js in enumerate(result.js_code, 1):
print(f"{i}. {js}\n")
# In real usage, you'd pass result.js_code to Crawl4AI:
# config = CrawlerRunConfig(js_code=result.js_code)
else:
# Error! Handle the compilation error
print("❌ Compilation failed!")
# Get the first error (there might be multiple)
error = result.first_error
# Show error details
print(f"Error at line {error.line}, column {error.column}")
print(f"Message: {error.message}")
# Show the problematic code
print(f"\nCode: {error.source_line}")
print(" " * (6 + error.column) + "^")
# Show suggestions if available
if error.suggestions:
print("\n💡 How to fix:")
for suggestion in error.suggestions:
print(f" {suggestion.message}")
# For debugging or logging, you can also get JSON
# error_json = result.to_json()

View File

@@ -1,53 +0,0 @@
"""
C4A-Script Hello World - Error Example
Shows how error handling works
"""
from c4a_compile import compile
# Define a script with an error (missing THEN)
script = """
GO https://example.com
WAIT `#content` 5
IF (EXISTS `.cookie-banner`) CLICK `.accept`
CLICK `button.submit`
"""
# Compile the script
result = compile(script)
# Check if compilation was successful
if result.success:
# Success! Use the generated JavaScript
print("✅ Compilation successful!")
print(f"Generated {len(result.js_code)} JavaScript statements:\n")
for i, js in enumerate(result.js_code, 1):
print(f"{i}. {js}\n")
# In real usage, you'd pass result.js_code to Crawl4AI:
# config = CrawlerRunConfig(js_code=result.js_code)
else:
# Error! Handle the compilation error
print("❌ Compilation failed!")
# Get the first error (there might be multiple)
error = result.first_error
# Show error details
print(f"Error at line {error.line}, column {error.column}")
print(f"Message: {error.message}")
# Show the problematic code
print(f"\nCode: {error.source_line}")
print(" " * (6 + error.column) + "^")
# Show suggestions if available
if error.suggestions:
print("\n💡 How to fix:")
for suggestion in error.suggestions:
print(f" {suggestion.message}")
# For debugging or logging, you can also get JSON
# error_json = result.to_json()

View File

@@ -1,285 +0,0 @@
"""
Demonstration of C4A-Script integration with Crawl4AI
Shows various use cases and features
"""
import asyncio
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
from crawl4ai import c4a_compile, CompilationResult
async def example_basic_usage():
"""Basic C4A-Script usage with Crawl4AI"""
print("\n" + "="*60)
print("Example 1: Basic C4A-Script Usage")
print("="*60)
# Define your automation script
c4a_script = """
# Wait for page to load
WAIT `body` 2
# Handle cookie banner if present
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-btn`
# Scroll down to load more content
SCROLL DOWN 500
WAIT 1
# Click load more button if exists
IF (EXISTS `.load-more`) THEN CLICK `.load-more`
"""
# Create crawler config with C4A script
config = CrawlerRunConfig(
url="https://example.com",
c4a_script=c4a_script,
wait_for="css:.content",
verbose=False
)
print("✅ C4A Script compiled successfully!")
print(f"Generated {len(config.js_code)} JavaScript commands")
# In production, you would run:
# async with AsyncWebCrawler() as crawler:
# result = await crawler.arun(config=config)
async def example_form_filling():
"""Form filling with C4A-Script"""
print("\n" + "="*60)
print("Example 2: Form Filling with C4A-Script")
print("="*60)
# Form automation script
form_script = """
# Set form values
SET email = "test@example.com"
SET message = "This is a test message"
# Fill the form
CLICK `#email-input`
TYPE $email
CLICK `#message-textarea`
TYPE $message
# Submit the form
CLICK `button[type="submit"]`
# Wait for success message
WAIT `.success-message` 10
"""
config = CrawlerRunConfig(
url="https://example.com/contact",
c4a_script=form_script
)
print("✅ Form filling script ready")
print("Script will:")
print(" - Fill email field")
print(" - Fill message textarea")
print(" - Submit form")
print(" - Wait for confirmation")
async def example_dynamic_loading():
"""Handle dynamic content loading"""
print("\n" + "="*60)
print("Example 3: Dynamic Content Loading")
print("="*60)
# Script for infinite scroll or pagination
pagination_script = """
# Initial wait
WAIT `.product-list` 5
# Load all products by clicking "Load More" repeatedly
REPEAT (CLICK `.load-more`, `document.querySelector('.load-more') !== null`)
# Alternative: Scroll to load (infinite scroll)
# REPEAT (SCROLL DOWN 1000, `document.querySelectorAll('.product').length < 100`)
# Extract count
EVAL `console.log('Products loaded: ' + document.querySelectorAll('.product').length)`
"""
config = CrawlerRunConfig(
url="https://example.com/products",
c4a_script=pagination_script,
screenshot=True # Capture final state
)
print("✅ Dynamic loading script ready")
print("Script will load all products by repeatedly clicking 'Load More'")
async def example_multi_step_workflow():
"""Complex multi-step workflow with procedures"""
print("\n" + "="*60)
print("Example 4: Multi-Step Workflow with Procedures")
print("="*60)
# Complex workflow with reusable procedures
workflow_script = """
# Define login procedure
PROC login
CLICK `#username`
TYPE "demo_user"
CLICK `#password`
TYPE "demo_pass"
CLICK `#login-btn`
WAIT `.dashboard` 10
ENDPROC
# Define search procedure
PROC search_product
CLICK `.search-box`
TYPE "laptop"
PRESS Enter
WAIT `.search-results` 5
ENDPROC
# Main workflow
GO https://example.com
login
search_product
# Process results
IF (EXISTS `.no-results`) THEN EVAL `console.log('No products found')`
ELSE REPEAT (CLICK `.add-to-cart`, 3)
"""
# Compile to check for errors
result = c4a_compile(workflow_script)
if result.success:
print("✅ Complex workflow compiled successfully!")
print("Workflow includes:")
print(" - Login procedure")
print(" - Product search")
print(" - Conditional cart additions")
config = CrawlerRunConfig(
url="https://example.com",
c4a_script=workflow_script
)
else:
print("❌ Compilation error:")
error = result.first_error
print(f" Line {error.line}: {error.message}")
async def example_error_handling():
"""Demonstrate error handling"""
print("\n" + "="*60)
print("Example 5: Error Handling")
print("="*60)
# Script with intentional error
bad_script = """
WAIT body 2
CLICK button
IF (EXISTS .modal) CLICK .close
"""
try:
config = CrawlerRunConfig(
url="https://example.com",
c4a_script=bad_script
)
except ValueError as e:
print("✅ Error caught as expected:")
print(f" {e}")
# Fixed version
good_script = """
WAIT `body` 2
CLICK `button`
IF (EXISTS `.modal`) THEN CLICK `.close`
"""
config = CrawlerRunConfig(
url="https://example.com",
c4a_script=good_script
)
print("\n✅ Fixed script compiled successfully!")
async def example_combining_with_extraction():
"""Combine C4A-Script with extraction strategies"""
print("\n" + "="*60)
print("Example 6: C4A-Script + Extraction Strategies")
print("="*60)
from crawl4ai import JsonCssExtractionStrategy
# Script to prepare page for extraction
prep_script = """
# Expand all collapsed sections
REPEAT (CLICK `.expand-btn`, `document.querySelectorAll('.expand-btn:not(.expanded)').length > 0`)
# Load all comments
IF (EXISTS `.load-comments`) THEN CLICK `.load-comments`
WAIT `.comments-section` 5
# Close any popups
IF (EXISTS `.popup-close`) THEN CLICK `.popup-close`
"""
# Define extraction schema
schema = {
"name": "article",
"selector": "article.main",
"fields": {
"title": {"selector": "h1", "type": "text"},
"content": {"selector": ".content", "type": "text"},
"comments": {
"selector": ".comment",
"type": "list",
"fields": {
"author": {"selector": ".author", "type": "text"},
"text": {"selector": ".text", "type": "text"}
}
}
}
}
config = CrawlerRunConfig(
url="https://example.com/article",
c4a_script=prep_script,
extraction_strategy=JsonCssExtractionStrategy(schema),
wait_for="css:.comments-section"
)
print("✅ Combined C4A + Extraction ready")
print("Workflow:")
print(" 1. Expand collapsed sections")
print(" 2. Load comments")
print(" 3. Extract structured data")
async def main():
"""Run all examples"""
print("\n🚀 C4A-Script + Crawl4AI Integration Demo\n")
# Run all examples
await example_basic_usage()
await example_form_filling()
await example_dynamic_loading()
await example_multi_step_workflow()
await example_error_handling()
await example_combining_with_extraction()
print("\n" + "="*60)
print("✅ All examples completed successfully!")
print("="*60)
print("\nTo run actual crawls, uncomment the AsyncWebCrawler sections")
print("or create your own scripts using these examples as templates.")
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -1,89 +0,0 @@
#!/usr/bin/env python3
"""
Hello World Example: LLM-Generated C4A-Script
This example shows how to use the new generate_script() function to automatically
create C4A-Script automation from natural language descriptions and HTML.
"""
from crawl4ai.script.c4a_compile import C4ACompiler
def main():
print("🤖 C4A-Script Generation Hello World")
print("=" * 50)
# Example 1: Simple login form
html = """
<html>
<body>
<form id="login">
<input id="email" type="email" placeholder="Email">
<input id="password" type="password" placeholder="Password">
<button id="submit">Login</button>
</form>
</body>
</html>
"""
goal = "Fill in email 'user@example.com', password 'secret123', and submit the form"
print("📝 Goal:", goal)
print("🌐 HTML: Simple login form")
print()
# Generate C4A-Script
print("🔧 Generated C4A-Script:")
print("-" * 30)
c4a_script = C4ACompiler.generate_script(
html=html,
query=goal,
mode="c4a"
)
print(c4a_script)
print()
# Generate JavaScript
print("🔧 Generated JavaScript:")
print("-" * 30)
js_script = C4ACompiler.generate_script(
html=html,
query=goal,
mode="js"
)
print(js_script)
print()
# Example 2: Simple button click
html2 = """
<html>
<body>
<div class="content">
<h1>Welcome!</h1>
<button id="start-btn" class="primary">Get Started</button>
</div>
</body>
</html>
"""
goal2 = "Click the 'Get Started' button"
print("=" * 50)
print("📝 Goal:", goal2)
print("🌐 HTML: Simple button")
print()
print("🔧 Generated C4A-Script:")
print("-" * 30)
c4a_script2 = C4ACompiler.generate_script(
html=html2,
query=goal2,
mode="c4a"
)
print(c4a_script2)
print()
print("✅ Done! The LLM automatically converted natural language goals")
print(" into executable automation scripts.")
if __name__ == "__main__":
main()

View File

@@ -1,111 +0,0 @@
[
{
"repository_name": "unclecode/crawl4ai",
"repository_owner": "unclecode/crawl4ai",
"repository_url": "/unclecode/crawl4ai",
"description": "\ud83d\ude80\ud83e\udd16Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here:https://discord.gg/jP8KfhDhyN",
"primary_language": "Python",
"star_count": "45.1k",
"topics": [],
"last_updated": "23 hours ago"
},
{
"repository_name": "coleam00/mcp-crawl4ai-rag",
"repository_owner": "coleam00/mcp-crawl4ai-rag",
"repository_url": "/coleam00/mcp-crawl4ai-rag",
"description": "Web Crawling and RAG Capabilities for AI Agents and AI Coding Assistants",
"primary_language": "Python",
"star_count": "748",
"topics": [],
"last_updated": "yesterday"
},
{
"repository_name": "pdichone/crawl4ai-rag-system",
"repository_owner": "pdichone/crawl4ai-rag-system",
"repository_url": "/pdichone/crawl4ai-rag-system",
"primary_language": "Python",
"star_count": "44",
"topics": [],
"last_updated": "on 21 Jan"
},
{
"repository_name": "weidwonder/crawl4ai-mcp-server",
"repository_owner": "weidwonder/crawl4ai-mcp-server",
"repository_url": "/weidwonder/crawl4ai-mcp-server",
"description": "\u7528\u4e8e\u63d0\u4f9b\u7ed9\u672c\u5730\u5f00\u53d1\u8005\u7684 LLM\u7684\u9ad8\u6548\u4e92\u8054\u7f51\u641c\u7d22&\u5185\u5bb9\u83b7\u53d6\u7684MCP Server\uff0c \u8282\u7701\u4f60\u7684token",
"primary_language": "Python",
"star_count": "87",
"topics": [],
"last_updated": "24 days ago"
},
{
"repository_name": "leonardogrig/crawl4ai-deepseek-example",
"repository_owner": "leonardogrig/crawl4ai-deepseek-example",
"repository_url": "/leonardogrig/crawl4ai-deepseek-example",
"primary_language": "Python",
"star_count": "29",
"topics": [],
"last_updated": "on 18 Jan"
},
{
"repository_name": "laurentvv/crawl4ai-mcp",
"repository_owner": "laurentvv/crawl4ai-mcp",
"repository_url": "/laurentvv/crawl4ai-mcp",
"description": "Web crawling tool that integrates with AI assistants via the MCP",
"primary_language": "Python",
"star_count": "10",
"topics": [
{},
{},
{},
{},
{}
],
"last_updated": "on 16 Mar"
},
{
"repository_name": "kaymen99/ai-web-scraper",
"repository_owner": "kaymen99/ai-web-scraper",
"repository_url": "/kaymen99/ai-web-scraper",
"description": "AI web scraper built withCrawl4AIfor extracting structured leads data from websites.",
"primary_language": "Python",
"star_count": "30",
"topics": [
{},
{},
{},
{},
{}
],
"last_updated": "on 13 Feb"
},
{
"repository_name": "atakkant/ai_web_crawler",
"repository_owner": "atakkant/ai_web_crawler",
"repository_url": "/atakkant/ai_web_crawler",
"description": "crawl4ai, DeepSeek, Groq",
"primary_language": "Python",
"star_count": "9",
"topics": [],
"last_updated": "on 19 Feb"
},
{
"repository_name": "Croups/auto-scraper-with-llms",
"repository_owner": "Croups/auto-scraper-with-llms",
"repository_url": "/Croups/auto-scraper-with-llms",
"description": "Web scraping AI that leverages thecrawl4ailibrary to extract structured data from web pages using various large language models (LLMs).",
"primary_language": "Python",
"star_count": "49",
"topics": [],
"last_updated": "on 8 Apr"
},
{
"repository_name": "leonardogrig/crawl4ai_llm_examples",
"repository_owner": "leonardogrig/crawl4ai_llm_examples",
"repository_url": "/leonardogrig/crawl4ai_llm_examples",
"primary_language": "Python",
"star_count": "8",
"topics": [],
"last_updated": "on 29 Jan"
}
]

View File

@@ -1,66 +0,0 @@
{
"name": "GitHub Repository Cards",
"baseSelector": "div.Box-sc-g0xbh4-0.iwUbcA",
"fields": [
{
"name": "repository_name",
"selector": "div.search-title a span",
"type": "text",
"transform": "strip"
},
{
"name": "repository_owner",
"selector": "div.search-title a span",
"type": "text",
"transform": "split",
"pattern": "/"
},
{
"name": "repository_url",
"selector": "div.search-title a",
"type": "attribute",
"attribute": "href",
"transform": "prepend",
"pattern": "https://github.com"
},
{
"name": "description",
"selector": "div.dcdlju span",
"type": "text"
},
{
"name": "primary_language",
"selector": "ul.bZkODq li span[aria-label]",
"type": "text"
},
{
"name": "star_count",
"selector": "ul.bZkODq li a[href*='stargazers'] span",
"type": "text",
"transform": "strip"
},
{
"name": "topics",
"type": "list",
"selector": "div.jgRnBg div a",
"fields": [
{
"name": "topic_name",
"selector": "a",
"type": "text"
}
]
},
{
"name": "last_updated",
"selector": "ul.bZkODq li span[title]",
"type": "text"
},
{
"name": "has_sponsor_button",
"selector": "button[aria-label*='Sponsor']",
"type": "text",
"transform": "exists"
}
]
}

View File

@@ -1,39 +0,0 @@
(async () => {
const waitForElement = (selector, timeout = 10000) => new Promise((resolve, reject) => {
const el = document.querySelector(selector);
if (el) return resolve(el);
const observer = new MutationObserver(() => {
const el = document.querySelector(selector);
if (el) {
observer.disconnect();
resolve(el);
}
});
observer.observe(document.body, { childList: true, subtree: true });
setTimeout(() => {
observer.disconnect();
reject(new Error(`Timeout waiting for ${selector}`));
}, timeout);
});
try {
const searchInput = await waitForElement('#adv_code_search input[type="text"]');
searchInput.value = 'crawl4AI';
searchInput.dispatchEvent(new Event('input', { bubbles: true }));
const languageSelect = await waitForElement('#search_language');
languageSelect.value = 'Python';
languageSelect.dispatchEvent(new Event('change', { bubbles: true }));
const starsInput = await waitForElement('#search_stars');
starsInput.value = '>10000';
starsInput.dispatchEvent(new Event('input', { bubbles: true }));
const searchButton = await waitForElement('#adv_code_search button[type="submit"]');
searchButton.click();
await waitForElement('.codesearch-results, #search-results');
} catch (e) {
console.error('Search script failed:', e.message);
}
})();

View File

@@ -1,211 +0,0 @@
#!/usr/bin/env python3
"""
GitHub Advanced Search Example using Crawl4AI
This example demonstrates:
1. Using LLM to generate C4A-Script from HTML snippets
2. Single arun() call with navigation, search form filling, and extraction
3. JSON CSS extraction for structured repository data
4. Complete workflow: navigate → fill form → submit → extract results
Requirements:
- Crawl4AI with generate_script support
- LLM API key (configured in environment)
"""
import asyncio
import json
import os
from pathlib import Path
from typing import List, Dict, Any
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
from crawl4ai.script.c4a_compile import C4ACompiler
class GitHubSearchScraper:
def __init__(self):
self.base_dir = Path(__file__).parent
self.search_script_path = self.base_dir / "generated_search_script.js"
self.schema_path = self.base_dir / "generated_result_schema.json"
self.results_path = self.base_dir / "extracted_repositories.json"
self.session_id = "github_search_session"
async def generate_search_script(self) -> str:
"""Generate JavaScript for GitHub advanced search interaction"""
print("🔧 Generating search script from search_form.html...")
# Check if already generated
if self.search_script_path.exists():
print("✅ Using cached search script")
return self.search_script_path.read_text()
# Read the search form HTML
search_form_html = (self.base_dir / "search_form.html").read_text()
# Generate script using LLM
search_goal = """
Search for crawl4AI repositories written in Python with more than 10000 stars:
1. Wait for the main search input to be visible
2. Type "crawl4AI" into the main search box
3. Select "Python" from the language dropdown (#search_language)
4. Type ">10000" into the stars input field (#search_stars)
5. Click the search button to submit the form
6. Wait for the search results to appear
"""
try:
script = C4ACompiler.generate_script(
html=search_form_html,
query=search_goal,
mode="js"
)
# Save for future use
self.search_script_path.write_text(script)
print("✅ Search script generated and saved!")
print(f"📄 Script preview:\n{script[:500]}...")
return script
except Exception as e:
print(f"❌ Error generating search script: {e}")
raise
async def generate_result_schema(self) -> Dict[str, Any]:
"""Generate JSON CSS extraction schema from result HTML"""
print("\n🔧 Generating result extraction schema...")
# Check if already generated
if self.schema_path.exists():
print("✅ Using cached extraction schema")
return json.loads(self.schema_path.read_text())
# Read the result HTML
result_html = (self.base_dir / "result.html").read_text()
# Generate extraction schema using LLM
schema_goal = """
Create a JSON CSS extraction schema to extract from each repository card:
- Repository name (the repository name only, not including owner)
- Repository owner (organization or username)
- Repository URL (full GitHub URL)
- Description
- Primary programming language
- Star count (numeric value)
- Topics/tags (array of topic names)
- Last updated (time ago string)
- Whether it has a sponsor button
The schema should handle multiple repository results on the search results page.
"""
try:
# Generate schema
schema = JsonCssExtractionStrategy.generate_schema(
html=result_html,
query=schema_goal,
)
# Save for future use
self.schema_path.write_text(json.dumps(schema, indent=2))
print("✅ Extraction schema generated and saved!")
print(f"📄 Schema fields: {[f['name'] for f in schema['fields']]}")
return schema
except Exception as e:
print(f"❌ Error generating schema: {e}")
raise
async def crawl_github(self):
"""Main crawling logic with single arun() call"""
print("\n🚀 Starting GitHub repository search...")
# Generate scripts and schemas
search_script = await self.generate_search_script()
result_schema = await self.generate_result_schema()
# Configure browser (headless=False to see the action)
browser_config = BrowserConfig(
headless=False,
verbose=True,
viewport_width=1920,
viewport_height=1080
)
async with AsyncWebCrawler(config=browser_config) as crawler:
print("\n📍 Navigating to GitHub advanced search and executing search...")
# Single call: Navigate, execute search, and extract results
search_config = CrawlerRunConfig(
session_id=self.session_id,
js_code=search_script, # Execute generated JS
# wait_for="[data-testid='results-list']", # Wait for search results
wait_for=".Box-sc-g0xbh4-0.iwUbcA", # Wait for search results
extraction_strategy=JsonCssExtractionStrategy(schema=result_schema),
delay_before_return_html=3.0, # Give time for results to fully load
cache_mode=CacheMode.BYPASS # Don't cache for fresh results
)
result = await crawler.arun(
url="https://github.com/search/advanced",
config=search_config
)
if not result.success:
print("❌ Failed to search GitHub")
print(f"Error: {result.error_message}")
return
print("✅ Search and extraction completed successfully!")
# Extract and save results
if result.extracted_content:
repositories = json.loads(result.extracted_content)
print(f"\n🔍 Found {len(repositories)} repositories matching criteria")
# Save results
self.results_path.write_text(
json.dumps(repositories, indent=2)
)
print(f"💾 Results saved to: {self.results_path}")
# Print sample results
print("\n📊 Sample Results:")
for i, repo in enumerate(repositories[:5], 1):
print(f"\n{i}. {repo.get('owner', 'Unknown')}/{repo.get('name', 'Unknown')}")
print(f" Description: {repo.get('description', 'No description')[:80]}...")
print(f" Language: {repo.get('language', 'Unknown')}")
print(f" Stars: {repo.get('stars', 'Unknown')}")
print(f" Updated: {repo.get('last_updated', 'Unknown')}")
if repo.get('topics'):
print(f" Topics: {', '.join(repo['topics'][:5])}")
print(f" URL: {repo.get('url', 'Unknown')}")
else:
print("❌ No repositories extracted")
# Save screenshot for reference
if result.screenshot:
screenshot_path = self.base_dir / "search_results_screenshot.png"
with open(screenshot_path, "wb") as f:
f.write(result.screenshot)
print(f"\n📸 Screenshot saved to: {screenshot_path}")
async def main():
"""Run the GitHub search scraper"""
scraper = GitHubSearchScraper()
await scraper.crawl_github()
print("\n🎉 GitHub search example completed!")
print("Check the generated files:")
print(" - generated_search_script.js")
print(" - generated_result_schema.json")
print(" - extracted_repositories.json")
print(" - search_results_screenshot.png")
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -1,54 +0,0 @@
<div class="Box-sc-g0xbh4-0 iwUbcA"><div class="Box-sc-g0xbh4-0 cSURfY"><div class="Box-sc-g0xbh4-0 gPrlij"><h3 class="Box-sc-g0xbh4-0 cvnppv"><div class="Box-sc-g0xbh4-0 kYLlPM"><div class="Box-sc-g0xbh4-0 eurdCD"><img data-component="Avatar" class="prc-Avatar-Avatar-ZRS-m" alt="" data-square="" width="20" height="20" src="https://github.com/TheAlgorithms.png?size=40" data-testid="github-avatar" style="--avatarSize-regular: 20px;"></div><div class="Box-sc-g0xbh4-0 MHoGG search-title"><a class="prc-Link-Link-85e08" href="/TheAlgorithms/Python"><span class="Box-sc-g0xbh4-0 kzfhBO search-match prc-Text-Text-0ima0">TheAlgorithms/<em>Python</em></span></a></div></div></h3><div class="Box-sc-g0xbh4-0 dcdlju"><span class="Box-sc-g0xbh4-0 gKFdvh search-match prc-Text-Text-0ima0">All Algorithms implemented in <em>Python</em></span></div><div class="Box-sc-g0xbh4-0 jgRnBg"><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/python">python</a></div><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/education">education</a></div><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/algorithm">algorithm</a></div><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/practice">practice</a></div><div><a class="Box-sc-g0xbh4-0 hIVEGR prc-Link-Link-85e08" href="/topics/interview">interview</a></div></div><ul class="Box-sc-g0xbh4-0 bZkODq"><li class="Box-sc-g0xbh4-0 eCfCAC"><div class="Box-sc-g0xbh4-0 hjDqIa"><div class="Box-sc-g0xbh4-0 fwSYsx"></div></div><span aria-label="Python language">Python</span></li><span class="Box-sc-g0xbh4-0 eXQoFa prc-Text-Text-0ima0" aria-hidden="true">·</span><li class="Box-sc-g0xbh4-0 eCfCAC"><a class="Box-sc-g0xbh4-0 iPuHRc prc-Link-Link-85e08" href="/TheAlgorithms/Python/stargazers" aria-label="201161 stars"><svg aria-hidden="true" focusable="false" class="octicon octicon-star Octicon-sc-9kayk9-0 kHVtWu" viewBox="0 0 16 16" width="16" height="16" fill="currentColor" display="inline-block" overflow="visible" style="vertical-align: text-bottom;"><path d="M8 .25a.75.75 0 0 1 .673.418l1.882 3.815 4.21.612a.75.75 0 0 1 .416 1.279l-3.046 2.97.719 4.192a.751.751 0 0 1-1.088.791L8 12.347l-3.766 1.98a.75.75 0 0 1-1.088-.79l.72-4.194L.818 6.374a.75.75 0 0 1 .416-1.28l4.21-.611L7.327.668A.75.75 0 0 1 8 .25Zm0 2.445L6.615 5.5a.75.75 0 0 1-.564.41l-3.097.45 2.24 2.184a.75.75 0 0 1 .216.664l-.528 3.084 2.769-1.456a.75.75 0 0 1 .698 0l2.77 1.456-.53-3.084a.75.75 0 0 1 .216-.664l2.24-2.183-3.096-.45a.75.75 0 0 1-.564-.41L8 2.694Z"></path></svg><span class="prc-Text-Text-0ima0">201k</span></a></li><span class="Box-sc-g0xbh4-0 eXQoFa prc-Text-Text-0ima0" aria-hidden="true">·</span><li class="Box-sc-g0xbh4-0 eCfCAC"><span>Updated <div title="3 Jun 2025, 01:57 GMT+8" class="Truncate__StyledTruncate-sc-23o1d2-0 liVpTx"><span class="prc-Text-Text-0ima0" title="3 Jun 2025, 01:57 GMT+8">4 days ago</span></div></span></li></ul></div><div class="Box-sc-g0xbh4-0 gtlRHe"><div class="Box-sc-g0xbh4-0 fvaNTI"><button type="button" class="prc-Button-ButtonBase-c50BI" data-loading="false" data-size="small" data-variant="default" aria-describedby=":r1c:-loading-announcement"><span data-component="buttonContent" data-align="center" class="prc-Button-ButtonContent-HKbr-"><span data-component="leadingVisual" class="prc-Button-Visual-2epfX prc-Button-VisualWrap-Db-eB"><svg aria-hidden="true" focusable="false" class="octicon octicon-star" viewBox="0 0 16 16" width="16" height="16" fill="currentColor" display="inline-block" overflow="visible" style="vertical-align: text-bottom;"><path d="M8 .25a.75.75 0 0 1 .673.418l1.882 3.815 4.21.612a.75.75 0 0 1 .416 1.279l-3.046 2.97.719 4.192a.751.751 0 0 1-1.088.791L8 12.347l-3.766 1.98a.75.75 0 0 1-1.088-.79l.72-4.194L.818 6.374a.75.75 0 0 1 .416-1.28l4.21-.611L7.327.668A.75.75 0 0 1 8 .25Zm0 2.445L6.615 5.5a.75.75 0 0 1-.564.41l-3.097.45 2.24 2.184a.75.75 0 0 1 .216.664l-.528 3.084 2.769-1.456a.75.75 0 0 1 .698 0l2.77 1.456-.53-3.084a.75.75 0 0 1 .216-.664l2.24-2.183-3.096-.45a.75.75 0 0 1-.564-.41L8 2.694Z"></path></svg></span><span data-component="text" class="prc-Button-Label-pTQ3x">Star</span></span></button></div><div class="Box-sc-g0xbh4-0 llZEgI"><div class="Box-sc-g0xbh4-0"> <button id="dialog-show-funding-links-modal-TheAlgorithms-Python" aria-label="Sponsor TheAlgorithms/Python" data-show-dialog-id="funding-links-modal-TheAlgorithms-Python" type="button" data-view-component="true" class="Button--secondary Button--small Button"> <span class="Button-content">
<span class="Button-label"><svg aria-hidden="true" height="16" viewBox="0 0 16 16" version="1.1" width="16" data-view-component="true" class="octicon octicon-heart icon-sponsor mr-1 color-fg-sponsors">
<path d="m8 14.25.345.666a.75.75 0 0 1-.69 0l-.008-.004-.018-.01a7.152 7.152 0 0 1-.31-.17 22.055 22.055 0 0 1-3.434-2.414C2.045 10.731 0 8.35 0 5.5 0 2.836 2.086 1 4.25 1 5.797 1 7.153 1.802 8 3.02 8.847 1.802 10.203 1 11.75 1 13.914 1 16 2.836 16 5.5c0 2.85-2.045 5.231-3.885 6.818a22.066 22.066 0 0 1-3.744 2.584l-.018.01-.006.003h-.002ZM4.25 2.5c-1.336 0-2.75 1.164-2.75 3 0 2.15 1.58 4.144 3.365 5.682A20.58 20.58 0 0 0 8 13.393a20.58 20.58 0 0 0 3.135-2.211C12.92 9.644 14.5 7.65 14.5 5.5c0-1.836-1.414-3-2.75-3-1.373 0-2.609.986-3.029 2.456a.749.749 0 0 1-1.442 0C6.859 3.486 5.623 2.5 4.25 2.5Z"></path>
</svg> <span data-view-component="true">Sponsor</span></span>
</span>
</button>
<dialog-helper>
<dialog id="funding-links-modal-TheAlgorithms-Python" aria-modal="true" aria-labelledby="funding-links-modal-TheAlgorithms-Python-title" aria-describedby="funding-links-modal-TheAlgorithms-Python-description" data-view-component="true" class="Overlay Overlay-whenNarrow Overlay--size-medium Overlay--motion-scaleFade Overlay--disableScroll">
<div data-view-component="true" class="Overlay-header">
<div class="Overlay-headerContentWrap">
<div class="Overlay-titleWrap">
<h1 class="Overlay-title " id="funding-links-modal-TheAlgorithms-Python-title">
Sponsor TheAlgorithms/Python
</h1>
</div>
<div class="Overlay-actionWrap">
<button data-close-dialog-id="funding-links-modal-TheAlgorithms-Python" aria-label="Close" type="button" data-view-component="true" class="close-button Overlay-closeButton"><svg aria-hidden="true" height="16" viewBox="0 0 16 16" version="1.1" width="16" data-view-component="true" class="octicon octicon-x">
<path d="M3.72 3.72a.75.75 0 0 1 1.06 0L8 6.94l3.22-3.22a.749.749 0 0 1 1.275.326.749.749 0 0 1-.215.734L9.06 8l3.22 3.22a.749.749 0 0 1-.326 1.275.749.749 0 0 1-.734-.215L8 9.06l-3.22 3.22a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042L6.94 8 3.72 4.78a.75.75 0 0 1 0-1.06Z"></path>
</svg></button>
</div>
</div>
</div>
<scrollable-region data-labelled-by="funding-links-modal-TheAlgorithms-Python-title" data-catalyst="" style="overflow: auto;">
<div data-view-component="true" class="Overlay-body"> <div class="text-left f5">
<div class="pt-3 color-bg-overlay">
<h5 class="flex-auto mb-3 mt-0">External links</h5>
<div class="d-flex mb-3">
<div class="circle mr-2 border d-flex flex-justify-center flex-items-center flex-shrink-0" style="width:24px;height:24px;">
<img width="16" height="16" class="octicon rounded-2 d-block" alt="liberapay" src="https://github.githubassets.com/assets/liberapay-48108ded7267.svg">
</div>
<div class="flex-auto min-width-0">
<a target="_blank" data-ga-click="Dashboard, click, Nav menu - item:org-profile context:organization" data-hydro-click="{&quot;event_type&quot;:&quot;sponsors.repo_funding_links_link_click&quot;,&quot;payload&quot;:{&quot;platform&quot;:{&quot;platform_type&quot;:&quot;LIBERAPAY&quot;,&quot;platform_url&quot;:&quot;https://liberapay.com/TheAlgorithms&quot;},&quot;platforms&quot;:[{&quot;platform_type&quot;:&quot;LIBERAPAY&quot;,&quot;platform_url&quot;:&quot;https://liberapay.com/TheAlgorithms&quot;}],&quot;repo_id&quot;:63476337,&quot;owner_id&quot;:20487725,&quot;user_id&quot;:12494079,&quot;originating_url&quot;:&quot;https://github.com/TheAlgorithms/Python/funding_links?fragment=1&quot;}}" data-hydro-click-hmac="123b5aa7d5ffff5ef0530f8e7fbaebcb564e8de1af26f1b858a19b0e1d4f9e5f" href="https://liberapay.com/TheAlgorithms"><span>liberapay.com/<strong>TheAlgorithms</strong></span></a>
</div>
</div>
</div>
<div class="text-small p-3 border-top">
<p class="my-0">
<a class="Link--inTextBlock" href="https://docs.github.com/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/displaying-a-sponsor-button-in-your-repository">Learn more about funding links in repositories</a>.
</p>
<p class="my-0">
<a class="Link--secondary" href="/contact/report-abuse?report=TheAlgorithms%2FPython+%28Repository+Funding+Links%29">Report abuse</a>
</p>
</div>
</div>
</div>
</scrollable-region>
</dialog></dialog-helper>
</div></div></div></div></div>

View File

@@ -1,336 +0,0 @@
<form id="search_form" class="search_repos" data-turbo="false" action="/search" accept-charset="UTF-8" method="get">
<div class="pagehead codesearch-head color-border-muted">
<div class="container-lg p-responsive d-flex flex-column flex-md-row">
<h1 class="flex-shrink-0" id="search-title">Advanced search</h1>
<div class="search-form-fluid flex-auto d-flex flex-column flex-md-row pt-2 pt-md-0" id="adv_code_search">
<div class="flex-auto pr-md-2">
<label class="form-control search-page-label js-advanced-search-label">
<input aria-labelledby="search-title" class="form-control input-block search-page-input js-advanced-search-input js-advanced-search-prefix" data-search-prefix="" type="text" value="">
<p class="completed-query js-advanced-query top-0 right-0 left-0"><span></span> </p>
</label>
<input class="js-search-query" type="hidden" name="q" value="">
<input class="js-type-value" type="hidden" name="type" value="Repositories">
<input type="hidden" name="ref" value="advsearch">
</div>
<div class="d-flex d-md-block flex-shrink-0 pt-2 pt-md-0">
<button type="submit" data-view-component="true" class="btn flex-auto"> Search
</button>
</div>
</div>
</div>
</div>
<div class="container-lg p-responsive advanced-search-form">
<fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
<h3>Advanced options</h3>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_from">From these owners</label></dt>
<dd><input id="search_from" type="text" class="form-control js-advanced-search-prefix" placeholder="github, atom, electron, octokit" data-search-prefix="user:"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_repos">In these repositories</label></dt>
<dd><input id="search_repos" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="twbs/bootstrap, rails/rails" data-search-prefix="repo:"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_date">Created on the dates</label></dt>
<dd><input id="search_date" type="text" class="form-control js-advanced-search-prefix" value="" placeholder=">YYYY-MM-DD, YYYY-MM-DD" data-search-prefix="created:"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_language">Written in this language</label></dt>
<dd>
<select id="search_language" name="l" class="form-select js-advanced-search-prefix" data-search-prefix="language:">
<option value="">Any language</option>
<optgroup label="Popular">
<option value="C">C</option>
<option value="C#">C#</option>
<option value="C++">C++</option>
<option value="CoffeeScript">CoffeeScript</option>
<option value="CSS">CSS</option>
<option value="Dart">Dart</option>
<option value="DM">DM</option>
<option value="Elixir">Elixir</option>
<option value="Go">Go</option>
<option value="Groovy">Groovy</option>
<option value="HTML">HTML</option>
<option value="Java">Java</option>
<option value="JavaScript">JavaScript</option>
<option value="Kotlin">Kotlin</option>
<option value="Objective-C">Objective-C</option>
<option value="Perl">Perl</option>
<option value="PHP">PHP</option>
<option value="PowerShell">PowerShell</option>
<option value="Python">Python</option>
<option value="Ruby">Ruby</option>
<option value="Rust">Rust</option>
<option value="Scala">Scala</option>
<option value="Shell">Shell</option>
<option value="Swift">Swift</option>
<option value="TypeScript">TypeScript</option>
</optgroup>
<optgroup label="Everything else">
<option value="1C Enterprise">1C Enterprise</option>
<option value="2-Dimensional Array">2-Dimensional Array</option>
<option value="4D">4D</option>
<option value="ABAP">ABAP</option>
<option value="ABAP CDS">ABAP CDS</option>
<option value="ABNF">ABNF</option>
<option value="ActionScript">ActionScript</option>
<option value="Ada">Ada</option>
<option value="Adblock Filter List">Adblock Filter List</option>
<option value="Adobe Font Metrics">Adobe Font Metrics</option>
<option value="Agda">Agda</option>
<option value="AGS Script">AGS Script</option>
<option value="AIDL">AIDL</option>
<option value="Aiken">Aiken</option>
</optgroup>
</select>
</dd>
</dl>
</fieldset>
<fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
<h3>Repositories options</h3>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_stars">With this many stars</label></dt>
<dd><input id="search_stars" type="text" class="form-control js-advanced-search-prefix" placeholder="0..100, 200, >1000" data-search-prefix="stars:" data-search-type="Repositories"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_forks">With this many forks</label></dt>
<dd><input id="search_forks" type="text" class="form-control js-advanced-search-prefix" placeholder="50..100, 200, <5" data-search-prefix="forks:" data-search-type="Repositories"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_size">Of this size</label></dt>
<dd><input id="search_size" type="text" class="form-control js-advanced-search-prefix" placeholder="Repository size in KB" data-search-prefix="size:" data-search-type="Repositories"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_push">Pushed to</label></dt>
<dd><input id="search_push" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="<YYYY-MM-DD" data-search-prefix="pushed:" data-search-type="Repositories"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_license">With this license</label></dt>
<dd>
<select id="search_license" class="form-select js-advanced-search-prefix" data-search-prefix="license:" data-search-type="Repositories">
<option value="">Any license</option>
<optgroup label="Licenses">
<option value="0bsd">BSD Zero Clause License</option>
<option value="afl-3.0">Academic Free License v3.0</option>
<option value="agpl-3.0">GNU Affero General Public License v3.0</option>
<option value="apache-2.0">Apache License 2.0</option>
<option value="artistic-2.0">Artistic License 2.0</option>
<option value="blueoak-1.0.0">Blue Oak Model License 1.0.0</option>
<option value="bsd-2-clause">BSD 2-Clause "Simplified" License</option>
<option value="bsd-2-clause-patent">BSD-2-Clause Plus Patent License</option>
<option value="bsd-3-clause">BSD 3-Clause "New" or "Revised" License</option>
<option value="bsd-3-clause-clear">BSD 3-Clause Clear License</option>
<option value="bsd-4-clause">BSD 4-Clause "Original" or "Old" License</option>
<option value="bsl-1.0">Boost Software License 1.0</option>
<option value="cc-by-4.0">Creative Commons Attribution 4.0 International</option>
<option value="cc-by-sa-4.0">Creative Commons Attribution Share Alike 4.0 International</option>
<option value="cc0-1.0">Creative Commons Zero v1.0 Universal</option>
<option value="cecill-2.1">CeCILL Free Software License Agreement v2.1</option>
<option value="cern-ohl-p-2.0">CERN Open Hardware Licence Version 2 - Permissive</option>
<option value="cern-ohl-s-2.0">CERN Open Hardware Licence Version 2 - Strongly Reciprocal</option>
<option value="cern-ohl-w-2.0">CERN Open Hardware Licence Version 2 - Weakly Reciprocal</option>
<option value="ecl-2.0">Educational Community License v2.0</option>
<option value="epl-1.0">Eclipse Public License 1.0</option>
<option value="epl-2.0">Eclipse Public License 2.0</option>
<option value="eupl-1.1">European Union Public License 1.1</option>
<option value="eupl-1.2">European Union Public License 1.2</option>
<option value="gfdl-1.3">GNU Free Documentation License v1.3</option>
<option value="gpl-2.0">GNU General Public License v2.0</option>
<option value="gpl-3.0">GNU General Public License v3.0</option>
<option value="isc">ISC License</option>
<option value="lgpl-2.1">GNU Lesser General Public License v2.1</option>
<option value="lgpl-3.0">GNU Lesser General Public License v3.0</option>
<option value="lppl-1.3c">LaTeX Project Public License v1.3c</option>
<option value="mit">MIT License</option>
<option value="mit-0">MIT No Attribution</option>
<option value="mpl-2.0">Mozilla Public License 2.0</option>
<option value="ms-pl">Microsoft Public License</option>
<option value="ms-rl">Microsoft Reciprocal License</option>
<option value="mulanpsl-2.0">Mulan Permissive Software License, Version 2</option>
<option value="ncsa">University of Illinois/NCSA Open Source License</option>
<option value="odbl-1.0">Open Data Commons Open Database License v1.0</option>
<option value="ofl-1.1">SIL Open Font License 1.1</option>
<option value="osl-3.0">Open Software License 3.0</option>
<option value="postgresql">PostgreSQL License</option>
<option value="unlicense">The Unlicense</option>
<option value="upl-1.0">Universal Permissive License v1.0</option>
<option value="vim">Vim License</option>
<option value="wtfpl">Do What The F*ck You Want To Public License</option>
<option value="zlib">zlib License</option>
</optgroup>
<optgroup label="License families">
<option value="cc">Creative Commons</option>
<option value="gpl">GNU General Public License</option>
<option value="lgpl">GNU Lesser General Public License</option>
</optgroup>
</select>
</dd>
</dl>
<label>
Return repositories <select class="form-select js-advanced-search-prefix" data-search-prefix="fork:" data-search-type="Repositories">
<option value="">not</option>
<option value="true">and</option>
<option value="only">only</option>
</select> including forks.
</label>
</fieldset>
<fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
<h3>Code options</h3>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_extension">With this extension</label></dt>
<dd>
<input id="search_extension" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="rb, py, jpg" data-search-type="Code" data-search-prefix="path:" data-glob-pattern="*.$0" data-regex-pattern="/.$0$/" data-use-or="true">
</dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_path">In this path</label></dt>
<dd><input id="search_path" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="/foo/bar/baz/qux" data-search-prefix="path:" data-search-type="Code" data-use-or=""></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_filename">With this file name</label></dt>
<dd>
<input id="search_filename" type="text" class="form-control js-advanced-search-prefix" placeholder="app.rb, footer.erb" data-search-type="code:" data-search-prefix="path:" data-glob-pattern="**/$0" data-regex-pattern="/(^|/)$0$/" data-use-or="true">
</dd>
</dl>
<label>
Return code <select class="form-select js-advanced-search-prefix" data-search-prefix="fork:" data-search-type="Code">
<option value="">not</option>
<option value="true">and</option>
<option value="only">only</option>
</select> including forks.
</label>
</fieldset>
<fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
<h3>Issues options</h3>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_state">In the state</label></dt>
<dd><select id="search_state" class="form-select js-advanced-search-prefix" data-search-prefix="state:" data-search-type="Issues">
<option value="">open/closed</option>
<option value="open">open</option>
<option value="closed">closed</option>
</select></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_state_reason">With the reason</label></dt>
<dd><select id="search_state_reason" class="form-select js-advanced-search-prefix" data-search-prefix="reason:" data-search-type="Issues">
<option value="">any reason</option>
<option value="completed">completed</option>
<option value="not planned">not planned</option>
<option value="reopened">reopened</option>
</select></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_comments">With this many comments</label></dt>
<dd><input id="search_comments" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="0..100, >442" data-search-prefix="comments:" data-search-type="Issues"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_labels">With the labels</label></dt>
<dd><input id="search_labels" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="bug, ie6" data-search-prefix="label:" data-search-type="Issues"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_author">Opened by the author</label></dt>
<dd><input id="search_author" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="hubot, octocat" data-search-prefix="author:" data-search-type="Issues"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_mention">Mentioning the users</label></dt>
<dd><input id="search_mention" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="tpope, mattt" data-search-prefix="mentions:" data-search-type="Issues"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_assignment">Assigned to the users</label></dt>
<dd><input id="search_assignment" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="twp, jim" data-search-prefix="assignee:" data-search-type="Issues"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_updated_date">Updated before the date</label></dt>
<dd><input id="search_updated_date" type="text" class="form-control js-advanced-search-prefix" value="" placeholder="<YYYY-MM-DD" data-search-prefix="updated:" data-search-type="Issues"></dd>
</dl>
</fieldset>
<fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
<h3>Users options</h3>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_full_name">With this full name</label></dt>
<dd><input id="search_full_name" type="text" class="form-control js-advanced-search-prefix" placeholder="Grace Hopper" data-search-prefix="fullname:" data-search-type="Users"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_location">From this location</label></dt>
<dd><input id="search_location" type="text" class="form-control js-advanced-search-prefix" placeholder="San Francisco, CA" data-search-prefix="location:" data-search-type="Users"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_followers">With this many followers</label></dt>
<dd><input id="search_followers" type="text" class="form-control js-advanced-search-prefix" placeholder="20..50, >200, <2" data-search-prefix="followers:" data-search-type="Users"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_public_repos">With this many public repositories</label></dt>
<dd><input id="search_public_repos" type="text" class="form-control js-advanced-search-prefix" placeholder="0, <42, >5" data-search-prefix="repos:" data-search-type="Users"></dd>
</dl>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_user_language">Working in this language</label></dt>
<dd>
<select id="search_user_language" name="l" class="form-select js-advanced-search-prefix" data-search-prefix="language:">
<option value="">Any language</option>
<optgroup label="Popular">
<option value="C">C</option>
<option value="C#">C#</option>
<option value="C++">C++</option>
<option value="CoffeeScript">CoffeeScript</option>
<option value="CSS">CSS</option>
<option value="Dart">Dart</option>
<option value="DM">DM</option>
<option value="Elixir">Elixir</option>
<option value="Go">Go</option>
<option value="Groovy">Groovy</option>
<option value="HTML">HTML</option>
<option value="Java">Java</option>
<option value="JavaScript">JavaScript</option>
<option value="Kotlin">Kotlin</option>
<option value="Objective-C">Objective-C</option>
<option value="Perl">Perl</option>
<option value="PHP">PHP</option>
<option value="PowerShell">PowerShell</option>
<option value="Python">Python</option>
<option value="Ruby">Ruby</option>
<option value="Rust">Rust</option>
<option value="Scala">Scala</option>
<option value="Shell">Shell</option>
<option value="Swift">Swift</option>
<option value="TypeScript">TypeScript</option>
</optgroup>
<optgroup label="Everything else">
<option value="1C Enterprise">1C Enterprise</option>
<option value="2-Dimensional Array">2-Dimensional Array</option>
<option value="4D">4D</option>
<option value="ABAP">ABAP</option>
<option value="ABAP CDS">ABAP CDS</option>
<option value="ABNF">ABNF</option>
<option value="ActionScript">ActionScript</option>
<option value="Ada">Ada</option>
<option value="Yul">Yul</option>
<option value="ZAP">ZAP</option>
<option value="Zeek">Zeek</option>
<option value="ZenScript">ZenScript</option>
<option value="Zephir">Zephir</option>
<option value="Zig">Zig</option>
<option value="ZIL">ZIL</option>
<option value="Zimpl">Zimpl</option>
<option value="Zmodel">Zmodel</option>
</optgroup>
</select>
</dd>
</dl>
</fieldset>
<fieldset class="pb-3 mb-4 border-bottom color-border-muted min-width-0">
<h3>Wiki options</h3>
<dl class="form-group flattened d-flex d-md-block flex-column">
<dt><label for="search_wiki_updated_date">Updated before the date</label></dt>
<dd><input id="search_wiki_updated_date" type="text" class="form-control js-advanced-search-prefix" placeholder="<YYYY-MM-DD" data-search-prefix="updated:" data-search-type="Wiki"></dd>
</dl>
</fieldset>
<div class="form-group flattened">
<div class="d-flex d-md-block"> <button type="submit" data-view-component="true" class="btn flex-auto"> Search
</button></div>
</div>
</div>
</form>

View File

@@ -1,7 +0,0 @@
GO https://store.example.com/product/laptop
WAIT `.product-details` 8
CLICK `button.add-to-cart`
WAIT `.cart-notification` 3
CLICK `.cart-icon`
WAIT `.checkout-btn` 5
CLICK `.checkout-btn`

View File

@@ -1,43 +0,0 @@
# Advanced control flow with IF, EXISTS, and REPEAT
# Define reusable procedures
PROC handle_cookie_banner
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-cookies`
IF (EXISTS `.privacy-notice`) THEN CLICK `.dismiss-privacy`
ENDPROC
PROC scroll_to_load
SCROLL DOWN 500
WAIT 0.5
ENDPROC
PROC try_login
CLICK `#email`
TYPE "user@example.com"
CLICK `#password`
TYPE "secure123"
CLICK `button[type="submit"]`
WAIT 2
ENDPROC
# Main script
GO https://example.com
WAIT 2
# Handle popups
handle_cookie_banner
# Conditional navigation based on login state
IF (EXISTS `.user-menu`) THEN CLICK `.dashboard-link` ELSE try_login
# Repeat scrolling based on content count
REPEAT (scroll_to_load, 5)
# Load more content while button exists
REPEAT (CLICK `.load-more`, `document.querySelector('.load-more') && !document.querySelector('.no-more-content')`)
# Process items conditionally
IF (`document.querySelectorAll('.item').length > 10`) THEN EVAL `console.log('Found ' + document.querySelectorAll('.item').length + ' items')`
# Complex condition with viewport check
IF (`window.innerWidth < 768 && document.querySelector('.mobile-menu')`) THEN CLICK `.mobile-menu-toggle`

View File

@@ -1,8 +0,0 @@
GO https://myapp.com
WAIT 2
IF (EXISTS `.user-avatar`) THEN CLICK `.logout` ELSE CLICK `.login`
WAIT `#auth-form` 5
IF (EXISTS `#auth-form`) THEN TYPE "user@example.com"
IF (EXISTS `#auth-form`) THEN PRESS Tab
IF (EXISTS `#auth-form`) THEN TYPE "password123"
IF (EXISTS `#auth-form`) THEN CLICK `button[type="submit"]`

View File

@@ -1,56 +0,0 @@
# Data extraction example
# Scrapes product information from an e-commerce site
# Navigate to products page
GO https://shop.example.com/products
WAIT `.product-list` 10
# Scroll to load lazy-loaded content
SCROLL DOWN 500
WAIT 1
SCROLL DOWN 500
WAIT 1
SCROLL DOWN 500
WAIT 2
# Extract product data
EVAL `
// Extract all product information
const products = Array.from(document.querySelectorAll('.product-card')).map((card, index) => {
return {
id: index + 1,
name: card.querySelector('.product-title')?.textContent?.trim() || 'N/A',
price: card.querySelector('.price')?.textContent?.trim() || 'N/A',
rating: card.querySelector('.rating')?.textContent?.trim() || 'N/A',
availability: card.querySelector('.in-stock') ? 'In Stock' : 'Out of Stock',
image: card.querySelector('img')?.src || 'N/A'
};
});
// Log results
console.log('=== Product Extraction Results ===');
console.log('Total products found:', products.length);
console.log(JSON.stringify(products, null, 2));
// Save to localStorage for retrieval
localStorage.setItem('scraped_products', JSON.stringify(products));
`
# Optional: Click on first product for details
CLICK `.product-card:first-child`
WAIT `.product-details` 5
# Extract detailed information
EVAL `
const details = {
description: document.querySelector('.product-description')?.textContent?.trim(),
specifications: Array.from(document.querySelectorAll('.spec-item')).map(spec => ({
label: spec.querySelector('.spec-label')?.textContent,
value: spec.querySelector('.spec-value')?.textContent
})),
reviews: document.querySelector('.review-count')?.textContent
};
console.log('=== Product Details ===');
console.log(JSON.stringify(details, null, 2));
`

View File

@@ -1,8 +0,0 @@
GO https://company.com/contact
WAIT `form#contact` 10
TYPE "John Smith"
PRESS Tab
TYPE "john@email.com"
PRESS Tab
TYPE "Need help with my order"
CLICK `button[type="submit"]`

View File

@@ -1,7 +0,0 @@
GO https://news.example.com
WAIT `.article-list` 5
REPEAT (SCROLL DOWN 500, 3)
WAIT 1
REPEAT (CLICK `.load-more`, `document.querySelector('.load-more') !== null`)
WAIT 2
IF (`document.querySelectorAll('.article').length > 20`) THEN EVAL `console.log('Loaded enough articles')`

View File

@@ -1,36 +0,0 @@
# Login flow with error handling
# Demonstrates procedures, variables, and conditional checks
# Define login procedure
PROC perform_login
CLICK `input#email`
TYPE $email
CLICK `input#password`
TYPE $password
CLICK `button.login-submit`
ENDPROC
# Set credentials
SET email = "user@example.com"
SET password = "securePassword123"
# Navigate to login page
GO https://app.example.com/login
WAIT `.login-container` 15
# Attempt login
perform_login
# Wait for page to load
WAIT 3
# Check if login was successful
EVAL `
if (document.querySelector('.dashboard')) {
console.log('Login successful - on dashboard');
} else if (document.querySelector('.error-message')) {
console.log('Login failed:', document.querySelector('.error-message').textContent);
} else {
console.log('Unknown state after login');
}
`

View File

@@ -1,106 +0,0 @@
# Multi-step e-commerce workflow
# Complete purchase flow with procedures and error handling
# Reusable procedures
PROC search_product
CLICK `input.search-bar`
TYPE $search_term
PRESS Enter
WAIT `.search-results` 10
ENDPROC
PROC add_first_item_to_cart
CLICK `.product-item:first-child .add-to-cart`
WAIT ".added-to-cart-notification" 3
ENDPROC
PROC go_to_checkout
CLICK `.cart-icon`
WAIT `.cart-drawer` 5
CLICK `button.proceed-to-checkout`
WAIT `.checkout-page` 10
ENDPROC
PROC fill_customer_info
# Billing information
CLICK `#billing-firstname`
TYPE $first_name
CLICK `#billing-lastname`
TYPE $last_name
CLICK `#billing-email`
TYPE $email
CLICK `#billing-phone`
TYPE $phone
# Address
CLICK `#billing-address`
TYPE $address
CLICK `#billing-city`
TYPE $city
CLICK `#billing-state`
TYPE $state
CLICK `#billing-zip`
TYPE $zip
ENDPROC
PROC select_shipping
CLICK `input[value="standard"]`
WAIT 1
ENDPROC
# Set all required variables
SET search_term = "wireless headphones"
SET first_name = "John"
SET last_name = "Doe"
SET email = "john.doe@example.com"
SET phone = "555-0123"
SET address = "123 Main Street"
SET city = "San Francisco"
SET state = "CA"
SET zip = "94105"
# Main workflow starts here
GO https://shop.example.com
WAIT `.homepage-loaded` 10
# Step 1: Search and add to cart
search_product
EVAL `console.log('Found', document.querySelectorAll('.product-item').length, 'products')`
add_first_item_to_cart
# Add a second item
CLICK `.product-item:nth-child(2) .add-to-cart`
WAIT 2
# Step 2: Go to checkout
go_to_checkout
# Step 3: Fill customer information
fill_customer_info
# Step 4: Select shipping method
select_shipping
# Step 5: Continue to payment
CLICK `button.continue-to-payment`
WAIT `.payment-section` 10
# Log order summary
EVAL `
const orderTotal = document.querySelector('.order-total')?.textContent;
const itemCount = document.querySelectorAll('.order-item').length;
console.log('=== Order Summary ===');
console.log('Items:', itemCount);
console.log('Total:', orderTotal);
// Get all items
const items = Array.from(document.querySelectorAll('.order-item')).map(item => ({
name: item.querySelector('.item-name')?.textContent,
quantity: item.querySelector('.item-quantity')?.textContent,
price: item.querySelector('.item-price')?.textContent
}));
console.log('Items:', JSON.stringify(items, null, 2));
`
# Note: Stopping here before actual payment submission
EVAL `console.log('Workflow completed - stopped before payment submission')`

View File

@@ -1,8 +0,0 @@
GO https://app.example.com
WAIT `.nav-menu` 8
CLICK `a[href="/products"]`
WAIT 2
CLICK `a[href="/about"]`
WAIT 2
BACK
WAIT 1

View File

@@ -1,8 +0,0 @@
GO https://myapp.com/login
WAIT `input#email` 5
CLICK `input#email`
TYPE "user@example.com"
PRESS Tab
TYPE "password123"
CLICK `button.login-btn`
WAIT `.dashboard` 10

View File

@@ -1,7 +0,0 @@
GO https://responsive.site.com
WAIT 2
IF (`window.innerWidth < 768`) THEN CLICK `.mobile-menu`
IF (`window.innerWidth < 768`) THEN WAIT `.mobile-nav` 3
IF (`window.innerWidth >= 768`) THEN CLICK `.desktop-menu li:nth-child(2)`
REPEAT (CLICK `.next-slide`, 5)
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-cookies`

View File

@@ -1,8 +0,0 @@
GO https://news.site.com
WAIT `.article-list` 10
SCROLL DOWN 500
WAIT 1
SCROLL DOWN 500
WAIT 1
CLICK `.article:nth-child(5)`
WAIT `.article-content` 5

View File

@@ -1,7 +0,0 @@
GO https://shop.example.com
WAIT `.search-bar` 10
CLICK `.search-bar`
TYPE "wireless headphones"
PRESS Enter
WAIT `.results` 5
CLICK `.product-card:first-child`

View File

@@ -1,19 +0,0 @@
# Simple form submission example
# This script fills out a contact form and submits it
GO https://example.com/contact
WAIT `form#contact-form` 10
# Fill out the form fields
CLICK `input[name="name"]`
TYPE "Alice Smith"
PRESS Tab
TYPE "alice@example.com"
PRESS Tab
TYPE "I'd like to learn more about your services"
# Submit the form
CLICK `button[type="submit"]`
# Wait for success message
WAIT "Thank you for your message" 5

View File

@@ -1,11 +0,0 @@
PROC fill_field
TYPE "test@example.com"
PRESS Tab
ENDPROC
GO https://forms.example.com
WAIT `form` 5
IF (EXISTS `input[type="email"]`) THEN CLICK `input[type="email"]`
IF (EXISTS `input[type="email"]`) THEN fill_field
REPEAT (PRESS Tab, `document.activeElement.type !== 'submit'`)
CLICK `button[type="submit"]`

View File

@@ -1,396 +0,0 @@
# C4A-Script Interactive Tutorial
A comprehensive web-based tutorial for learning and experimenting with C4A-Script - Crawl4AI's visual web automation language.
## 🚀 Quick Start
### Prerequisites
- Python 3.7+
- Modern web browser (Chrome, Firefox, Safari, Edge)
### Running the Tutorial
1. **Clone and Navigate**
```bash
git clone https://github.com/unclecode/crawl4ai.git
cd crawl4ai/docs/examples/c4a_script/tutorial/
```
2. **Install Dependencies**
```bash
pip install flask
```
3. **Launch the Server**
```bash
python server.py
```
4. **Open in Browser**
```
http://localhost:8080
```
**🌐 Try Online**: [Live Demo](https://docs.crawl4ai.com/c4a-script/demo)
### 2. Try Your First Script
```c4a
# Basic interaction
GO playground/
WAIT `body` 2
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
CLICK `#start-tutorial`
```
## 🎯 What You'll Learn
### Core Features
- **📝 Text Editor**: Write C4A-Script with syntax highlighting
- **🧩 Visual Editor**: Build scripts using drag-and-drop Blockly interface
- **🎬 Recording Mode**: Capture browser actions and auto-generate scripts
- **⚡ Live Execution**: Run scripts in real-time with instant feedback
- **📊 Timeline View**: Visualize and edit automation steps
## 📚 Tutorial Content
### Basic Commands
- **Navigation**: `GO url`
- **Waiting**: `WAIT selector timeout` or `WAIT seconds`
- **Clicking**: `CLICK selector`
- **Typing**: `TYPE "text"`
- **Scrolling**: `SCROLL DOWN/UP amount`
### Control Flow
- **Conditionals**: `IF (condition) THEN action`
- **Loops**: `REPEAT (action, condition)`
- **Procedures**: Define reusable command sequences
### Advanced Features
- **JavaScript evaluation**: `EVAL code`
- **Variables**: `SET name = "value"`
- **Complex selectors**: CSS selectors in backticks
## 🎮 Interactive Playground Features
The tutorial includes a fully interactive web app with:
### 1. **Authentication System**
- Login form with validation
- Session management
- Protected content
### 2. **Dynamic Content**
- Infinite scroll products
- Pagination controls
- Load more buttons
### 3. **Complex Forms**
- Multi-step wizards
- Dynamic field visibility
- Form validation
### 4. **Interactive Elements**
- Tabs and accordions
- Modals and popups
- Expandable content
### 5. **Data Tables**
- Sortable columns
- Search functionality
- Export options
## 🛠️ Tutorial Features
### Live Code Editor
- Syntax highlighting
- Real-time compilation
- Error messages with suggestions
### JavaScript Output Viewer
- See generated JavaScript code
- Edit and test JS directly
- Understand the compilation
### Visual Execution
- Step-by-step progress
- Element highlighting
- Console output
### Example Scripts
Load pre-written examples demonstrating:
- Cookie banner handling
- Login workflows
- Infinite scroll automation
- Multi-step form completion
- Complex interaction sequences
## 📖 Tutorial Sections
### 1. Getting Started
Learn basic commands and syntax:
```c4a
GO https://example.com
WAIT `.content` 5
CLICK `.button`
```
### 2. Handling Dynamic Content
Master waiting strategies and conditionals:
```c4a
IF (EXISTS `.popup`) THEN CLICK `.close`
WAIT `.results` 10
```
### 3. Form Automation
Fill and submit forms:
```c4a
CLICK `#email`
TYPE "user@example.com"
CLICK `button[type="submit"]`
```
### 4. Advanced Workflows
Build complex automation flows:
```c4a
PROC login
CLICK `#username`
TYPE $username
CLICK `#password`
TYPE $password
CLICK `#login-btn`
ENDPROC
SET username = "demo"
SET password = "pass123"
login
```
## 🎯 Practice Challenges
### Challenge 1: Cookie & Popups
Handle the cookie banner and newsletter popup that appear on page load.
### Challenge 2: Complete Login
Successfully log into the application using the demo credentials.
### Challenge 3: Load All Products
Use infinite scroll to load all 100 products in the catalog.
### Challenge 4: Multi-step Survey
Complete the entire multi-step survey form.
### Challenge 5: Full Workflow
Create a script that logs in, browses products, and exports data.
## 💡 Tips & Tricks
### 1. Use Specific Selectors
```c4a
# Good - specific
CLICK `button.submit-order`
# Bad - too generic
CLICK `button`
```
### 2. Always Handle Popups
```c4a
# Check for common popups
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
IF (EXISTS `.newsletter-modal`) THEN CLICK `.close`
```
### 3. Add Appropriate Waits
```c4a
# Wait for elements before interacting
WAIT `.form` 5
CLICK `#submit`
```
### 4. Use Procedures for Reusability
```c4a
PROC handle_popups
IF (EXISTS `.popup`) THEN CLICK `.close`
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
ENDPROC
# Use anywhere
handle_popups
```
## 🔧 Troubleshooting
### Common Issues
1. **"Element not found"**
- Add a WAIT before clicking
- Check selector specificity
- Verify element exists with IF
2. **"Timeout waiting for selector"**
- Increase timeout value
- Check if element is dynamically loaded
- Verify selector is correct
3. **"Missing THEN keyword"**
- All IF statements need THEN
- Format: `IF (condition) THEN action`
## 🚀 Using with Crawl4AI
Once you've mastered C4A-Script in the tutorial, use it with Crawl4AI:
```python
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
config = CrawlerRunConfig(
url="https://example.com",
c4a_script="""
WAIT `.content` 5
IF (EXISTS `.load-more`) THEN CLICK `.load-more`
WAIT `.new-content` 3
"""
)
async with AsyncWebCrawler() as crawler:
result = await crawler.arun(config=config)
```
## 📝 Example Scripts
Check the `scripts/` folder for complete examples:
- `01-basic-interaction.c4a` - Getting started
- `02-login-flow.c4a` - Authentication
- `03-infinite-scroll.c4a` - Dynamic content
- `04-multi-step-form.c4a` - Complex forms
- `05-complex-workflow.c4a` - Full automation
## 🏗️ Developer Guide
### Project Architecture
```
tutorial/
├── server.py # Flask application server
├── assets/ # Tutorial-specific assets
│ ├── app.js # Main application logic
│ ├── c4a-blocks.js # Custom Blockly blocks
│ ├── c4a-generator.js # Code generation
│ ├── blockly-manager.js # Blockly integration
│ └── styles.css # Main styling
├── playground/ # Interactive demo environment
│ ├── index.html # Demo web application
│ ├── app.js # Demo app logic
│ └── styles.css # Demo styling
├── scripts/ # Example C4A scripts
└── index.html # Main tutorial interface
```
### Key Components
#### 1. TutorialApp (`assets/app.js`)
Main application controller managing:
- Code editor integration (CodeMirror)
- Script execution and browser preview
- Tutorial navigation and lessons
- State management and persistence
#### 2. BlocklyManager (`assets/blockly-manager.js`)
Visual programming interface:
- Custom C4A-Script block definitions
- Bidirectional sync between visual blocks and text
- Real-time code generation
- Dark theme integration
#### 3. Recording System
Powers the recording functionality:
- Browser event capture
- Smart event grouping and filtering
- Automatic C4A-Script generation
- Timeline visualization
### Customization
#### Adding New Commands
1. **Define Block** (`assets/c4a-blocks.js`)
2. **Add Generator** (`assets/c4a-generator.js`)
3. **Update Parser** (`assets/blockly-manager.js`)
#### Themes and Styling
- Main styles: `assets/styles.css`
- Theme variables: CSS custom properties
- Dark mode: Auto-applied based on system preference
### Configuration
```python
# server.py configuration
PORT = 8080
DEBUG = True
THREADED = True
```
### API Endpoints
- `GET /` - Main tutorial interface
- `GET /playground/` - Interactive demo environment
- `POST /execute` - Script execution endpoint
- `GET /examples/<script>` - Load example scripts
## 🔧 Troubleshooting
### Common Issues
**Port Already in Use**
```bash
# Kill existing process
lsof -ti:8080 | xargs kill -9
# Or use different port
python server.py --port 8081
```
**Blockly Not Loading**
- Check browser console for JavaScript errors
- Verify all static files are served correctly
- Ensure proper script loading order
**Recording Issues**
- Verify iframe permissions
- Check cross-origin communication
- Ensure event listeners are attached
### Debug Mode
Enable detailed logging by setting `DEBUG = True` in `assets/app.js`
## 📚 Additional Resources
- **[C4A-Script Documentation](../../md_v2/core/c4a-script.md)** - Complete language guide
- **[API Reference](../../md_v2/api/c4a-script-reference.md)** - Detailed command documentation
- **[Live Demo](https://docs.crawl4ai.com/c4a-script/demo)** - Try without installation
- **[Example Scripts](../)** - More automation examples
## 🤝 Contributing
### Bug Reports
1. Check existing issues on GitHub
2. Provide minimal reproduction steps
3. Include browser and system information
4. Add relevant console logs
### Feature Requests
1. Fork the repository
2. Create feature branch: `git checkout -b feature/my-feature`
3. Test thoroughly with different browsers
4. Update documentation
5. Submit pull request
### Code Style
- Use consistent indentation (2 spaces for JS, 4 for Python)
- Add comments for complex logic
- Follow existing naming conventions
- Test with multiple browsers
---
**Happy Automating!** 🎉
Need help? Check our [documentation](https://docs.crawl4ai.com) or open an issue on [GitHub](https://github.com/unclecode/crawl4ai).

View File

@@ -1,906 +0,0 @@
/* ================================================================
C4A-Script Tutorial - App Layout CSS
Terminal theme with Dank Mono font
================================================================ */
/* CSS Variables */
:root {
--bg-primary: #070708;
--bg-secondary: #0e0e10;
--bg-tertiary: #1a1a1b;
--border-color: #2a2a2c;
--border-hover: #3a3a3c;
--text-primary: #e0e0e0;
--text-secondary: #8b8b8d;
--text-muted: #606065;
--primary-color: #0fbbaa;
--primary-hover: #0da89a;
--primary-dim: #0a8577;
--error-color: #ff5555;
--warning-color: #ffb86c;
--success-color: #50fa7b;
--info-color: #8be9fd;
--code-bg: #1e1e20;
--modal-overlay: rgba(0, 0, 0, 0.8);
}
/* Base Reset */
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
/* Fonts */
@font-face {
font-family: 'Dank Mono';
src: url('DankMono-Regular.woff2') format('woff2');
font-weight: 400;
font-style: normal;
}
@font-face {
font-family: 'Dank Mono';
src: url('DankMono-Bold.woff2') format('woff2');
font-weight: 700;
font-style: normal;
}
@font-face {
font-family: 'Dank Mono';
src: url('DankMono-Italic.woff2') format('woff2');
font-weight: 400;
font-style: italic;
}
/* Body & App Container */
body {
font-family: 'Dank Mono', 'Monaco', 'Consolas', monospace;
background: var(--bg-primary);
color: var(--text-primary);
font-size: 14px;
line-height: 1.6;
overflow: hidden;
}
.app-container {
display: flex;
height: 100vh;
width: 100vw;
overflow: hidden;
}
/* Panels */
.editor-panel,
.playground-panel {
display: flex;
flex-direction: column;
height: 100%;
overflow: hidden;
}
.editor-panel {
flex: 1;
background: var(--bg-secondary);
border-right: 1px solid var(--border-color);
min-width: 400px;
}
.playground-panel {
flex: 1;
background: var(--bg-primary);
min-width: 400px;
}
/* Panel Headers */
.panel-header {
display: flex;
justify-content: space-between;
align-items: center;
padding: 12px 16px;
background: var(--bg-tertiary);
border-bottom: 1px solid var(--border-color);
flex-shrink: 0;
}
.panel-header h2 {
font-size: 16px;
font-weight: 600;
color: var(--primary-color);
margin: 0;
}
.header-actions {
display: flex;
gap: 8px;
}
/* Action Buttons */
.action-btn {
display: flex;
align-items: center;
gap: 6px;
padding: 6px 12px;
background: var(--bg-secondary);
color: var(--text-secondary);
border: 1px solid var(--border-color);
border-radius: 4px;
font-family: inherit;
font-size: 13px;
cursor: pointer;
transition: all 0.2s;
}
.action-btn:hover {
background: var(--bg-tertiary);
color: var(--text-primary);
border-color: var(--border-hover);
}
.action-btn.primary {
background: var(--primary-color);
color: var(--bg-primary);
border-color: var(--primary-color);
}
.action-btn.primary:hover {
background: var(--primary-hover);
border-color: var(--primary-hover);
}
.action-btn .icon {
font-size: 16px;
}
/* Editor Wrapper */
.editor-wrapper {
flex: 1;
display: flex;
overflow: hidden;
position: relative;
z-index: 1; /* Ensure it's above any potential overlays */
}
.editor-wrapper .CodeMirror {
flex: 1;
height: 100%;
font-family: 'Dank Mono', monospace;
font-size: 14px;
line-height: 1.5;
}
/* Ensure CodeMirror is interactive */
.CodeMirror {
background: var(--bg-primary) !important;
}
.CodeMirror-scroll {
overflow: auto !important;
}
/* Make cursor more visible */
.CodeMirror-cursor {
border-left: 2px solid var(--primary-color) !important;
border-left-width: 2px !important;
opacity: 1 !important;
visibility: visible !important;
}
/* Ensure cursor is visible when focused */
.CodeMirror-focused .CodeMirror-cursor {
visibility: visible !important;
}
/* Fix for CodeMirror in flex container */
.CodeMirror-sizer {
min-height: auto !important;
}
/* Remove aggressive pointer-events override */
.CodeMirror-code {
cursor: text;
}
.editor-wrapper textarea {
display: none;
}
/* Output Section (Bottom of Editor) */
.output-section {
height: 250px;
border-top: 1px solid var(--border-color);
display: flex;
flex-direction: column;
flex-shrink: 0;
}
/* Tabs */
.tabs {
display: flex;
background: var(--bg-tertiary);
border-bottom: 1px solid var(--border-color);
flex-shrink: 0;
}
.tab {
padding: 8px 20px;
background: transparent;
color: var(--text-secondary);
border: none;
border-bottom: 2px solid transparent;
font-family: inherit;
font-size: 13px;
cursor: pointer;
transition: all 0.2s;
}
.tab:hover {
color: var(--text-primary);
background: var(--bg-secondary);
}
.tab.active {
color: var(--primary-color);
border-bottom-color: var(--primary-color);
}
/* Tab Content */
.tab-content {
flex: 1;
overflow: hidden;
}
.tab-pane {
display: none;
height: 100%;
overflow-y: auto;
}
.tab-pane.active {
display: block;
}
/* Console */
.console {
padding: 12px;
background: var(--bg-primary);
font-size: 13px;
min-height: 100%;
}
.console-line {
margin-bottom: 8px;
display: flex;
align-items: flex-start;
gap: 8px;
}
.console-prompt {
color: var(--primary-color);
flex-shrink: 0;
}
.console-text {
color: var(--text-primary);
}
.console-error {
color: var(--error-color);
}
.console-warning {
color: var(--warning-color);
}
.console-success {
color: var(--success-color);
}
/* JavaScript Output */
.js-output-header {
display: flex;
justify-content: flex-end;
padding: 8px 12px;
background: var(--bg-tertiary);
border-bottom: 1px solid var(--border-color);
}
.js-actions {
display: flex;
gap: 8px;
}
.mini-btn {
padding: 4px 8px;
background: var(--bg-secondary);
color: var(--text-secondary);
border: 1px solid var(--border-color);
border-radius: 3px;
font-size: 12px;
cursor: pointer;
transition: all 0.2s;
}
.mini-btn:hover {
background: var(--bg-primary);
color: var(--text-primary);
}
.js-output {
padding: 12px;
background: var(--code-bg);
color: var(--text-primary);
font-family: 'Dank Mono', monospace;
font-size: 13px;
line-height: 1.5;
white-space: pre-wrap;
margin: 0;
min-height: calc(100% - 44px);
}
/* Execution Progress */
.execution-progress {
padding: 12px;
background: var(--bg-primary);
}
.progress-item {
display: flex;
align-items: center;
gap: 8px;
margin-bottom: 8px;
font-size: 13px;
}
.progress-icon {
color: var(--text-muted);
}
.progress-item.active .progress-icon {
color: var(--info-color);
animation: pulse 1s infinite;
}
.progress-item.completed .progress-icon {
color: var(--success-color);
}
.progress-item.error .progress-icon {
color: var(--error-color);
}
/* Playground */
.playground-wrapper {
flex: 1;
overflow: hidden;
}
#playground-frame {
width: 100%;
height: 100%;
border: none;
background: var(--bg-secondary);
}
/* Tutorial Intro Modal */
.tutorial-intro-modal {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: var(--modal-overlay);
display: flex;
align-items: center;
justify-content: center;
z-index: 2000;
transition: opacity 0.3s;
}
.tutorial-intro-modal.hidden {
display: none;
}
.intro-content {
background: var(--bg-tertiary);
border: 1px solid var(--border-color);
border-radius: 8px;
padding: 32px;
max-width: 500px;
box-shadow: 0 16px 48px rgba(0, 0, 0, 0.6);
}
.intro-content h2 {
color: var(--primary-color);
margin-bottom: 16px;
font-size: 24px;
}
.intro-content p {
color: var(--text-primary);
margin-bottom: 16px;
line-height: 1.6;
}
.intro-content ul {
list-style: none;
margin-bottom: 24px;
}
.intro-content li {
color: var(--text-secondary);
margin-bottom: 8px;
padding-left: 20px;
position: relative;
}
.intro-content li:before {
content: "▸";
position: absolute;
left: 0;
color: var(--primary-color);
}
.intro-actions {
display: flex;
gap: 12px;
justify-content: flex-end;
}
.intro-btn {
padding: 10px 24px;
background: var(--bg-secondary);
color: var(--text-primary);
border: 1px solid var(--border-color);
border-radius: 4px;
font-family: inherit;
font-size: 14px;
cursor: pointer;
transition: all 0.2s;
}
.intro-btn:hover {
background: var(--bg-primary);
border-color: var(--border-hover);
}
.intro-btn.primary {
background: var(--primary-color);
color: var(--bg-primary);
border-color: var(--primary-color);
}
.intro-btn.primary:hover {
background: var(--primary-hover);
border-color: var(--primary-hover);
}
/* Tutorial Navigation Bar */
.tutorial-nav {
position: fixed;
top: 0;
left: 0;
right: 0;
background: var(--bg-tertiary);
border-bottom: 1px solid var(--primary-color);
z-index: 1000;
transition: transform 0.3s;
}
.tutorial-nav.hidden {
transform: translateY(-100%);
}
.tutorial-nav-content {
display: flex;
align-items: center;
justify-content: space-between;
padding: 16px 24px;
}
.tutorial-left {
flex: 1;
}
.tutorial-step-title {
display: flex;
align-items: center;
gap: 16px;
margin-bottom: 8px;
}
.tutorial-step-title span:first-child {
color: var(--text-secondary);
font-size: 12px;
text-transform: uppercase;
}
.tutorial-step-title span:last-child {
color: var(--primary-color);
font-weight: 600;
font-size: 16px;
}
.tutorial-description {
color: var(--text-primary);
margin: 0;
font-size: 14px;
max-width: 600px;
}
.tutorial-right {
display: flex;
align-items: center;
}
.tutorial-progress-bar {
height: 3px;
background: var(--bg-secondary);
position: absolute;
bottom: 0;
left: 0;
right: 0;
}
.tutorial-progress-bar .progress-fill {
height: 100%;
background: var(--primary-color);
transition: width 0.3s;
}
/* Adjust app container when tutorial is active */
.app-container.tutorial-active {
padding-top: 80px;
}
.tutorial-controls {
display: flex;
gap: 12px;
}
.nav-btn {
padding: 8px 16px;
background: var(--bg-secondary);
color: var(--text-primary);
border: 1px solid var(--border-color);
border-radius: 4px;
font-family: inherit;
font-size: 13px;
cursor: pointer;
transition: all 0.2s;
}
.nav-btn:hover:not(:disabled) {
background: var(--bg-primary);
border-color: var(--border-hover);
}
.nav-btn:disabled {
opacity: 0.5;
cursor: not-allowed;
}
.nav-btn.primary {
background: var(--primary-color);
color: var(--bg-primary);
border-color: var(--primary-color);
}
.nav-btn.primary:hover {
background: var(--primary-hover);
border-color: var(--primary-hover);
}
.exit-btn {
width: 32px;
height: 32px;
background: transparent;
color: var(--text-secondary);
border: none;
font-size: 20px;
cursor: pointer;
border-radius: 4px;
transition: all 0.2s;
margin-left: 16px;
}
.exit-btn:hover {
background: var(--bg-secondary);
color: var(--text-primary);
}
/* Fullscreen Mode */
.playground-panel.fullscreen {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
z-index: 1500;
}
/* Animations */
@keyframes pulse {
0%, 100% { opacity: 1; }
50% { opacity: 0.5; }
}
/* Scrollbar Styling */
::-webkit-scrollbar {
width: 10px;
height: 10px;
}
::-webkit-scrollbar-track {
background: var(--bg-secondary);
}
::-webkit-scrollbar-thumb {
background: var(--border-color);
border-radius: 5px;
}
::-webkit-scrollbar-thumb:hover {
background: var(--border-hover);
}
/* Responsive */
@media (max-width: 768px) {
.app-container {
flex-direction: column;
}
.editor-panel,
.playground-panel {
min-width: auto;
width: 100%;
}
.editor-panel {
border-right: none;
border-bottom: 1px solid var(--border-color);
}
.output-section {
height: 200px;
}
}
/* ================================================================
Recording Timeline Styles
================================================================ */
.action-btn.record {
background: var(--bg-tertiary);
border-color: var(--error-color);
}
.action-btn.record:hover {
background: var(--error-color);
border-color: var(--error-color);
}
.action-btn.record.recording {
background: var(--error-color);
animation: pulse 1.5s infinite;
}
.action-btn.record.recording .icon {
animation: blink 1s infinite;
}
@keyframes pulse {
0%, 100% { opacity: 1; }
50% { opacity: 0.8; }
}
@keyframes blink {
0%, 100% { opacity: 1; }
50% { opacity: 0.3; }
}
.editor-container {
flex: 1;
display: flex;
flex-direction: column;
overflow: hidden;
}
#editor-view,
#timeline-view {
flex: 1;
display: flex;
flex-direction: column;
overflow: hidden;
}
.recording-timeline {
background: var(--bg-secondary);
display: flex;
flex-direction: column;
height: 100%;
}
.timeline-header {
display: flex;
justify-content: space-between;
align-items: center;
padding: 10px 15px;
border-bottom: 1px solid var(--border-color);
background: var(--bg-tertiary);
}
.timeline-header h3 {
font-size: 14px;
font-weight: 600;
color: var(--text-primary);
margin: 0;
}
.timeline-actions {
display: flex;
gap: 8px;
}
.timeline-events {
flex: 1;
overflow-y: auto;
padding: 10px;
}
.timeline-event {
display: flex;
align-items: center;
padding: 8px 10px;
margin-bottom: 6px;
background: var(--bg-tertiary);
border: 1px solid var(--border-color);
border-radius: 4px;
transition: all 0.2s;
cursor: pointer;
}
.timeline-event:hover {
border-color: var(--border-hover);
background: var(--code-bg);
}
.timeline-event.selected {
border-color: var(--primary-color);
background: rgba(15, 187, 170, 0.1);
}
.event-checkbox {
margin-right: 10px;
width: 16px;
height: 16px;
cursor: pointer;
}
.event-time {
font-size: 11px;
color: var(--text-muted);
margin-right: 10px;
font-family: 'Dank Mono', monospace;
min-width: 45px;
}
.event-command {
flex: 1;
font-family: 'Dank Mono', monospace;
font-size: 13px;
color: var(--text-primary);
}
.event-command .cmd-name {
color: var(--primary-color);
font-weight: 600;
}
.event-command .cmd-selector {
color: var(--info-color);
}
.event-command .cmd-value {
color: var(--warning-color);
}
.event-command .cmd-detail {
color: var(--text-secondary);
font-size: 11px;
margin-left: 5px;
}
.event-edit {
margin-left: 10px;
padding: 2px 8px;
font-size: 11px;
background: var(--bg-secondary);
border: 1px solid var(--border-color);
color: var(--text-secondary);
cursor: pointer;
border-radius: 3px;
transition: all 0.2s;
}
.event-edit:hover {
border-color: var(--primary-color);
color: var(--primary-color);
}
/* Event Editor Modal */
.modal-overlay {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: var(--modal-overlay);
z-index: 999;
}
.event-editor-modal {
position: fixed;
top: 50%;
left: 50%;
transform: translate(-50%, -50%);
background: var(--bg-secondary);
border: 1px solid var(--border-color);
border-radius: 8px;
padding: 20px;
z-index: 1000;
min-width: 400px;
}
.event-editor-modal h4 {
margin: 0 0 15px 0;
color: var(--text-primary);
font-family: 'Dank Mono', monospace;
}
.editor-field {
margin-bottom: 15px;
}
.editor-field label {
display: block;
margin-bottom: 5px;
font-size: 12px;
color: var(--text-secondary);
font-family: 'Dank Mono', monospace;
}
.editor-field input,
.editor-field select {
width: 100%;
padding: 8px;
background: var(--bg-tertiary);
border: 1px solid var(--border-color);
color: var(--text-primary);
border-radius: 4px;
font-family: 'Dank Mono', monospace;
font-size: 13px;
}
.editor-field input:focus,
.editor-field select:focus {
outline: none;
border-color: var(--primary-color);
}
.editor-actions {
display: flex;
justify-content: flex-end;
gap: 10px;
margin-top: 20px;
}
/* Blockly Button */
#blockly-btn .icon {
font-size: 16px;
}
/* Hidden State */
.hidden {
display: none !important;
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,591 +0,0 @@
// Blockly Manager for C4A-Script
// Handles Blockly workspace, code generation, and synchronization with text editor
class BlocklyManager {
constructor(tutorialApp) {
this.app = tutorialApp;
this.workspace = null;
this.isUpdating = false; // Prevent circular updates
this.blocklyVisible = false;
this.toolboxXml = this.generateToolbox();
this.init();
}
init() {
this.setupBlocklyContainer();
this.initializeWorkspace();
this.setupEventHandlers();
this.setupSynchronization();
}
setupBlocklyContainer() {
// Create blockly container div
const editorContainer = document.querySelector('.editor-container');
const blocklyDiv = document.createElement('div');
blocklyDiv.id = 'blockly-view';
blocklyDiv.className = 'blockly-workspace hidden';
blocklyDiv.style.height = '100%';
blocklyDiv.style.width = '100%';
editorContainer.appendChild(blocklyDiv);
}
generateToolbox() {
return `
<xml id="toolbox" style="display: none">
<category name="Navigation" colour="${BlockColors.NAVIGATION}">
<block type="c4a_go"></block>
<block type="c4a_reload"></block>
<block type="c4a_back"></block>
<block type="c4a_forward"></block>
</category>
<category name="Wait" colour="${BlockColors.WAIT}">
<block type="c4a_wait_time">
<field name="SECONDS">3</field>
</block>
<block type="c4a_wait_selector">
<field name="SELECTOR">#content</field>
<field name="TIMEOUT">10</field>
</block>
<block type="c4a_wait_text">
<field name="TEXT">Loading complete</field>
<field name="TIMEOUT">5</field>
</block>
</category>
<category name="Mouse Actions" colour="${BlockColors.ACTIONS}">
<block type="c4a_click">
<field name="SELECTOR">button.submit</field>
</block>
<block type="c4a_click_xy"></block>
<block type="c4a_double_click"></block>
<block type="c4a_right_click"></block>
<block type="c4a_move"></block>
<block type="c4a_drag"></block>
<block type="c4a_scroll">
<field name="DIRECTION">DOWN</field>
<field name="AMOUNT">500</field>
</block>
</category>
<category name="Keyboard" colour="${BlockColors.KEYBOARD}">
<block type="c4a_type">
<field name="TEXT">hello@example.com</field>
</block>
<block type="c4a_type_var">
<field name="VAR">email</field>
</block>
<block type="c4a_clear"></block>
<block type="c4a_set">
<field name="SELECTOR">#email</field>
<field name="VALUE">user@example.com</field>
</block>
<block type="c4a_press">
<field name="KEY">Tab</field>
</block>
<block type="c4a_key_down">
<field name="KEY">Shift</field>
</block>
<block type="c4a_key_up">
<field name="KEY">Shift</field>
</block>
</category>
<category name="Control Flow" colour="${BlockColors.CONTROL}">
<block type="c4a_if_exists">
<field name="SELECTOR">.cookie-banner</field>
</block>
<block type="c4a_if_exists_else">
<field name="SELECTOR">#user</field>
</block>
<block type="c4a_if_not_exists">
<field name="SELECTOR">.modal</field>
</block>
<block type="c4a_if_js">
<field name="CONDITION">window.innerWidth < 768</field>
</block>
<block type="c4a_repeat_times">
<field name="TIMES">5</field>
</block>
<block type="c4a_repeat_while">
<field name="CONDITION">document.querySelector('.load-more')</field>
</block>
</category>
<category name="Variables" colour="${BlockColors.VARIABLES}">
<block type="c4a_setvar">
<field name="NAME">username</field>
<field name="VALUE">john@example.com</field>
</block>
<block type="c4a_eval">
<field name="CODE">console.log('Hello')</field>
</block>
</category>
<category name="Procedures" colour="${BlockColors.PROCEDURES}">
<block type="c4a_proc_def">
<field name="NAME">login</field>
</block>
<block type="c4a_proc_call">
<field name="NAME">login</field>
</block>
</category>
<category name="Comments" colour="#9E9E9E">
<block type="c4a_comment">
<field name="TEXT">Add comment here</field>
</block>
</category>
</xml>`;
}
initializeWorkspace() {
const blocklyDiv = document.getElementById('blockly-view');
// Dark theme configuration
const theme = Blockly.Theme.defineTheme('c4a-dark', {
'base': Blockly.Themes.Classic,
'componentStyles': {
'workspaceBackgroundColour': '#0e0e10',
'toolboxBackgroundColour': '#1a1a1b',
'toolboxForegroundColour': '#e0e0e0',
'flyoutBackgroundColour': '#1a1a1b',
'flyoutForegroundColour': '#e0e0e0',
'flyoutOpacity': 0.9,
'scrollbarColour': '#2a2a2c',
'scrollbarOpacity': 0.5,
'insertionMarkerColour': '#0fbbaa',
'insertionMarkerOpacity': 0.3,
'markerColour': '#0fbbaa',
'cursorColour': '#0fbbaa',
'selectedGlowColour': '#0fbbaa',
'selectedGlowOpacity': 0.4,
'replacementGlowColour': '#0fbbaa',
'replacementGlowOpacity': 0.5
},
'fontStyle': {
'family': 'Dank Mono, Monaco, Consolas, monospace',
'weight': 'normal',
'size': 13
}
});
this.workspace = Blockly.inject(blocklyDiv, {
toolbox: this.toolboxXml,
theme: theme,
grid: {
spacing: 20,
length: 3,
colour: '#2a2a2c',
snap: true
},
zoom: {
controls: true,
wheel: true,
startScale: 1.0,
maxScale: 3,
minScale: 0.3,
scaleSpeed: 1.2
},
trashcan: true,
sounds: false,
media: 'https://unpkg.com/blockly/media/'
});
// Add workspace change listener
this.workspace.addChangeListener((event) => {
if (!this.isUpdating && event.type !== Blockly.Events.UI) {
this.syncBlocksToCode();
}
});
}
setupEventHandlers() {
// Add blockly toggle button
const headerActions = document.querySelector('.editor-panel .header-actions');
const blocklyBtn = document.createElement('button');
blocklyBtn.id = 'blockly-btn';
blocklyBtn.className = 'action-btn';
blocklyBtn.title = 'Toggle Blockly Mode';
blocklyBtn.innerHTML = '<span class="icon">🧩</span>';
// Insert before the Run button
const runBtn = document.getElementById('run-btn');
headerActions.insertBefore(blocklyBtn, runBtn);
blocklyBtn.addEventListener('click', () => this.toggleBlocklyView());
}
setupSynchronization() {
// Listen to CodeMirror changes
this.app.editor.on('change', (instance, changeObj) => {
if (!this.isUpdating && this.blocklyVisible && changeObj.origin !== 'setValue') {
this.syncCodeToBlocks();
}
});
}
toggleBlocklyView() {
const editorView = document.getElementById('editor-view');
const blocklyView = document.getElementById('blockly-view');
const timelineView = document.getElementById('timeline-view');
const blocklyBtn = document.getElementById('blockly-btn');
this.blocklyVisible = !this.blocklyVisible;
if (this.blocklyVisible) {
// Show Blockly
editorView.classList.add('hidden');
timelineView.classList.add('hidden');
blocklyView.classList.remove('hidden');
blocklyBtn.classList.add('active');
// Resize workspace
Blockly.svgResize(this.workspace);
// Sync current code to blocks
this.syncCodeToBlocks();
} else {
// Show editor
blocklyView.classList.add('hidden');
editorView.classList.remove('hidden');
blocklyBtn.classList.remove('active');
// Refresh CodeMirror
setTimeout(() => this.app.editor.refresh(), 100);
}
}
syncBlocksToCode() {
if (this.isUpdating) return;
try {
this.isUpdating = true;
// Generate C4A-Script from blocks using our custom generator
if (typeof c4aGenerator !== 'undefined') {
const code = c4aGenerator.workspaceToCode(this.workspace);
// Process the code to maintain proper formatting
const lines = code.split('\n');
const formattedLines = [];
let lastWasComment = false;
for (let i = 0; i < lines.length; i++) {
const line = lines[i].trim();
if (!line) continue;
const isComment = line.startsWith('#');
// Add blank line when transitioning between comments and commands
if (formattedLines.length > 0 && lastWasComment !== isComment) {
formattedLines.push('');
}
formattedLines.push(line);
lastWasComment = isComment;
}
const cleanCode = formattedLines.join('\n');
// Update CodeMirror
this.app.editor.setValue(cleanCode);
}
} catch (error) {
console.error('Error syncing blocks to code:', error);
} finally {
this.isUpdating = false;
}
}
syncCodeToBlocks() {
if (this.isUpdating) return;
try {
this.isUpdating = true;
// Clear workspace
this.workspace.clear();
// Parse C4A-Script and generate blocks
const code = this.app.editor.getValue();
const blocks = this.parseC4AToBlocks(code);
if (blocks) {
Blockly.Xml.domToWorkspace(blocks, this.workspace);
}
} catch (error) {
console.error('Error syncing code to blocks:', error);
// Show error in console
this.app.addConsoleMessage(`Blockly sync error: ${error.message}`, 'warning');
} finally {
this.isUpdating = false;
}
}
parseC4AToBlocks(code) {
const lines = code.split('\n');
const xml = document.createElement('xml');
let yPos = 20;
let previousBlock = null;
let rootBlock = null;
for (let i = 0; i < lines.length; i++) {
const line = lines[i].trim();
// Skip empty lines
if (!line) continue;
// Handle comments
if (line.startsWith('#')) {
const commentBlock = this.parseLineToBlock(line, i, lines);
if (commentBlock) {
if (previousBlock) {
// Connect to previous block
const next = document.createElement('next');
next.appendChild(commentBlock);
previousBlock.appendChild(next);
} else {
// First block - set position
commentBlock.setAttribute('x', 20);
commentBlock.setAttribute('y', yPos);
xml.appendChild(commentBlock);
rootBlock = commentBlock;
yPos += 60;
}
previousBlock = commentBlock;
}
continue;
}
const block = this.parseLineToBlock(line, i, lines);
if (block) {
if (previousBlock) {
// Connect to previous block using <next>
const next = document.createElement('next');
next.appendChild(block);
previousBlock.appendChild(next);
} else {
// First block - set position
block.setAttribute('x', 20);
block.setAttribute('y', yPos);
xml.appendChild(block);
rootBlock = block;
yPos += 60;
}
previousBlock = block;
}
}
return xml;
}
parseLineToBlock(line, index, allLines) {
// Navigation commands
if (line.startsWith('GO ')) {
const url = line.substring(3).trim();
return this.createBlock('c4a_go', { 'URL': url });
}
if (line === 'RELOAD') {
return this.createBlock('c4a_reload');
}
if (line === 'BACK') {
return this.createBlock('c4a_back');
}
if (line === 'FORWARD') {
return this.createBlock('c4a_forward');
}
// Wait commands
if (line.startsWith('WAIT ')) {
const parts = line.substring(5).trim();
// Check if it's just a number (wait time)
if (/^\d+(\.\d+)?$/.test(parts)) {
return this.createBlock('c4a_wait_time', { 'SECONDS': parts });
}
// Check for selector wait
const selectorMatch = parts.match(/^`([^`]+)`\s+(\d+)$/);
if (selectorMatch) {
return this.createBlock('c4a_wait_selector', {
'SELECTOR': selectorMatch[1],
'TIMEOUT': selectorMatch[2]
});
}
// Check for text wait
const textMatch = parts.match(/^"([^"]+)"\s+(\d+)$/);
if (textMatch) {
return this.createBlock('c4a_wait_text', {
'TEXT': textMatch[1],
'TIMEOUT': textMatch[2]
});
}
}
// Click commands
if (line.startsWith('CLICK ')) {
const target = line.substring(6).trim();
// Check for coordinates
const coordMatch = target.match(/^(\d+)\s+(\d+)$/);
if (coordMatch) {
return this.createBlock('c4a_click_xy', {
'X': coordMatch[1],
'Y': coordMatch[2]
});
}
// Selector click
const selectorMatch = target.match(/^`([^`]+)`$/);
if (selectorMatch) {
return this.createBlock('c4a_click', {
'SELECTOR': selectorMatch[1]
});
}
}
// Other mouse actions
if (line.startsWith('DOUBLE_CLICK ')) {
const selector = line.substring(13).trim().match(/^`([^`]+)`$/);
if (selector) {
return this.createBlock('c4a_double_click', {
'SELECTOR': selector[1]
});
}
}
if (line.startsWith('RIGHT_CLICK ')) {
const selector = line.substring(12).trim().match(/^`([^`]+)`$/);
if (selector) {
return this.createBlock('c4a_right_click', {
'SELECTOR': selector[1]
});
}
}
// Scroll
if (line.startsWith('SCROLL ')) {
const match = line.match(/^SCROLL\s+(UP|DOWN|LEFT|RIGHT)(?:\s+(\d+))?$/);
if (match) {
return this.createBlock('c4a_scroll', {
'DIRECTION': match[1],
'AMOUNT': match[2] || '500'
});
}
}
// Type commands
if (line.startsWith('TYPE ')) {
const content = line.substring(5).trim();
// Variable type
if (content.startsWith('$')) {
return this.createBlock('c4a_type_var', {
'VAR': content.substring(1)
});
}
// Text type
const textMatch = content.match(/^"([^"]*)"$/);
if (textMatch) {
return this.createBlock('c4a_type', {
'TEXT': textMatch[1]
});
}
}
// SET command
if (line.startsWith('SET ')) {
const match = line.match(/^SET\s+`([^`]+)`\s+"([^"]*)"$/);
if (match) {
return this.createBlock('c4a_set', {
'SELECTOR': match[1],
'VALUE': match[2]
});
}
}
// CLEAR command
if (line.startsWith('CLEAR ')) {
const match = line.match(/^CLEAR\s+`([^`]+)`$/);
if (match) {
return this.createBlock('c4a_clear', {
'SELECTOR': match[1]
});
}
}
// SETVAR command
if (line.startsWith('SETVAR ')) {
const match = line.match(/^SETVAR\s+(\w+)\s*=\s*"([^"]*)"$/);
if (match) {
return this.createBlock('c4a_setvar', {
'NAME': match[1],
'VALUE': match[2]
});
}
}
// IF commands (simplified - only single line)
if (line.startsWith('IF ')) {
// IF EXISTS
const existsMatch = line.match(/^IF\s+\(EXISTS\s+`([^`]+)`\)\s+THEN\s+(.+?)(?:\s+ELSE\s+(.+))?$/);
if (existsMatch) {
if (existsMatch[3]) {
// Has ELSE
const block = this.createBlock('c4a_if_exists_else', {
'SELECTOR': existsMatch[1]
});
// Parse then and else commands - simplified for now
return block;
} else {
// No ELSE
const block = this.createBlock('c4a_if_exists', {
'SELECTOR': existsMatch[1]
});
return block;
}
}
// IF NOT EXISTS
const notExistsMatch = line.match(/^IF\s+\(NOT\s+EXISTS\s+`([^`]+)`\)\s+THEN\s+(.+)$/);
if (notExistsMatch) {
const block = this.createBlock('c4a_if_not_exists', {
'SELECTOR': notExistsMatch[1]
});
return block;
}
}
// Comments
if (line.startsWith('#')) {
return this.createBlock('c4a_comment', {
'TEXT': line.substring(1).trim()
});
}
// If we can't parse it, return null
return null;
}
createBlock(type, fields = {}) {
const block = document.createElement('block');
block.setAttribute('type', type);
// Add fields
for (const [name, value] of Object.entries(fields)) {
const field = document.createElement('field');
field.setAttribute('name', name);
field.textContent = value;
block.appendChild(field);
}
return block;
}
}

View File

@@ -1,238 +0,0 @@
/* Blockly Theme CSS for C4A-Script */
/* Blockly workspace container */
.blockly-workspace {
position: relative;
width: 100%;
height: 100%;
background: var(--bg-primary);
}
/* Blockly button active state */
#blockly-btn.active {
background: var(--primary-color);
color: var(--bg-primary);
border-color: var(--primary-color);
}
#blockly-btn.active:hover {
background: var(--primary-hover);
border-color: var(--primary-hover);
}
/* Override Blockly's default styles for dark theme */
.blocklyToolboxDiv {
background-color: var(--bg-tertiary) !important;
border-right: 1px solid var(--border-color) !important;
}
.blocklyFlyout {
background-color: var(--bg-secondary) !important;
}
.blocklyFlyoutBackground {
fill: var(--bg-secondary) !important;
}
.blocklyMainBackground {
stroke: none !important;
}
.blocklyTreeRow {
color: var(--text-primary) !important;
font-family: 'Dank Mono', monospace !important;
padding: 4px 16px !important;
margin: 2px 0 !important;
}
.blocklyTreeRow:hover {
background-color: var(--bg-secondary) !important;
}
.blocklyTreeSelected {
background-color: var(--primary-dim) !important;
}
.blocklyTreeLabel {
cursor: pointer;
}
/* Blockly scrollbars */
.blocklyScrollbarHorizontal,
.blocklyScrollbarVertical {
background-color: transparent !important;
}
.blocklyScrollbarHandle {
fill: var(--border-color) !important;
opacity: 0.5 !important;
}
.blocklyScrollbarHandle:hover {
fill: var(--border-hover) !important;
opacity: 0.8 !important;
}
/* Blockly zoom controls */
.blocklyZoom > image {
opacity: 0.6;
}
.blocklyZoom > image:hover {
opacity: 1;
}
/* Blockly trash can */
.blocklyTrash {
opacity: 0.6;
}
.blocklyTrash:hover {
opacity: 1;
}
/* Blockly context menus */
.blocklyContextMenu {
background-color: var(--bg-tertiary) !important;
border: 1px solid var(--border-color) !important;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.3) !important;
}
.blocklyMenuItem {
color: var(--text-primary) !important;
font-family: 'Dank Mono', monospace !important;
}
.blocklyMenuItemDisabled {
color: var(--text-muted) !important;
}
.blocklyMenuItem:hover {
background-color: var(--bg-secondary) !important;
}
/* Blockly text inputs */
.blocklyHtmlInput {
background-color: var(--bg-tertiary) !important;
color: var(--text-primary) !important;
border: 1px solid var(--border-color) !important;
font-family: 'Dank Mono', monospace !important;
font-size: 13px !important;
padding: 4px 8px !important;
}
.blocklyHtmlInput:focus {
border-color: var(--primary-color) !important;
outline: none !important;
}
/* Blockly dropdowns */
.blocklyDropDownDiv {
background-color: var(--bg-tertiary) !important;
border: 1px solid var(--border-color) !important;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.3) !important;
}
.blocklyDropDownContent {
color: var(--text-primary) !important;
}
.blocklyDropDownDiv .goog-menuitem {
color: var(--text-primary) !important;
font-family: 'Dank Mono', monospace !important;
padding: 4px 16px !important;
}
.blocklyDropDownDiv .goog-menuitem-highlight,
.blocklyDropDownDiv .goog-menuitem-hover {
background-color: var(--bg-secondary) !important;
}
/* Custom block colors are defined in the block definitions */
/* Block text styling */
.blocklyText {
fill: #ffffff !important;
font-family: 'Dank Mono', monospace !important;
font-size: 13px !important;
}
.blocklyEditableText > .blocklyText {
fill: #ffffff !important;
}
.blocklyEditableText:hover > rect {
stroke: var(--primary-color) !important;
stroke-width: 2px !important;
}
/* Improve visibility of connection highlights */
.blocklyHighlightedConnectionPath {
stroke: var(--primary-color) !important;
stroke-width: 4px !important;
}
.blocklyInsertionMarker > .blocklyPath {
fill-opacity: 0.3 !important;
stroke-opacity: 0.6 !important;
}
/* Workspace grid pattern */
.blocklyWorkspace > .blocklyBlockCanvas > .blocklyGridCanvas {
opacity: 0.1;
}
/* Smooth transitions */
.blocklyDraggable {
transition: transform 0.1s ease;
}
/* Field labels */
.blocklyFieldLabel {
font-weight: normal !important;
}
/* Comment blocks styling */
.blocklyCommentText {
font-style: italic !important;
}
/* Make comment blocks slightly transparent */
g[data-category="Comments"] .blocklyPath {
fill-opacity: 0.8 !important;
}
/* Better visibility for disabled blocks */
.blocklyDisabled > .blocklyPath {
fill-opacity: 0.3 !important;
}
.blocklyDisabled > .blocklyText {
fill-opacity: 0.5 !important;
}
/* Warning and error text */
.blocklyWarningText,
.blocklyErrorText {
font-family: 'Dank Mono', monospace !important;
font-size: 12px !important;
}
/* Workspace scrollbar improvement for dark theme */
::-webkit-scrollbar {
width: 10px;
height: 10px;
}
::-webkit-scrollbar-track {
background: var(--bg-secondary);
}
::-webkit-scrollbar-thumb {
background: var(--border-color);
border-radius: 5px;
}
::-webkit-scrollbar-thumb:hover {
background: var(--border-hover);
}

View File

@@ -1,549 +0,0 @@
// C4A-Script Blockly Block Definitions
// This file defines all custom blocks for C4A-Script commands
// Color scheme for different block categories
const BlockColors = {
NAVIGATION: '#1E88E5', // Blue
ACTIONS: '#43A047', // Green
CONTROL: '#FB8C00', // Orange
VARIABLES: '#8E24AA', // Purple
WAIT: '#E53935', // Red
KEYBOARD: '#00ACC1', // Cyan
PROCEDURES: '#6A1B9A' // Deep Purple
};
// Helper to create selector input with backticks
Blockly.Blocks['c4a_selector_input'] = {
init: function() {
this.appendDummyInput()
.appendField("`")
.appendField(new Blockly.FieldTextInput("selector"), "SELECTOR")
.appendField("`");
this.setOutput(true, "Selector");
this.setColour(BlockColors.ACTIONS);
this.setTooltip("CSS selector for element");
}
};
// ============================================
// NAVIGATION BLOCKS
// ============================================
Blockly.Blocks['c4a_go'] = {
init: function() {
this.appendDummyInput()
.appendField("GO")
.appendField(new Blockly.FieldTextInput("https://example.com"), "URL");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.NAVIGATION);
this.setTooltip("Navigate to URL");
}
};
Blockly.Blocks['c4a_reload'] = {
init: function() {
this.appendDummyInput()
.appendField("RELOAD");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.NAVIGATION);
this.setTooltip("Reload current page");
}
};
Blockly.Blocks['c4a_back'] = {
init: function() {
this.appendDummyInput()
.appendField("BACK");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.NAVIGATION);
this.setTooltip("Go back in browser history");
}
};
Blockly.Blocks['c4a_forward'] = {
init: function() {
this.appendDummyInput()
.appendField("FORWARD");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.NAVIGATION);
this.setTooltip("Go forward in browser history");
}
};
// ============================================
// WAIT BLOCKS
// ============================================
Blockly.Blocks['c4a_wait_time'] = {
init: function() {
this.appendDummyInput()
.appendField("WAIT")
.appendField(new Blockly.FieldNumber(1, 0), "SECONDS")
.appendField("seconds");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.WAIT);
this.setTooltip("Wait for specified seconds");
}
};
Blockly.Blocks['c4a_wait_selector'] = {
init: function() {
this.appendDummyInput()
.appendField("WAIT for")
.appendField("`")
.appendField(new Blockly.FieldTextInput("selector"), "SELECTOR")
.appendField("`")
.appendField("max")
.appendField(new Blockly.FieldNumber(10, 1), "TIMEOUT")
.appendField("sec");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.WAIT);
this.setTooltip("Wait for element to appear");
}
};
Blockly.Blocks['c4a_wait_text'] = {
init: function() {
this.appendDummyInput()
.appendField("WAIT for text")
.appendField(new Blockly.FieldTextInput("Loading complete"), "TEXT")
.appendField("max")
.appendField(new Blockly.FieldNumber(5, 1), "TIMEOUT")
.appendField("sec");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.WAIT);
this.setTooltip("Wait for text to appear on page");
}
};
// ============================================
// MOUSE ACTION BLOCKS
// ============================================
Blockly.Blocks['c4a_click'] = {
init: function() {
this.appendDummyInput()
.appendField("CLICK")
.appendField("`")
.appendField(new Blockly.FieldTextInput("button"), "SELECTOR")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Click on element");
}
};
Blockly.Blocks['c4a_click_xy'] = {
init: function() {
this.appendDummyInput()
.appendField("CLICK at")
.appendField("X:")
.appendField(new Blockly.FieldNumber(100, 0), "X")
.appendField("Y:")
.appendField(new Blockly.FieldNumber(100, 0), "Y");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Click at coordinates");
}
};
Blockly.Blocks['c4a_double_click'] = {
init: function() {
this.appendDummyInput()
.appendField("DOUBLE_CLICK")
.appendField("`")
.appendField(new Blockly.FieldTextInput(".item"), "SELECTOR")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Double click on element");
}
};
Blockly.Blocks['c4a_right_click'] = {
init: function() {
this.appendDummyInput()
.appendField("RIGHT_CLICK")
.appendField("`")
.appendField(new Blockly.FieldTextInput("#menu"), "SELECTOR")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Right click on element");
}
};
Blockly.Blocks['c4a_move'] = {
init: function() {
this.appendDummyInput()
.appendField("MOVE to")
.appendField("X:")
.appendField(new Blockly.FieldNumber(500, 0), "X")
.appendField("Y:")
.appendField(new Blockly.FieldNumber(300, 0), "Y");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Move mouse to position");
}
};
Blockly.Blocks['c4a_drag'] = {
init: function() {
this.appendDummyInput()
.appendField("DRAG from")
.appendField("X:")
.appendField(new Blockly.FieldNumber(100, 0), "X1")
.appendField("Y:")
.appendField(new Blockly.FieldNumber(100, 0), "Y1");
this.appendDummyInput()
.appendField("to")
.appendField("X:")
.appendField(new Blockly.FieldNumber(500, 0), "X2")
.appendField("Y:")
.appendField(new Blockly.FieldNumber(300, 0), "Y2");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Drag from one point to another");
}
};
Blockly.Blocks['c4a_scroll'] = {
init: function() {
this.appendDummyInput()
.appendField("SCROLL")
.appendField(new Blockly.FieldDropdown([
["DOWN", "DOWN"],
["UP", "UP"],
["LEFT", "LEFT"],
["RIGHT", "RIGHT"]
]), "DIRECTION")
.appendField(new Blockly.FieldNumber(500, 0), "AMOUNT")
.appendField("pixels");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Scroll in direction");
}
};
// ============================================
// KEYBOARD BLOCKS
// ============================================
Blockly.Blocks['c4a_type'] = {
init: function() {
this.appendDummyInput()
.appendField("TYPE")
.appendField(new Blockly.FieldTextInput("text to type"), "TEXT");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Type text");
}
};
Blockly.Blocks['c4a_type_var'] = {
init: function() {
this.appendDummyInput()
.appendField("TYPE")
.appendField("$")
.appendField(new Blockly.FieldTextInput("variable"), "VAR");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Type variable value");
}
};
Blockly.Blocks['c4a_clear'] = {
init: function() {
this.appendDummyInput()
.appendField("CLEAR")
.appendField("`")
.appendField(new Blockly.FieldTextInput("input"), "SELECTOR")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Clear input field");
}
};
Blockly.Blocks['c4a_set'] = {
init: function() {
this.appendDummyInput()
.appendField("SET")
.appendField("`")
.appendField(new Blockly.FieldTextInput("#input"), "SELECTOR")
.appendField("`")
.appendField("to")
.appendField(new Blockly.FieldTextInput("value"), "VALUE");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Set input field value");
}
};
Blockly.Blocks['c4a_press'] = {
init: function() {
this.appendDummyInput()
.appendField("PRESS")
.appendField(new Blockly.FieldDropdown([
["Tab", "Tab"],
["Enter", "Enter"],
["Escape", "Escape"],
["Space", "Space"],
["ArrowUp", "ArrowUp"],
["ArrowDown", "ArrowDown"],
["ArrowLeft", "ArrowLeft"],
["ArrowRight", "ArrowRight"],
["Delete", "Delete"],
["Backspace", "Backspace"]
]), "KEY");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Press and release key");
}
};
Blockly.Blocks['c4a_key_down'] = {
init: function() {
this.appendDummyInput()
.appendField("KEY_DOWN")
.appendField(new Blockly.FieldDropdown([
["Shift", "Shift"],
["Control", "Control"],
["Alt", "Alt"],
["Meta", "Meta"]
]), "KEY");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Hold key down");
}
};
Blockly.Blocks['c4a_key_up'] = {
init: function() {
this.appendDummyInput()
.appendField("KEY_UP")
.appendField(new Blockly.FieldDropdown([
["Shift", "Shift"],
["Control", "Control"],
["Alt", "Alt"],
["Meta", "Meta"]
]), "KEY");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Release key");
}
};
// ============================================
// CONTROL FLOW BLOCKS
// ============================================
Blockly.Blocks['c4a_if_exists'] = {
init: function() {
this.appendDummyInput()
.appendField("IF EXISTS")
.appendField("`")
.appendField(new Blockly.FieldTextInput(".element"), "SELECTOR")
.appendField("`")
.appendField("THEN");
this.appendStatementInput("THEN")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("If element exists, then do something");
}
};
Blockly.Blocks['c4a_if_exists_else'] = {
init: function() {
this.appendDummyInput()
.appendField("IF EXISTS")
.appendField("`")
.appendField(new Blockly.FieldTextInput(".element"), "SELECTOR")
.appendField("`")
.appendField("THEN");
this.appendStatementInput("THEN")
.setCheck(null);
this.appendDummyInput()
.appendField("ELSE");
this.appendStatementInput("ELSE")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("If element exists, then do something, else do something else");
}
};
Blockly.Blocks['c4a_if_not_exists'] = {
init: function() {
this.appendDummyInput()
.appendField("IF NOT EXISTS")
.appendField("`")
.appendField(new Blockly.FieldTextInput(".element"), "SELECTOR")
.appendField("`")
.appendField("THEN");
this.appendStatementInput("THEN")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("If element does not exist, then do something");
}
};
Blockly.Blocks['c4a_if_js'] = {
init: function() {
this.appendDummyInput()
.appendField("IF")
.appendField("`")
.appendField(new Blockly.FieldTextInput("window.innerWidth < 768"), "CONDITION")
.appendField("`")
.appendField("THEN");
this.appendStatementInput("THEN")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("If JavaScript condition is true");
}
};
Blockly.Blocks['c4a_repeat_times'] = {
init: function() {
this.appendDummyInput()
.appendField("REPEAT")
.appendField(new Blockly.FieldNumber(5, 1), "TIMES")
.appendField("times");
this.appendStatementInput("DO")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("Repeat commands N times");
}
};
Blockly.Blocks['c4a_repeat_while'] = {
init: function() {
this.appendDummyInput()
.appendField("REPEAT WHILE")
.appendField("`")
.appendField(new Blockly.FieldTextInput("document.querySelector('.load-more')"), "CONDITION")
.appendField("`");
this.appendStatementInput("DO")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("Repeat while condition is true");
}
};
// ============================================
// VARIABLE BLOCKS
// ============================================
Blockly.Blocks['c4a_setvar'] = {
init: function() {
this.appendDummyInput()
.appendField("SETVAR")
.appendField(new Blockly.FieldTextInput("username"), "NAME")
.appendField("=")
.appendField(new Blockly.FieldTextInput("value"), "VALUE");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.VARIABLES);
this.setTooltip("Set variable value");
}
};
// ============================================
// ADVANCED BLOCKS
// ============================================
Blockly.Blocks['c4a_eval'] = {
init: function() {
this.appendDummyInput()
.appendField("EVAL")
.appendField("`")
.appendField(new Blockly.FieldTextInput("console.log('Hello')"), "CODE")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.VARIABLES);
this.setTooltip("Execute JavaScript code");
}
};
Blockly.Blocks['c4a_comment'] = {
init: function() {
this.appendDummyInput()
.appendField("#")
.appendField(new Blockly.FieldTextInput("Comment", null, {
spellcheck: false,
class: 'blocklyCommentText'
}), "TEXT");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour("#616161");
this.setTooltip("Add a comment");
this.setStyle('comment_blocks');
}
};
// ============================================
// PROCEDURE BLOCKS
// ============================================
Blockly.Blocks['c4a_proc_def'] = {
init: function() {
this.appendDummyInput()
.appendField("PROC")
.appendField(new Blockly.FieldTextInput("procedure_name"), "NAME");
this.appendStatementInput("BODY")
.setCheck(null);
this.appendDummyInput()
.appendField("ENDPROC");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.PROCEDURES);
this.setTooltip("Define a procedure");
}
};
Blockly.Blocks['c4a_proc_call'] = {
init: function() {
this.appendDummyInput()
.appendField("Call")
.appendField(new Blockly.FieldTextInput("procedure_name"), "NAME");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.PROCEDURES);
this.setTooltip("Call a procedure");
}
};
// Code generators have been moved to c4a-generator.js

View File

@@ -1,261 +0,0 @@
// C4A-Script Code Generator for Blockly
// Compatible with latest Blockly API
// Create a custom code generator for C4A-Script
const c4aGenerator = new Blockly.Generator('C4A');
// Helper to get field value with proper escaping
c4aGenerator.getFieldValue = function(block, fieldName) {
return block.getFieldValue(fieldName);
};
// Navigation generators
c4aGenerator.forBlock['c4a_go'] = function(block, generator) {
const url = generator.getFieldValue(block, 'URL');
return `GO ${url}\n`;
};
c4aGenerator.forBlock['c4a_reload'] = function(block, generator) {
return 'RELOAD\n';
};
c4aGenerator.forBlock['c4a_back'] = function(block, generator) {
return 'BACK\n';
};
c4aGenerator.forBlock['c4a_forward'] = function(block, generator) {
return 'FORWARD\n';
};
// Wait generators
c4aGenerator.forBlock['c4a_wait_time'] = function(block, generator) {
const seconds = generator.getFieldValue(block, 'SECONDS');
return `WAIT ${seconds}\n`;
};
c4aGenerator.forBlock['c4a_wait_selector'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const timeout = generator.getFieldValue(block, 'TIMEOUT');
return `WAIT \`${selector}\` ${timeout}\n`;
};
c4aGenerator.forBlock['c4a_wait_text'] = function(block, generator) {
const text = generator.getFieldValue(block, 'TEXT');
const timeout = generator.getFieldValue(block, 'TIMEOUT');
return `WAIT "${text}" ${timeout}\n`;
};
// Mouse action generators
c4aGenerator.forBlock['c4a_click'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
return `CLICK \`${selector}\`\n`;
};
c4aGenerator.forBlock['c4a_click_xy'] = function(block, generator) {
const x = generator.getFieldValue(block, 'X');
const y = generator.getFieldValue(block, 'Y');
return `CLICK ${x} ${y}\n`;
};
c4aGenerator.forBlock['c4a_double_click'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
return `DOUBLE_CLICK \`${selector}\`\n`;
};
c4aGenerator.forBlock['c4a_right_click'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
return `RIGHT_CLICK \`${selector}\`\n`;
};
c4aGenerator.forBlock['c4a_move'] = function(block, generator) {
const x = generator.getFieldValue(block, 'X');
const y = generator.getFieldValue(block, 'Y');
return `MOVE ${x} ${y}\n`;
};
c4aGenerator.forBlock['c4a_drag'] = function(block, generator) {
const x1 = generator.getFieldValue(block, 'X1');
const y1 = generator.getFieldValue(block, 'Y1');
const x2 = generator.getFieldValue(block, 'X2');
const y2 = generator.getFieldValue(block, 'Y2');
return `DRAG ${x1} ${y1} ${x2} ${y2}\n`;
};
c4aGenerator.forBlock['c4a_scroll'] = function(block, generator) {
const direction = generator.getFieldValue(block, 'DIRECTION');
const amount = generator.getFieldValue(block, 'AMOUNT');
return `SCROLL ${direction} ${amount}\n`;
};
// Keyboard generators
c4aGenerator.forBlock['c4a_type'] = function(block, generator) {
const text = generator.getFieldValue(block, 'TEXT');
return `TYPE "${text}"\n`;
};
c4aGenerator.forBlock['c4a_type_var'] = function(block, generator) {
const varName = generator.getFieldValue(block, 'VAR');
return `TYPE $${varName}\n`;
};
c4aGenerator.forBlock['c4a_clear'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
return `CLEAR \`${selector}\`\n`;
};
c4aGenerator.forBlock['c4a_set'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const value = generator.getFieldValue(block, 'VALUE');
return `SET \`${selector}\` "${value}"\n`;
};
c4aGenerator.forBlock['c4a_press'] = function(block, generator) {
const key = generator.getFieldValue(block, 'KEY');
return `PRESS ${key}\n`;
};
c4aGenerator.forBlock['c4a_key_down'] = function(block, generator) {
const key = generator.getFieldValue(block, 'KEY');
return `KEY_DOWN ${key}\n`;
};
c4aGenerator.forBlock['c4a_key_up'] = function(block, generator) {
const key = generator.getFieldValue(block, 'KEY');
return `KEY_UP ${key}\n`;
};
// Control flow generators
c4aGenerator.forBlock['c4a_if_exists'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const thenCode = generator.statementToCode(block, 'THEN').trim();
if (thenCode.includes('\n')) {
// Multi-line then block
const lines = thenCode.split('\n').filter(line => line.trim());
return lines.map(line => `IF (EXISTS \`${selector}\`) THEN ${line}`).join('\n') + '\n';
} else if (thenCode) {
// Single line
return `IF (EXISTS \`${selector}\`) THEN ${thenCode}\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_if_exists_else'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const thenCode = generator.statementToCode(block, 'THEN').trim();
const elseCode = generator.statementToCode(block, 'ELSE').trim();
// For simplicity, only handle single-line then/else
const thenLine = thenCode.split('\n')[0];
const elseLine = elseCode.split('\n')[0];
if (thenLine && elseLine) {
return `IF (EXISTS \`${selector}\`) THEN ${thenLine} ELSE ${elseLine}\n`;
} else if (thenLine) {
return `IF (EXISTS \`${selector}\`) THEN ${thenLine}\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_if_not_exists'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const thenCode = generator.statementToCode(block, 'THEN').trim();
if (thenCode.includes('\n')) {
const lines = thenCode.split('\n').filter(line => line.trim());
return lines.map(line => `IF (NOT EXISTS \`${selector}\`) THEN ${line}`).join('\n') + '\n';
} else if (thenCode) {
return `IF (NOT EXISTS \`${selector}\`) THEN ${thenCode}\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_if_js'] = function(block, generator) {
const condition = generator.getFieldValue(block, 'CONDITION');
const thenCode = generator.statementToCode(block, 'THEN').trim();
if (thenCode.includes('\n')) {
const lines = thenCode.split('\n').filter(line => line.trim());
return lines.map(line => `IF (\`${condition}\`) THEN ${line}`).join('\n') + '\n';
} else if (thenCode) {
return `IF (\`${condition}\`) THEN ${thenCode}\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_repeat_times'] = function(block, generator) {
const times = generator.getFieldValue(block, 'TIMES');
const doCode = generator.statementToCode(block, 'DO').trim();
if (doCode) {
// Get first command for repeat
const firstLine = doCode.split('\n')[0];
return `REPEAT (${firstLine}, ${times})\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_repeat_while'] = function(block, generator) {
const condition = generator.getFieldValue(block, 'CONDITION');
const doCode = generator.statementToCode(block, 'DO').trim();
if (doCode) {
// Get first command for repeat
const firstLine = doCode.split('\n')[0];
return `REPEAT (${firstLine}, \`${condition}\`)\n`;
}
return '';
};
// Variable generators
c4aGenerator.forBlock['c4a_setvar'] = function(block, generator) {
const name = generator.getFieldValue(block, 'NAME');
const value = generator.getFieldValue(block, 'VALUE');
return `SETVAR ${name} = "${value}"\n`;
};
// Advanced generators
c4aGenerator.forBlock['c4a_eval'] = function(block, generator) {
const code = generator.getFieldValue(block, 'CODE');
return `EVAL \`${code}\`\n`;
};
c4aGenerator.forBlock['c4a_comment'] = function(block, generator) {
const text = generator.getFieldValue(block, 'TEXT');
return `# ${text}\n`;
};
// Procedure generators
c4aGenerator.forBlock['c4a_proc_def'] = function(block, generator) {
const name = generator.getFieldValue(block, 'NAME');
const body = generator.statementToCode(block, 'BODY');
return `PROC ${name}\n${body}ENDPROC\n`;
};
c4aGenerator.forBlock['c4a_proc_call'] = function(block, generator) {
const name = generator.getFieldValue(block, 'NAME');
return `${name}\n`;
};
// Override scrub_ to handle our custom format
c4aGenerator.scrub_ = function(block, code, opt_thisOnly) {
const nextBlock = block.nextConnection && block.nextConnection.targetBlock();
let nextCode = '';
if (nextBlock) {
if (!opt_thisOnly) {
nextCode = c4aGenerator.blockToCode(nextBlock);
// Add blank line between comment and non-comment blocks
const currentIsComment = block.type === 'c4a_comment';
const nextIsComment = nextBlock.type === 'c4a_comment';
// Add blank line when transitioning from command to comment or vice versa
if (currentIsComment !== nextIsComment && code.trim() && nextCode.trim()) {
nextCode = '\n' + nextCode;
}
}
}
return code + nextCode;
};

View File

@@ -1,531 +0,0 @@
/* DankMono Font Faces */
@font-face {
font-family: 'DankMono';
src: url('DankMono-Regular.woff2') format('woff2');
font-weight: 400;
font-style: normal;
}
@font-face {
font-family: 'DankMono';
src: url('DankMono-Bold.woff2') format('woff2');
font-weight: 700;
font-style: normal;
}
@font-face {
font-family: 'DankMono';
src: url('DankMono-Italic.woff2') format('woff2');
font-weight: 400;
font-style: italic;
}
/* Root Variables - Matching docs theme */
:root {
--global-font-size: 14px;
--global-code-font-size: 13px;
--global-line-height: 1.5em;
--global-space: 10px;
--font-stack: DankMono, Monaco, Courier New, monospace;
--mono-font-stack: DankMono, Monaco, Courier New, monospace;
--background-color: #070708;
--font-color: #e8e9ed;
--invert-font-color: #222225;
--secondary-color: #d5cec0;
--tertiary-color: #a3abba;
--primary-color: #0fbbaa;
--error-color: #ff3c74;
--progress-bar-background: #3f3f44;
--progress-bar-fill: #09b5a5;
--code-bg-color: #3f3f44;
--block-background-color: #202020;
--header-height: 55px;
}
/* Base Styles */
* {
box-sizing: border-box;
}
body {
margin: 0;
padding: 0;
font-family: var(--font-stack);
font-size: var(--global-font-size);
line-height: var(--global-line-height);
color: var(--font-color);
background-color: var(--background-color);
}
/* Terminal Framework */
.terminal {
min-height: 100vh;
}
.container {
width: 100%;
margin: 0 auto;
}
/* Header */
.header-container {
position: fixed;
top: 0;
left: 0;
right: 0;
height: var(--header-height);
background-color: var(--background-color);
border-bottom: 1px solid var(--progress-bar-background);
z-index: 1000;
padding: 0 calc(var(--global-space) * 2);
}
.terminal-nav {
display: flex;
align-items: center;
justify-content: space-between;
height: 100%;
}
.terminal-logo h1 {
margin: 0;
font-size: 1.2em;
color: var(--primary-color);
font-weight: 400;
}
.terminal-menu ul {
list-style: none;
margin: 0;
padding: 0;
display: flex;
gap: 2em;
}
.terminal-menu a {
color: var(--secondary-color);
text-decoration: none;
transition: color 0.2s;
}
.terminal-menu a:hover,
.terminal-menu a.active {
color: var(--primary-color);
}
/* Main Container */
.main-container {
padding-top: calc(var(--header-height) + 2em);
padding-left: 2em;
padding-right: 2em;
max-width: 1400px;
margin: 0 auto;
}
/* Tutorial Grid */
.tutorial-grid {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 2em;
align-items: start;
}
/* Terminal Cards */
.terminal-card {
background-color: var(--block-background-color);
border: 1px solid var(--progress-bar-background);
margin-bottom: 1.5em;
}
.terminal-card header {
background-color: var(--progress-bar-background);
padding: 0.8em 1em;
font-weight: 700;
color: var(--font-color);
display: flex;
justify-content: space-between;
align-items: center;
}
.terminal-card > div {
padding: 1.5em;
}
/* Editor Section */
.editor-controls {
display: flex;
gap: 0.5em;
}
.editor-container {
height: 300px;
overflow: hidden;
}
#c4a-editor {
width: 100%;
height: 100%;
font-family: var(--mono-font-stack);
font-size: var(--global-code-font-size);
background-color: var(--code-bg-color);
color: var(--font-color);
border: none;
padding: 1em;
resize: none;
}
/* JS Output */
.js-output-container {
max-height: 300px;
overflow-y: auto;
}
.js-output-container pre {
margin: 0;
padding: 1em;
background-color: var(--code-bg-color);
}
.js-output-container code {
font-family: var(--mono-font-stack);
font-size: var(--global-code-font-size);
color: var(--font-color);
white-space: pre-wrap;
}
/* Console Output */
.console-output {
font-family: var(--mono-font-stack);
font-size: var(--global-code-font-size);
max-height: 200px;
overflow-y: auto;
padding: 1em;
}
.console-line {
margin-bottom: 0.5em;
}
.console-prompt {
color: var(--primary-color);
margin-right: 0.5em;
}
.console-text {
color: var(--font-color);
}
.console-error {
color: var(--error-color);
}
.console-success {
color: var(--primary-color);
}
/* Playground */
.playground-container {
height: 600px;
background-color: #fff;
border: 1px solid var(--progress-bar-background);
}
#playground-frame {
width: 100%;
height: 100%;
border: none;
}
/* Execution Progress */
.execution-progress {
padding: 1em;
}
.progress-item {
display: flex;
align-items: center;
gap: 0.8em;
margin-bottom: 0.8em;
color: var(--secondary-color);
}
.progress-item.active {
color: var(--primary-color);
}
.progress-item.completed {
color: var(--tertiary-color);
}
.progress-item.error {
color: var(--error-color);
}
.progress-icon {
font-size: 1.2em;
}
/* Buttons */
.btn {
background-color: var(--primary-color);
color: var(--background-color);
border: none;
padding: 0.5em 1em;
font-family: var(--font-stack);
font-size: 0.9em;
cursor: pointer;
transition: all 0.2s;
}
.btn:hover {
background-color: var(--progress-bar-fill);
}
.btn-sm {
padding: 0.3em 0.8em;
font-size: 0.85em;
}
.btn-ghost {
background-color: transparent;
color: var(--secondary-color);
border: 1px solid var(--progress-bar-background);
}
.btn-ghost:hover {
background-color: var(--progress-bar-background);
color: var(--font-color);
}
/* Scrollbars */
::-webkit-scrollbar {
width: 8px;
height: 8px;
}
::-webkit-scrollbar-track {
background: var(--block-background-color);
}
::-webkit-scrollbar-thumb {
background: var(--progress-bar-background);
}
::-webkit-scrollbar-thumb:hover {
background: var(--secondary-color);
}
/* CodeMirror Theme Override */
.CodeMirror {
font-family: var(--mono-font-stack) !important;
font-size: var(--global-code-font-size) !important;
background-color: var(--code-bg-color) !important;
color: var(--font-color) !important;
height: 100% !important;
}
.CodeMirror-gutters {
background-color: var(--progress-bar-background) !important;
border-right: 1px solid var(--progress-bar-background) !important;
}
/* Responsive */
@media (max-width: 1200px) {
.tutorial-grid {
grid-template-columns: 1fr;
}
.playground-section {
order: -1;
}
}
/* Links */
a {
color: var(--primary-color);
text-decoration: none;
}
a:hover {
text-decoration: underline;
}
/* Lists */
ul, ol {
padding-left: 2em;
}
li {
margin-bottom: 0.5em;
}
/* Code */
code {
background-color: var(--code-bg-color);
padding: 0.2em 0.4em;
font-family: var(--mono-font-stack);
font-size: 0.9em;
}
/* Headings */
h1, h2, h3, h4, h5, h6 {
font-weight: 700;
margin-top: 1.5em;
margin-bottom: 0.8em;
}
h3 {
color: var(--primary-color);
font-size: 1.1em;
}
/* Tutorial Panel */
.tutorial-panel {
position: absolute;
top: 60px;
right: 20px;
width: 380px;
background: #1a1a1b;
border: 1px solid #2a2a2c;
border-radius: 8px;
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.5);
z-index: 1000;
transition: all 0.3s ease;
}
.tutorial-panel.hidden {
display: none;
}
.tutorial-header {
display: flex;
justify-content: space-between;
align-items: center;
padding: 16px 20px;
border-bottom: 1px solid #2a2a2c;
}
.tutorial-header h3 {
margin: 0;
color: #0fbbaa;
font-size: 18px;
}
.close-btn {
background: none;
border: none;
color: #8b8b8d;
font-size: 24px;
cursor: pointer;
padding: 0;
width: 30px;
height: 30px;
display: flex;
align-items: center;
justify-content: center;
border-radius: 4px;
transition: all 0.2s;
}
.close-btn:hover {
background: #2a2a2c;
color: #e0e0e0;
}
.tutorial-content {
padding: 20px;
}
.tutorial-content p {
margin: 0 0 16px 0;
color: #e0e0e0;
line-height: 1.6;
}
.tutorial-progress {
margin-top: 16px;
}
.tutorial-progress span {
display: block;
margin-bottom: 8px;
color: #8b8b8d;
font-size: 12px;
text-transform: uppercase;
}
.progress-bar {
height: 4px;
background: #2a2a2c;
border-radius: 2px;
overflow: hidden;
}
.progress-fill {
height: 100%;
background: #0fbbaa;
transition: width 0.3s ease;
}
.tutorial-actions {
display: flex;
gap: 12px;
padding: 0 20px 20px;
}
.tutorial-btn {
flex: 1;
padding: 10px 16px;
background: #2a2a2c;
color: #e0e0e0;
border: 1px solid #3a3a3c;
border-radius: 6px;
font-size: 14px;
cursor: pointer;
transition: all 0.2s;
}
.tutorial-btn:hover:not(:disabled) {
background: #3a3a3c;
transform: translateY(-1px);
}
.tutorial-btn:disabled {
opacity: 0.5;
cursor: not-allowed;
}
.tutorial-btn.primary {
background: #0fbbaa;
color: #070708;
border-color: #0fbbaa;
}
.tutorial-btn.primary:hover {
background: #0da89a;
border-color: #0da89a;
}
/* Tutorial Highlights */
.tutorial-highlight {
position: relative;
animation: pulse 2s infinite;
}
@keyframes pulse {
0% {
box-shadow: 0 0 0 0 rgba(15, 187, 170, 0.4);
}
50% {
box-shadow: 0 0 0 10px rgba(15, 187, 170, 0);
}
100% {
box-shadow: 0 0 0 0 rgba(15, 187, 170, 0);
}
}
.editor-card {
position: relative;
}

View File

@@ -1,21 +0,0 @@
# Demo: Login Flow with Blockly
# This script can be created visually using Blockly blocks
GO https://example.com/login
WAIT `#login-form` 5
# Check if already logged in
IF (EXISTS `.user-avatar`) THEN GO https://example.com/dashboard
# Fill login form
CLICK `#email`
TYPE "demo@example.com"
CLICK `#password`
TYPE "password123"
# Submit form
CLICK `button[type="submit"]`
WAIT `.dashboard` 10
# Success message
EVAL `console.log('Login successful!')`

View File

@@ -1,205 +0,0 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>C4A-Script Interactive Tutorial | Crawl4AI</title>
<link rel="stylesheet" href="assets/app.css">
<link rel="stylesheet" href="assets/blockly-theme.css">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/codemirror/6.65.7/codemirror.min.css">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/codemirror/6.65.7/theme/material-darker.min.css">
</head>
<body>
<!-- Tutorial Intro Modal -->
<div id="tutorial-intro" class="tutorial-intro-modal">
<div class="intro-content">
<h2>Welcome to C4A-Script Tutorial!</h2>
<p>C4A-Script is a simple language for web automation. This interactive tutorial will teach you:</p>
<ul>
<li>How to handle popups and banners</li>
<li>Form filling and navigation</li>
<li>Advanced automation techniques</li>
</ul>
<div class="intro-actions">
<button id="start-tutorial-btn" class="intro-btn primary">Start Tutorial</button>
<button id="skip-tutorial-btn" class="intro-btn">Skip</button>
</div>
</div>
</div>
<!-- Event Editor Modal -->
<div id="event-editor-overlay" class="modal-overlay hidden"></div>
<div id="event-editor-modal" class="event-editor-modal hidden">
<h4>Edit Event</h4>
<div class="editor-field">
<label>Command Type</label>
<select id="edit-command-type" disabled>
<option value="CLICK">CLICK</option>
<option value="DOUBLE_CLICK">DOUBLE_CLICK</option>
<option value="RIGHT_CLICK">RIGHT_CLICK</option>
<option value="TYPE">TYPE</option>
<option value="SET">SET</option>
<option value="SCROLL">SCROLL</option>
<option value="WAIT">WAIT</option>
</select>
</div>
<div id="edit-selector-field" class="editor-field">
<label>Selector</label>
<input type="text" id="edit-selector" placeholder=".class or #id">
</div>
<div id="edit-value-field" class="editor-field">
<label>Value</label>
<input type="text" id="edit-value" placeholder="Text or number">
</div>
<div id="edit-direction-field" class="editor-field hidden">
<label>Direction</label>
<select id="edit-direction">
<option value="UP">UP</option>
<option value="DOWN">DOWN</option>
<option value="LEFT">LEFT</option>
<option value="RIGHT">RIGHT</option>
</select>
</div>
<div class="editor-actions">
<button id="edit-cancel" class="mini-btn">Cancel</button>
<button id="edit-save" class="mini-btn primary">Save</button>
</div>
</div>
<!-- Main App Layout -->
<div class="app-container">
<!-- Left Panel: Editor -->
<div class="editor-panel">
<div class="panel-header">
<h2>C4A-Script Editor</h2>
<div class="header-actions">
<button id="tutorial-btn" class="action-btn" title="Tutorial">
<span class="icon">📚</span>
</button>
<button id="examples-btn" class="action-btn" title="Examples">
<span class="icon">📋</span>
</button>
<button id="clear-btn" class="action-btn" title="Clear">
<span class="icon">🗑</span>
</button>
<button id="run-btn" class="action-btn primary">
<span class="icon"></span>Run
</button>
<button id="record-btn" class="action-btn record">
<span class="icon"></span>Record
</button>
<button id="timeline-btn" class="action-btn timeline hidden" title="View Timeline">
<span class="icon">📊</span>
</button>
</div>
</div>
<div class="editor-container">
<div id="editor-view" class="editor-wrapper">
<textarea id="c4a-editor" placeholder="# Write your C4A script here..."></textarea>
</div>
<!-- Recording Timeline -->
<div id="timeline-view" class="recording-timeline hidden">
<div class="timeline-header">
<h3>Recording Timeline</h3>
<div class="timeline-actions">
<button id="back-to-editor" class="mini-btn">← Back</button>
<button id="select-all-events" class="mini-btn">Select All</button>
<button id="clear-events" class="mini-btn">Clear</button>
<button id="generate-script" class="mini-btn primary">Generate Script</button>
</div>
</div>
<div id="timeline-events" class="timeline-events">
<!-- Events will be added here dynamically -->
</div>
</div>
</div>
<!-- Bottom: Output Tabs -->
<div class="output-section">
<div class="tabs">
<button class="tab active" data-tab="console">Console</button>
<button class="tab" data-tab="javascript">Generated JS</button>
</div>
<div class="tab-content">
<div id="console-tab" class="tab-pane active">
<div id="console-output" class="console">
<div class="console-line">
<span class="console-prompt">$</span>
<span class="console-text">Ready to run C4A scripts...</span>
</div>
</div>
</div>
<div id="javascript-tab" class="tab-pane">
<div class="js-output-header">
<div class="js-actions">
<button id="copy-js-btn" class="mini-btn" title="Copy">
<span>📋</span>
</button>
<button id="edit-js-btn" class="mini-btn" title="Edit">
<span>✏️</span>
</button>
</div>
</div>
<pre id="js-output" class="js-output">// JavaScript will appear here...</pre>
</div>
</div>
</div>
</div>
<!-- Right Panel: Playground -->
<div class="playground-panel">
<div class="panel-header">
<h2>Playground</h2>
<div class="header-actions">
<button id="reset-playground" class="action-btn" title="Reset">
<span class="icon">🔄</span>
</button>
<button id="fullscreen-btn" class="action-btn" title="Fullscreen">
<span class="icon"></span>
</button>
</div>
</div>
<div class="playground-wrapper">
<iframe id="playground-frame" src="playground/" title="Playground"></iframe>
</div>
</div>
</div>
<!-- Tutorial Navigation Bar -->
<div id="tutorial-nav" class="tutorial-nav hidden">
<div class="tutorial-nav-content">
<div class="tutorial-left">
<div class="tutorial-step-title">
<span id="tutorial-step-info">Step 1 of 9</span>
<span id="tutorial-title">Welcome</span>
</div>
<p id="tutorial-description" class="tutorial-description">Let's start by waiting for the page to load.</p>
</div>
<div class="tutorial-right">
<div class="tutorial-controls">
<button id="tutorial-prev" class="nav-btn" disabled>← Previous</button>
<button id="tutorial-next" class="nav-btn primary">Next →</button>
</div>
<button id="tutorial-exit" class="exit-btn" title="Exit Tutorial">×</button>
</div>
</div>
<div class="tutorial-progress-bar">
<div id="tutorial-progress-fill" class="progress-fill"></div>
</div>
</div>
<!-- Scripts -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/codemirror/6.65.7/codemirror.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/codemirror/6.65.7/mode/javascript/javascript.min.js"></script>
<!-- Blockly -->
<script src="https://unpkg.com/blockly/blockly.min.js"></script>
<script src="assets/c4a-blocks.js"></script>
<script src="assets/c4a-generator.js"></script>
<script src="assets/blockly-manager.js"></script>
<script src="assets/app.js"></script>
</body>
</html>

View File

@@ -1,604 +0,0 @@
// Playground App JavaScript
class PlaygroundApp {
constructor() {
this.isLoggedIn = false;
this.currentSection = 'home';
this.productsLoaded = 0;
this.maxProducts = 100;
this.tableRowsLoaded = 10;
this.inspectorMode = false;
this.tooltip = null;
this.init();
}
init() {
this.setupCookieBanner();
this.setupNewsletterPopup();
this.setupNavigation();
this.setupAuth();
this.setupProductCatalog();
this.setupForms();
this.setupTabs();
this.setupDataTable();
this.setupInspector();
this.loadInitialData();
}
// Cookie Banner
setupCookieBanner() {
const banner = document.getElementById('cookie-banner');
const acceptBtn = banner.querySelector('.accept');
const declineBtn = banner.querySelector('.decline');
acceptBtn.addEventListener('click', () => {
banner.style.display = 'none';
console.log('✅ Cookies accepted');
});
declineBtn.addEventListener('click', () => {
banner.style.display = 'none';
console.log('❌ Cookies declined');
});
}
// Newsletter Popup
setupNewsletterPopup() {
const popup = document.getElementById('newsletter-popup');
const closeBtn = popup.querySelector('.close');
const subscribeBtn = popup.querySelector('.subscribe');
// Show popup after 3 seconds
setTimeout(() => {
popup.style.display = 'flex';
}, 3000);
closeBtn.addEventListener('click', () => {
popup.style.display = 'none';
});
subscribeBtn.addEventListener('click', () => {
const email = popup.querySelector('input').value;
if (email) {
console.log(`📧 Subscribed: ${email}`);
popup.style.display = 'none';
}
});
// Close on outside click
popup.addEventListener('click', (e) => {
if (e.target === popup) {
popup.style.display = 'none';
}
});
}
// Navigation
setupNavigation() {
const navLinks = document.querySelectorAll('.nav-link');
const sections = document.querySelectorAll('.section');
navLinks.forEach(link => {
link.addEventListener('click', (e) => {
e.preventDefault();
const targetId = link.getAttribute('href').substring(1);
// Update active states
navLinks.forEach(l => l.classList.remove('active'));
link.classList.add('active');
// Show target section
sections.forEach(s => s.classList.remove('active'));
const targetSection = document.getElementById(targetId);
if (targetSection) {
targetSection.classList.add('active');
this.currentSection = targetId;
// Load content for specific sections
this.loadSectionContent(targetId);
}
});
});
// Start tutorial button
const startBtn = document.getElementById('start-tutorial');
if (startBtn) {
startBtn.addEventListener('click', () => {
console.log('🚀 Tutorial started!');
alert('Tutorial started! Check the console for progress.');
});
}
}
// Authentication
setupAuth() {
const loginBtn = document.getElementById('login-btn');
const logoutBtn = document.getElementById('logout-btn');
const loginModal = document.getElementById('login-modal');
const loginForm = document.getElementById('login-form');
const closeBtn = loginModal.querySelector('.close');
loginBtn.addEventListener('click', () => {
loginModal.style.display = 'flex';
});
closeBtn.addEventListener('click', () => {
loginModal.style.display = 'none';
});
loginForm.addEventListener('submit', (e) => {
e.preventDefault();
const email = document.getElementById('email').value;
const password = document.getElementById('password').value;
const rememberMe = document.getElementById('remember-me').checked;
const messageEl = document.getElementById('login-message');
// Simple validation
if (email === 'demo@example.com' && password === 'demo123') {
this.isLoggedIn = true;
messageEl.textContent = '✅ Login successful!';
messageEl.className = 'form-message success';
setTimeout(() => {
loginModal.style.display = 'none';
document.getElementById('login-btn').style.display = 'none';
document.getElementById('user-info').style.display = 'flex';
document.getElementById('username-display').textContent = 'Demo User';
console.log(`✅ Logged in${rememberMe ? ' (remembered)' : ''}`);
}, 1000);
} else {
messageEl.textContent = '❌ Invalid credentials. Try demo@example.com / demo123';
messageEl.className = 'form-message error';
}
});
logoutBtn.addEventListener('click', () => {
this.isLoggedIn = false;
document.getElementById('login-btn').style.display = 'block';
document.getElementById('user-info').style.display = 'none';
console.log('👋 Logged out');
});
// Close modal on outside click
loginModal.addEventListener('click', (e) => {
if (e.target === loginModal) {
loginModal.style.display = 'none';
}
});
}
// Product Catalog
setupProductCatalog() {
// View toggle
const infiniteBtn = document.getElementById('infinite-scroll-btn');
const paginationBtn = document.getElementById('pagination-btn');
const infiniteView = document.getElementById('infinite-scroll-view');
const paginationView = document.getElementById('pagination-view');
infiniteBtn.addEventListener('click', () => {
infiniteBtn.classList.add('active');
paginationBtn.classList.remove('active');
infiniteView.style.display = 'block';
paginationView.style.display = 'none';
this.setupInfiniteScroll();
});
paginationBtn.addEventListener('click', () => {
paginationBtn.classList.add('active');
infiniteBtn.classList.remove('active');
paginationView.style.display = 'block';
infiniteView.style.display = 'none';
});
// Load more button
const loadMoreBtn = paginationView.querySelector('.load-more');
loadMoreBtn.addEventListener('click', () => {
this.loadMoreProducts();
});
// Collapsible filters
const collapsibles = document.querySelectorAll('.collapsible');
collapsibles.forEach(header => {
header.addEventListener('click', () => {
const content = header.nextElementSibling;
const toggle = header.querySelector('.toggle');
content.style.display = content.style.display === 'none' ? 'block' : 'none';
toggle.textContent = content.style.display === 'none' ? '▶' : '▼';
});
});
}
setupInfiniteScroll() {
const container = document.querySelector('.products-container');
const loadingIndicator = document.getElementById('loading-indicator');
container.addEventListener('scroll', () => {
if (container.scrollTop + container.clientHeight >= container.scrollHeight - 100) {
if (this.productsLoaded < this.maxProducts) {
loadingIndicator.style.display = 'block';
setTimeout(() => {
this.loadMoreProducts();
loadingIndicator.style.display = 'none';
}, 1000);
}
}
});
}
loadMoreProducts() {
const grid = document.getElementById('product-grid');
const batch = 10;
for (let i = 0; i < batch && this.productsLoaded < this.maxProducts; i++) {
const product = this.createProductCard(this.productsLoaded + 1);
grid.appendChild(product);
this.productsLoaded++;
}
console.log(`📦 Loaded ${batch} more products. Total: ${this.productsLoaded}`);
}
createProductCard(id) {
const card = document.createElement('div');
card.className = 'product-card';
card.innerHTML = `
<div class="product-image">📦</div>
<div class="product-name">Product ${id}</div>
<div class="product-price">$${(Math.random() * 100 + 10).toFixed(2)}</div>
<button class="btn btn-sm">Quick View</button>
`;
// Quick view functionality
const quickViewBtn = card.querySelector('button');
quickViewBtn.addEventListener('click', () => {
alert(`Quick view for Product ${id}`);
});
return card;
}
// Forms
setupForms() {
// Contact Form
const contactForm = document.getElementById('contact-form');
const subjectSelect = document.getElementById('contact-subject');
const departmentGroup = document.getElementById('department-group');
const departmentSelect = document.getElementById('department');
subjectSelect.addEventListener('change', () => {
if (subjectSelect.value === 'support') {
departmentGroup.style.display = 'block';
departmentSelect.innerHTML = `
<option value="">Select department</option>
<option value="technical">Technical Support</option>
<option value="billing">Billing Support</option>
<option value="general">General Support</option>
`;
} else {
departmentGroup.style.display = 'none';
}
});
contactForm.addEventListener('submit', (e) => {
e.preventDefault();
const messageDisplay = document.getElementById('contact-message-display');
messageDisplay.textContent = '✅ Message sent successfully!';
messageDisplay.className = 'form-message success';
console.log('📧 Contact form submitted');
});
// Multi-step Form
const surveyForm = document.getElementById('survey-form');
const steps = surveyForm.querySelectorAll('.form-step');
const progressFill = document.getElementById('progress-fill');
let currentStep = 1;
surveyForm.addEventListener('click', (e) => {
if (e.target.classList.contains('next-step')) {
if (currentStep < 3) {
steps[currentStep - 1].style.display = 'none';
currentStep++;
steps[currentStep - 1].style.display = 'block';
progressFill.style.width = `${(currentStep / 3) * 100}%`;
}
} else if (e.target.classList.contains('prev-step')) {
if (currentStep > 1) {
steps[currentStep - 1].style.display = 'none';
currentStep--;
steps[currentStep - 1].style.display = 'block';
progressFill.style.width = `${(currentStep / 3) * 100}%`;
}
}
});
surveyForm.addEventListener('submit', (e) => {
e.preventDefault();
document.getElementById('survey-success').style.display = 'block';
console.log('📋 Survey submitted successfully!');
});
}
// Tabs
setupTabs() {
const tabBtns = document.querySelectorAll('.tab-btn');
const tabPanes = document.querySelectorAll('.tab-pane');
tabBtns.forEach(btn => {
btn.addEventListener('click', () => {
const targetTab = btn.getAttribute('data-tab');
// Update active states
tabBtns.forEach(b => b.classList.remove('active'));
btn.classList.add('active');
// Show target pane
tabPanes.forEach(pane => {
pane.style.display = pane.id === targetTab ? 'block' : 'none';
});
});
});
// Show more functionality
const showMoreBtn = document.querySelector('.show-more');
const hiddenText = document.querySelector('.hidden-text');
if (showMoreBtn) {
showMoreBtn.addEventListener('click', () => {
if (hiddenText.style.display === 'none') {
hiddenText.style.display = 'block';
showMoreBtn.textContent = 'Show Less';
} else {
hiddenText.style.display = 'none';
showMoreBtn.textContent = 'Show More';
}
});
}
// Load comments
const loadCommentsBtn = document.querySelector('.load-comments');
const commentsSection = document.querySelector('.comments-section');
if (loadCommentsBtn) {
loadCommentsBtn.addEventListener('click', () => {
commentsSection.style.display = 'block';
commentsSection.innerHTML = `
<div class="comment">
<div class="comment-author">John Doe</div>
<div class="comment-text">Great product! Highly recommended.</div>
</div>
<div class="comment">
<div class="comment-author">Jane Smith</div>
<div class="comment-text">Excellent quality and fast shipping.</div>
</div>
`;
loadCommentsBtn.style.display = 'none';
console.log('💬 Comments loaded');
});
}
}
// Data Table
setupDataTable() {
const loadMoreBtn = document.querySelector('.load-more-rows');
const searchInput = document.querySelector('.search-input');
const exportBtn = document.getElementById('export-btn');
const sortableHeaders = document.querySelectorAll('.sortable');
// Load more rows
loadMoreBtn.addEventListener('click', () => {
this.loadMoreTableRows();
});
// Search functionality
searchInput.addEventListener('input', (e) => {
const searchTerm = e.target.value.toLowerCase();
const rows = document.querySelectorAll('#table-body tr');
rows.forEach(row => {
const text = row.textContent.toLowerCase();
row.style.display = text.includes(searchTerm) ? '' : 'none';
});
});
// Export functionality
exportBtn.addEventListener('click', () => {
console.log('📊 Exporting table data...');
alert('Table data exported! (Check console)');
});
// Sorting
sortableHeaders.forEach(header => {
header.addEventListener('click', () => {
console.log(`🔄 Sorting by ${header.getAttribute('data-sort')}`);
});
});
}
loadMoreTableRows() {
const tbody = document.getElementById('table-body');
const batch = 10;
for (let i = 0; i < batch; i++) {
const row = document.createElement('tr');
const id = this.tableRowsLoaded + i + 1;
row.innerHTML = `
<td>User ${id}</td>
<td>user${id}@example.com</td>
<td>${new Date().toLocaleDateString()}</td>
<td><button class="btn btn-sm">Edit</button></td>
`;
tbody.appendChild(row);
}
this.tableRowsLoaded += batch;
console.log(`📄 Loaded ${batch} more rows. Total: ${this.tableRowsLoaded}`);
}
// Load initial data
loadInitialData() {
// Load initial products
this.loadMoreProducts();
// Load initial table rows
this.loadMoreTableRows();
}
// Load content when navigating to sections
loadSectionContent(sectionId) {
switch(sectionId) {
case 'catalog':
// Ensure products are loaded in catalog
if (this.productsLoaded === 0) {
this.loadMoreProducts();
}
break;
case 'data-tables':
// Ensure table rows are loaded
if (this.tableRowsLoaded === 0) {
this.loadMoreTableRows();
}
break;
case 'forms':
// Forms are already set up
break;
case 'tabs':
// Tabs content is static
break;
}
}
// Inspector Mode
setupInspector() {
const inspectorBtn = document.getElementById('inspector-btn');
// Create tooltip element
this.tooltip = document.createElement('div');
this.tooltip.className = 'inspector-tooltip';
this.tooltip.style.cssText = `
position: fixed;
background: rgba(0, 0, 0, 0.9);
color: white;
padding: 8px 12px;
border-radius: 4px;
font-size: 12px;
font-family: monospace;
pointer-events: none;
z-index: 10000;
display: none;
max-width: 300px;
`;
document.body.appendChild(this.tooltip);
inspectorBtn.addEventListener('click', () => {
this.toggleInspector();
});
// Add mouse event listeners
document.addEventListener('mousemove', this.handleMouseMove.bind(this));
document.addEventListener('mouseout', this.handleMouseOut.bind(this));
}
toggleInspector() {
this.inspectorMode = !this.inspectorMode;
const inspectorBtn = document.getElementById('inspector-btn');
if (this.inspectorMode) {
inspectorBtn.classList.add('active');
inspectorBtn.style.background = '#0fbbaa';
document.body.style.cursor = 'crosshair';
} else {
inspectorBtn.classList.remove('active');
inspectorBtn.style.background = '';
document.body.style.cursor = '';
this.tooltip.style.display = 'none';
this.removeHighlight();
}
}
handleMouseMove(e) {
if (!this.inspectorMode) return;
const element = e.target;
if (element === this.tooltip) return;
// Highlight element
this.highlightElement(element);
// Show tooltip with element info
const info = this.getElementInfo(element);
this.tooltip.innerHTML = info;
this.tooltip.style.display = 'block';
// Position tooltip
const x = e.clientX + 15;
const y = e.clientY + 15;
// Adjust position if tooltip would go off screen
const rect = this.tooltip.getBoundingClientRect();
const adjustedX = x + rect.width > window.innerWidth ? x - rect.width - 30 : x;
const adjustedY = y + rect.height > window.innerHeight ? y - rect.height - 30 : y;
this.tooltip.style.left = adjustedX + 'px';
this.tooltip.style.top = adjustedY + 'px';
}
handleMouseOut(e) {
if (!this.inspectorMode) return;
if (e.target === document.body) {
this.removeHighlight();
this.tooltip.style.display = 'none';
}
}
highlightElement(element) {
this.removeHighlight();
element.style.outline = '2px solid #0fbbaa';
element.style.outlineOffset = '1px';
element.setAttribute('data-inspector-highlighted', 'true');
}
removeHighlight() {
const highlighted = document.querySelector('[data-inspector-highlighted]');
if (highlighted) {
highlighted.style.outline = '';
highlighted.style.outlineOffset = '';
highlighted.removeAttribute('data-inspector-highlighted');
}
}
getElementInfo(element) {
const tagName = element.tagName.toLowerCase();
const id = element.id ? `#${element.id}` : '';
const classes = element.className ?
`.${element.className.split(' ').filter(c => c).join('.')}` : '';
let selector = tagName;
if (id) {
selector = id;
} else if (classes) {
selector = `${tagName}${classes}`;
}
// Build info HTML
let info = `<strong>${selector}</strong>`;
// Add additional attributes
const attrs = [];
if (element.name) attrs.push(`name="${element.name}"`);
if (element.type) attrs.push(`type="${element.type}"`);
if (element.href) attrs.push(`href="${element.href}"`);
if (element.value && element.tagName === 'INPUT') attrs.push(`value="${element.value}"`);
if (attrs.length > 0) {
info += `<br><span style="color: #888;">${attrs.join(' ')}</span>`;
}
return info;
}
}
// Initialize app when DOM is ready
document.addEventListener('DOMContentLoaded', () => {
window.playgroundApp = new PlaygroundApp();
console.log('🎮 Playground app initialized!');
});

View File

@@ -1,328 +0,0 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>C4A-Script Playground</title>
<link rel="stylesheet" href="styles.css">
</head>
<body>
<!-- Cookie Banner -->
<div class="cookie-banner" id="cookie-banner">
<div class="cookie-content">
<p>🍪 We use cookies to enhance your experience. By continuing, you agree to our cookie policy.</p>
<div class="cookie-actions">
<button class="btn accept">Accept All</button>
<button class="btn btn-secondary decline">Decline</button>
</div>
</div>
</div>
<!-- Newsletter Popup (appears after 3 seconds) -->
<div class="modal" id="newsletter-popup" style="display: none;">
<div class="modal-content">
<span class="close">&times;</span>
<h2>📬 Subscribe to Our Newsletter</h2>
<p>Get the latest updates on web automation!</p>
<input type="email" placeholder="Enter your email" class="input">
<button class="btn subscribe">Subscribe</button>
</div>
</div>
<!-- Header -->
<header class="site-header">
<nav class="nav-menu">
<a href="#home" class="nav-link active">Home</a>
<a href="#catalog" class="nav-link" id="catalog-link">Products</a>
<a href="#forms" class="nav-link">Forms</a>
<a href="#data-tables" class="nav-link">Data Tables</a>
<div class="dropdown">
<a href="#" class="nav-link dropdown-toggle">More ▼</a>
<div class="dropdown-content">
<a href="#tabs">Tabs Demo</a>
<a href="#accordion">FAQ</a>
<a href="#gallery">Gallery</a>
</div>
</div>
</nav>
<div class="auth-section">
<button class="btn btn-sm" id="inspector-btn" title="Toggle Inspector">🔍</button>
<button class="btn btn-sm" id="login-btn">Login</button>
<div class="user-info" id="user-info" style="display: none;">
<span class="user-avatar">👤</span>
<span class="welcome-message">Welcome, <span id="username-display">User</span>!</span>
<button class="btn btn-sm btn-secondary" id="logout-btn">Logout</button>
</div>
</div>
</header>
<!-- Main Content -->
<main class="main-content">
<!-- Home Section -->
<section id="home" class="section active">
<h1>Welcome to C4A-Script Playground</h1>
<p>This is an interactive demo for testing C4A-Script commands. Each section contains different challenges for web automation.</p>
<button class="btn btn-primary" id="start-tutorial">Start Tutorial</button>
<div class="feature-grid">
<div class="feature-card">
<h3>🔐 Authentication</h3>
<p>Test login forms and user sessions</p>
</div>
<div class="feature-card">
<h3>📜 Dynamic Content</h3>
<p>Infinite scroll and pagination</p>
</div>
<div class="feature-card">
<h3>📝 Forms</h3>
<p>Complex form interactions</p>
</div>
<div class="feature-card">
<h3>📊 Data Tables</h3>
<p>Sortable and filterable data</p>
</div>
</div>
</section>
<!-- Login Modal -->
<div class="modal" id="login-modal" style="display: none;">
<div class="modal-content login-form">
<span class="close">&times;</span>
<h2>Login</h2>
<form id="login-form">
<div class="form-group">
<label>Email</label>
<input type="email" id="email" class="input" placeholder="demo@example.com">
</div>
<div class="form-group">
<label>Password</label>
<input type="password" id="password" class="input" placeholder="demo123">
</div>
<div class="form-group">
<label class="checkbox-label">
<input type="checkbox" id="remember-me">
Remember me
</label>
</div>
<button type="submit" class="btn btn-primary">Login</button>
<div class="form-message" id="login-message"></div>
</form>
</div>
</div>
<!-- Product Catalog Section -->
<section id="catalog" class="section">
<h1>Product Catalog</h1>
<div class="view-toggle">
<button class="btn btn-sm active" id="infinite-scroll-btn">Infinite Scroll</button>
<button class="btn btn-sm" id="pagination-btn">Pagination</button>
</div>
<!-- Filters Sidebar -->
<div class="catalog-layout">
<aside class="filters-sidebar">
<h3>Filters</h3>
<div class="filter-group">
<h4 class="collapsible">Category <span class="toggle"></span></h4>
<div class="filter-content">
<label><input type="checkbox"> Electronics</label>
<label><input type="checkbox"> Clothing</label>
<label><input type="checkbox"> Books</label>
</div>
</div>
<div class="filter-group">
<h4 class="collapsible">Price Range <span class="toggle"></span></h4>
<div class="filter-content">
<input type="range" min="0" max="1000" value="500">
<span>$0 - $500</span>
</div>
</div>
</aside>
<!-- Products Grid -->
<div class="products-container">
<div class="product-grid" id="product-grid">
<!-- Products will be loaded here -->
</div>
<!-- Infinite Scroll View -->
<div id="infinite-scroll-view" class="view-mode">
<div class="loading-indicator" id="loading-indicator" style="display: none;">
<div class="spinner"></div>
<p>Loading more products...</p>
</div>
</div>
<!-- Pagination View -->
<div id="pagination-view" class="view-mode" style="display: none;">
<button class="btn load-more">Load More</button>
<div class="pagination">
<button class="page-btn">1</button>
<button class="page-btn">2</button>
<button class="page-btn">3</button>
</div>
</div>
</div>
</div>
</section>
<!-- Forms Section -->
<section id="forms" class="section">
<h1>Form Examples</h1>
<!-- Contact Form -->
<div class="form-card">
<h2>Contact Form</h2>
<form id="contact-form">
<div class="form-group">
<label>Name</label>
<input type="text" class="input" id="contact-name">
</div>
<div class="form-group">
<label>Email</label>
<input type="email" class="input" id="contact-email">
</div>
<div class="form-group">
<label>Subject</label>
<select class="input" id="contact-subject">
<option value="">Select a subject</option>
<option value="support">Support</option>
<option value="sales">Sales</option>
<option value="feedback">Feedback</option>
</select>
</div>
<div class="form-group" id="department-group" style="display: none;">
<label>Department</label>
<select class="input" id="department">
<option value="">Select department</option>
</select>
</div>
<div class="form-group">
<label>Message</label>
<textarea class="input" id="contact-message" rows="4"></textarea>
</div>
<button type="submit" class="btn btn-primary">Send Message</button>
<div class="form-message" id="contact-message-display"></div>
</form>
</div>
<!-- Multi-step Form -->
<div class="form-card">
<h2>Multi-step Survey</h2>
<div class="progress-bar">
<div class="progress-fill" id="progress-fill" style="width: 33%"></div>
</div>
<form id="survey-form">
<!-- Step 1 -->
<div class="form-step active" data-step="1">
<h3>Step 1: Basic Information</h3>
<div class="form-group">
<label>Full Name</label>
<input type="text" class="input" id="full-name">
</div>
<div class="form-group">
<label>Email</label>
<input type="email" class="input" id="survey-email">
</div>
<button type="button" class="btn next-step">Next</button>
</div>
<!-- Step 2 -->
<div class="form-step" data-step="2" style="display: none;">
<h3>Step 2: Preferences</h3>
<div class="form-group">
<label>Interests (select multiple)</label>
<select multiple class="input" id="interests">
<option value="tech">Technology</option>
<option value="sports">Sports</option>
<option value="music">Music</option>
<option value="travel">Travel</option>
</select>
</div>
<button type="button" class="btn prev-step">Previous</button>
<button type="button" class="btn next-step">Next</button>
</div>
<!-- Step 3 -->
<div class="form-step" data-step="3" style="display: none;">
<h3>Step 3: Confirmation</h3>
<p>Please review your information and submit.</p>
<button type="button" class="btn prev-step">Previous</button>
<button type="submit" class="btn btn-primary" id="submit-survey">Submit Survey</button>
</div>
</form>
<div class="form-message success-message" id="survey-success" style="display: none;">
✅ Survey submitted successfully!
</div>
</div>
</section>
<!-- Tabs Section -->
<section id="tabs" class="section">
<h1>Tabs Demo</h1>
<div class="tabs-container">
<div class="tabs-header">
<button class="tab-btn active" data-tab="description">Description</button>
<button class="tab-btn" data-tab="reviews">Reviews</button>
<button class="tab-btn" data-tab="specs">Specifications</button>
</div>
<div class="tabs-content">
<div class="tab-pane active" id="description">
<h3>Product Description</h3>
<p>This is a detailed description of the product...</p>
<div class="expandable-text">
<p class="text-preview">Lorem ipsum dolor sit amet, consectetur adipiscing elit...</p>
<button class="btn btn-sm show-more">Show More</button>
<div class="hidden-text" style="display: none;">
<p>This is the hidden text that appears when you click "Show More". It contains additional details about the product that weren't visible initially.</p>
</div>
</div>
</div>
<div class="tab-pane" id="reviews" style="display: none;">
<h3>Customer Reviews</h3>
<button class="btn btn-sm load-comments">Load Comments</button>
<div class="comments-section" style="display: none;">
<!-- Comments will be loaded here -->
</div>
</div>
<div class="tab-pane" id="specs" style="display: none;">
<h3>Technical Specifications</h3>
<table class="specs-table">
<tr><td>Model</td><td>XYZ-2000</td></tr>
<tr><td>Weight</td><td>2.5 kg</td></tr>
<tr><td>Dimensions</td><td>30 x 20 x 10 cm</td></tr>
</table>
</div>
</div>
</div>
</section>
<!-- Data Tables Section -->
<section id="data-tables" class="section">
<h1>Data Tables</h1>
<div class="table-controls">
<input type="text" class="input search-input" placeholder="Search...">
<button class="btn btn-sm" id="export-btn">Export</button>
</div>
<table class="data-table" id="data-table">
<thead>
<tr>
<th class="sortable" data-sort="name">Name ↕</th>
<th class="sortable" data-sort="email">Email ↕</th>
<th class="sortable" data-sort="date">Date ↕</th>
<th>Actions</th>
</tr>
</thead>
<tbody id="table-body">
<!-- Table rows will be loaded here -->
</tbody>
</table>
<button class="btn load-more-rows">Load More Rows</button>
</section>
</main>
<script src="app.js"></script>
</body>
</html>

View File

@@ -1,627 +0,0 @@
/* Playground Styles - Modern Web App Theme */
:root {
--primary-color: #0fbbaa;
--secondary-color: #3f3f44;
--background-color: #ffffff;
--text-color: #333333;
--border-color: #e0e0e0;
--error-color: #ff3c74;
--success-color: #0fbbaa;
--warning-color: #ffa500;
}
* {
box-sizing: border-box;
}
body {
margin: 0;
padding: 0;
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
font-size: 16px;
line-height: 1.6;
color: var(--text-color);
background-color: var(--background-color);
}
/* Cookie Banner */
.cookie-banner {
position: fixed;
bottom: 0;
left: 0;
right: 0;
background-color: #2c3e50;
color: white;
padding: 1rem;
z-index: 1000;
box-shadow: 0 -2px 10px rgba(0,0,0,0.1);
}
.cookie-content {
max-width: 1200px;
margin: 0 auto;
display: flex;
align-items: center;
justify-content: space-between;
flex-wrap: wrap;
gap: 1rem;
}
.cookie-actions {
display: flex;
gap: 0.5rem;
}
/* Header */
.site-header {
background-color: #fff;
border-bottom: 1px solid var(--border-color);
padding: 1rem 2rem;
position: sticky;
top: 0;
z-index: 100;
display: flex;
justify-content: space-between;
align-items: center;
}
.nav-menu {
display: flex;
gap: 2rem;
align-items: center;
}
.nav-link {
text-decoration: none;
color: var(--text-color);
font-weight: 500;
transition: color 0.2s;
}
.nav-link:hover,
.nav-link.active {
color: var(--primary-color);
}
/* Dropdown */
.dropdown {
position: relative;
}
.dropdown-content {
display: none;
position: absolute;
background-color: white;
min-width: 160px;
box-shadow: 0 8px 16px rgba(0,0,0,0.1);
z-index: 1;
border-radius: 4px;
top: 100%;
margin-top: 0.5rem;
}
.dropdown:hover .dropdown-content {
display: block;
}
.dropdown-content a {
color: var(--text-color);
padding: 0.75rem 1rem;
text-decoration: none;
display: block;
}
.dropdown-content a:hover {
background-color: #f5f5f5;
}
/* Auth Section */
.auth-section {
display: flex;
align-items: center;
gap: 1rem;
}
.user-info {
display: flex;
align-items: center;
gap: 0.5rem;
}
.user-avatar {
font-size: 1.5rem;
}
/* Main Content */
.main-content {
padding: 2rem;
max-width: 1200px;
margin: 0 auto;
}
.section {
display: none;
}
.section.active {
display: block;
}
/* Buttons */
.btn {
background-color: var(--primary-color);
color: white;
border: none;
padding: 0.5rem 1rem;
border-radius: 4px;
cursor: pointer;
font-size: 1rem;
font-weight: 500;
transition: all 0.2s;
}
.btn:hover {
background-color: #0aa599;
transform: translateY(-1px);
}
.btn-sm {
padding: 0.25rem 0.75rem;
font-size: 0.875rem;
}
.btn-secondary {
background-color: var(--secondary-color);
}
.btn-secondary:hover {
background-color: #333;
}
.btn-primary {
background-color: var(--primary-color);
}
/* Feature Grid */
.feature-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
gap: 1.5rem;
margin-top: 2rem;
}
.feature-card {
background-color: #f8f9fa;
padding: 1.5rem;
border-radius: 8px;
text-align: center;
transition: transform 0.2s;
}
.feature-card:hover {
transform: translateY(-4px);
box-shadow: 0 4px 12px rgba(0,0,0,0.1);
}
.feature-card h3 {
margin-top: 0;
}
/* Modal */
.modal {
position: fixed;
z-index: 1000;
left: 0;
top: 0;
width: 100%;
height: 100%;
background-color: rgba(0,0,0,0.5);
display: flex;
align-items: center;
justify-content: center;
}
.modal-content {
background-color: white;
padding: 2rem;
border-radius: 8px;
max-width: 500px;
width: 90%;
position: relative;
animation: modalFadeIn 0.3s;
}
@keyframes modalFadeIn {
from { opacity: 0; transform: translateY(-20px); }
to { opacity: 1; transform: translateY(0); }
}
.close {
position: absolute;
right: 1rem;
top: 1rem;
font-size: 1.5rem;
cursor: pointer;
color: #999;
}
.close:hover {
color: #333;
}
/* Forms */
.form-group {
margin-bottom: 1rem;
}
.form-group label {
display: block;
margin-bottom: 0.5rem;
font-weight: 500;
}
.input {
width: 100%;
padding: 0.5rem;
border: 1px solid var(--border-color);
border-radius: 4px;
font-size: 1rem;
}
.input:focus {
outline: none;
border-color: var(--primary-color);
}
.checkbox-label {
display: flex;
align-items: center;
gap: 0.5rem;
}
.form-message {
margin-top: 1rem;
padding: 0.75rem;
border-radius: 4px;
display: none;
}
.form-message.error {
background-color: #ffe6e6;
color: var(--error-color);
display: block;
}
.form-message.success {
background-color: #e6fff6;
color: var(--success-color);
display: block;
}
/* Product Catalog */
.view-toggle {
margin-bottom: 1rem;
}
.catalog-layout {
display: grid;
grid-template-columns: 250px 1fr;
gap: 2rem;
}
.filters-sidebar {
background-color: #f8f9fa;
padding: 1rem;
border-radius: 8px;
}
.filter-group {
margin-bottom: 1.5rem;
}
.collapsible {
cursor: pointer;
display: flex;
justify-content: space-between;
align-items: center;
}
.filter-content {
margin-top: 0.5rem;
}
.filter-content label {
display: block;
margin-bottom: 0.5rem;
}
/* Product Grid */
.product-grid {
display: grid;
grid-template-columns: repeat(auto-fill, minmax(200px, 1fr));
gap: 1.5rem;
}
.product-card {
background-color: white;
border: 1px solid var(--border-color);
border-radius: 8px;
padding: 1rem;
text-align: center;
transition: transform 0.2s;
}
.product-card:hover {
transform: translateY(-4px);
box-shadow: 0 4px 12px rgba(0,0,0,0.1);
}
.product-image {
width: 100%;
height: 150px;
background-color: #f0f0f0;
margin-bottom: 1rem;
display: flex;
align-items: center;
justify-content: center;
font-size: 3rem;
}
.product-name {
font-weight: 600;
margin-bottom: 0.5rem;
}
.product-price {
color: var(--primary-color);
font-size: 1.2rem;
font-weight: 700;
}
/* Loading Indicator */
.loading-indicator {
text-align: center;
padding: 2rem;
}
.spinner {
border: 3px solid #f3f3f3;
border-top: 3px solid var(--primary-color);
border-radius: 50%;
width: 40px;
height: 40px;
animation: spin 1s linear infinite;
margin: 0 auto;
}
@keyframes spin {
0% { transform: rotate(0deg); }
100% { transform: rotate(360deg); }
}
/* Pagination */
.pagination {
display: flex;
gap: 0.5rem;
justify-content: center;
margin-top: 2rem;
}
.page-btn {
padding: 0.5rem 1rem;
border: 1px solid var(--border-color);
background-color: white;
cursor: pointer;
border-radius: 4px;
}
.page-btn:hover,
.page-btn.active {
background-color: var(--primary-color);
color: white;
}
/* Multi-step Form */
.progress-bar {
width: 100%;
height: 8px;
background-color: #e0e0e0;
border-radius: 4px;
margin-bottom: 2rem;
}
.progress-fill {
height: 100%;
background-color: var(--primary-color);
border-radius: 4px;
transition: width 0.3s;
}
.form-step {
display: none;
}
.form-step.active {
display: block;
}
/* Tabs */
.tabs-container {
margin-top: 2rem;
}
.tabs-header {
display: flex;
border-bottom: 2px solid var(--border-color);
}
.tab-btn {
background: none;
border: none;
padding: 1rem 2rem;
cursor: pointer;
font-size: 1rem;
font-weight: 500;
color: var(--text-color);
position: relative;
}
.tab-btn:hover {
color: var(--primary-color);
}
.tab-btn.active {
color: var(--primary-color);
}
.tab-btn.active::after {
content: '';
position: absolute;
bottom: -2px;
left: 0;
right: 0;
height: 2px;
background-color: var(--primary-color);
}
.tabs-content {
padding: 2rem 0;
}
.tab-pane {
display: none;
}
.tab-pane.active {
display: block;
}
/* Expandable Text */
.expandable-text {
margin-top: 1rem;
}
.text-preview {
margin-bottom: 0.5rem;
}
.show-more {
margin-top: 0.5rem;
}
/* Comments Section */
.comments-section {
margin-top: 1rem;
}
.comment {
background-color: #f8f9fa;
padding: 1rem;
border-radius: 4px;
margin-bottom: 1rem;
}
.comment-author {
font-weight: 600;
margin-bottom: 0.5rem;
}
/* Data Table */
.table-controls {
display: flex;
gap: 1rem;
margin-bottom: 1rem;
}
.search-input {
flex: 1;
max-width: 300px;
}
.data-table {
width: 100%;
border-collapse: collapse;
background-color: white;
}
.data-table th,
.data-table td {
padding: 0.75rem;
text-align: left;
border-bottom: 1px solid var(--border-color);
}
.data-table th {
background-color: #f8f9fa;
font-weight: 600;
}
.sortable {
cursor: pointer;
}
.sortable:hover {
color: var(--primary-color);
}
/* Form Cards */
.form-card {
background-color: white;
border: 1px solid var(--border-color);
border-radius: 8px;
padding: 2rem;
margin-bottom: 2rem;
}
.form-card h2 {
margin-top: 0;
}
/* Success Message */
.success-message {
background-color: #e6fff6;
color: var(--success-color);
padding: 1rem;
border-radius: 4px;
text-align: center;
font-weight: 500;
}
/* Load More Button */
.load-more,
.load-more-rows {
display: block;
margin: 2rem auto;
}
/* Responsive */
@media (max-width: 768px) {
.catalog-layout {
grid-template-columns: 1fr;
}
.feature-grid {
grid-template-columns: 1fr;
}
.nav-menu {
flex-wrap: wrap;
gap: 1rem;
}
.cookie-content {
flex-direction: column;
text-align: center;
}
}
/* Inspector Mode */
#inspector-btn.active {
background: var(--primary-color) !important;
color: var(--bg-primary) !important;
}
.inspector-tooltip {
box-shadow: 0 2px 8px rgba(0, 0, 0, 0.3);
border: 1px solid rgba(255, 255, 255, 0.1);
}

View File

@@ -1,2 +0,0 @@
flask>=2.3.0
flask-cors>=4.0.0

View File

@@ -1,18 +0,0 @@
# Basic Page Interaction
# This script demonstrates basic C4A commands
# Navigate to the playground
GO http://127.0.0.1:8080/playground/
# Wait for page to load
WAIT `body` 2
# Handle cookie banner if present
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
# Close newsletter popup if it appears
WAIT 3
IF (EXISTS `.newsletter-popup`) THEN CLICK `.close`
# Click the start tutorial button
CLICK `#start-tutorial`

View File

@@ -1,27 +0,0 @@
# Complete Login Flow
# Demonstrates form interaction and authentication
# Click login button
CLICK `#login-btn`
# Wait for login modal
WAIT `.login-form` 3
# Fill in credentials
CLICK `#email`
TYPE "demo@example.com"
CLICK `#password`
TYPE "demo123"
# Check remember me
IF (EXISTS `#remember-me`) THEN CLICK `#remember-me`
# Submit form
CLICK `button[type="submit"]`
# Wait for success
WAIT `.welcome-message` 5
# Verify login succeeded
IF (EXISTS `.user-info`) THEN EVAL `console.log('✅ Login successful!')`

View File

@@ -1,32 +0,0 @@
# Infinite Scroll Product Loading
# Load all products using scroll automation
# Navigate to catalog
CLICK `#catalog-link`
WAIT `.product-grid` 3
# Switch to infinite scroll mode
CLICK `#infinite-scroll-btn`
# Define scroll procedure
PROC load_more_products
# Get current product count
EVAL `window.initialCount = document.querySelectorAll('.product-card').length`
# Scroll down
SCROLL DOWN 1000
WAIT 2
# Check if more products loaded
EVAL `
const newCount = document.querySelectorAll('.product-card').length;
console.log('Products loaded: ' + newCount);
window.moreLoaded = newCount > window.initialCount;
`
ENDPROC
# Load products until no more
REPEAT (load_more_products, `window.moreLoaded !== false`)
# Final count
EVAL `console.log('✅ Total products: ' + document.querySelectorAll('.product-card').length)`

View File

@@ -1,41 +0,0 @@
# Multi-step Form Wizard
# Complete a complex form with multiple steps
# Navigate to forms section
CLICK `a[href="#forms"]`
WAIT `#survey-form` 2
# Step 1: Basic Information
CLICK `#full-name`
TYPE "John Doe"
CLICK `#survey-email`
TYPE "john.doe@example.com"
# Go to next step
CLICK `.next-step`
WAIT 1
# Step 2: Select Interests
# Select multiple options
CLICK `#interests`
CLICK `option[value="tech"]`
CLICK `option[value="music"]`
CLICK `option[value="travel"]`
# Continue to final step
CLICK `.next-step`
WAIT 1
# Step 3: Review and Submit
# Verify we're on the last step
IF (EXISTS `#submit-survey`) THEN EVAL `console.log('📋 On final step')`
# Submit the form
CLICK `#submit-survey`
# Wait for success message
WAIT `.success-message` 5
# Verify submission
IF (EXISTS `.success-message`) THEN EVAL `console.log('✅ Survey submitted successfully!')`

View File

@@ -1,82 +0,0 @@
# Complete E-commerce Workflow
# Login, browse products, and interact with various elements
# Define reusable procedures
PROC handle_popups
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
IF (EXISTS `.newsletter-popup`) THEN CLICK `.close`
ENDPROC
PROC login_user
CLICK `#login-btn`
WAIT `.login-form` 2
CLICK `#email`
TYPE "demo@example.com"
CLICK `#password`
TYPE "demo123"
CLICK `button[type="submit"]`
WAIT `.welcome-message` 5
ENDPROC
PROC browse_products
# Go to catalog
CLICK `#catalog-link`
WAIT `.product-grid` 3
# Apply filters
CLICK `.collapsible`
WAIT 0.5
CLICK `input[type="checkbox"]`
# Load some products
SCROLL DOWN 500
WAIT 1
SCROLL DOWN 500
WAIT 1
ENDPROC
# Main workflow
GO http://127.0.0.1:8080/playground/
WAIT `body` 2
# Handle initial popups
handle_popups
# Login if not already
IF (NOT EXISTS `.user-info`) THEN login_user
# Browse products
browse_products
# Navigate to tabs demo
CLICK `a[href="#tabs"]`
WAIT `.tabs-container` 2
# Interact with tabs
CLICK `button[data-tab="reviews"]`
WAIT 1
# Load comments
IF (EXISTS `.load-comments`) THEN CLICK `.load-comments`
WAIT `.comments-section` 2
# Check specifications
CLICK `button[data-tab="specs"]`
WAIT 1
# Final navigation to data tables
CLICK `a[href="#data"]`
WAIT `.data-table` 2
# Search in table
CLICK `.search-input`
TYPE "User"
# Load more rows
CLICK `.load-more-rows`
WAIT 1
# Export data
CLICK `#export-btn`
EVAL `console.log('✅ Workflow completed successfully!')`

View File

@@ -1,304 +0,0 @@
#!/usr/bin/env python3
"""
C4A-Script Tutorial Server
Serves the tutorial app and provides C4A compilation API
"""
import sys
import os
from pathlib import Path
from flask import Flask, render_template_string, request, jsonify, send_from_directory
from flask_cors import CORS
# Add parent directories to path to import crawl4ai
sys.path.insert(0, str(Path(__file__).parent.parent.parent.parent.parent))
try:
from crawl4ai.script import compile as c4a_compile
C4A_AVAILABLE = True
except ImportError:
print("⚠️ C4A compiler not available. Using mock compiler.")
C4A_AVAILABLE = False
app = Flask(__name__)
CORS(app)
# Serve static files
@app.route('/')
def index():
return send_from_directory('.', 'index.html')
@app.route('/assets/<path:path>')
def serve_assets(path):
return send_from_directory('assets', path)
@app.route('/playground/')
def playground():
return send_from_directory('playground', 'index.html')
@app.route('/playground/<path:path>')
def serve_playground(path):
return send_from_directory('playground', path)
# API endpoint for C4A compilation
@app.route('/api/compile', methods=['POST'])
def compile_endpoint():
try:
data = request.get_json()
script = data.get('script', '')
if not script:
return jsonify({
'success': False,
'error': {
'line': 1,
'column': 1,
'message': 'No script provided',
'suggestion': 'Write some C4A commands'
}
})
if C4A_AVAILABLE:
# Use real C4A compiler
result = c4a_compile(script)
if result.success:
return jsonify({
'success': True,
'jsCode': result.js_code,
'metadata': {
'lineCount': len(result.js_code),
'sourceLines': len(script.split('\n'))
}
})
else:
error = result.first_error
return jsonify({
'success': False,
'error': {
'line': error.line,
'column': error.column,
'message': error.message,
'suggestion': error.suggestions[0].message if error.suggestions else None,
'code': error.code,
'sourceLine': error.source_line
}
})
else:
# Use mock compiler for demo
result = mock_compile(script)
return jsonify(result)
except Exception as e:
return jsonify({
'success': False,
'error': {
'line': 1,
'column': 1,
'message': f'Server error: {str(e)}',
'suggestion': 'Check server logs'
}
}), 500
def mock_compile(script):
"""Simple mock compiler for demo when C4A is not available"""
lines = [line for line in script.split('\n') if line.strip() and not line.strip().startswith('#')]
js_code = []
for i, line in enumerate(lines):
line = line.strip()
try:
if line.startswith('GO '):
url = line[3:].strip()
# Handle relative URLs
if not url.startswith(('http://', 'https://')):
url = '/' + url.lstrip('/')
js_code.append(f"await page.goto('{url}');")
elif line.startswith('WAIT '):
parts = line[5:].strip().split(' ')
if parts[0].startswith('`'):
selector = parts[0].strip('`')
timeout = parts[1] if len(parts) > 1 else '5'
js_code.append(f"await page.waitForSelector('{selector}', {{ timeout: {timeout}000 }});")
else:
seconds = parts[0]
js_code.append(f"await page.waitForTimeout({seconds}000);")
elif line.startswith('CLICK '):
selector = line[6:].strip().strip('`')
js_code.append(f"await page.click('{selector}');")
elif line.startswith('TYPE '):
text = line[5:].strip().strip('"')
js_code.append(f"await page.keyboard.type('{text}');")
elif line.startswith('SCROLL '):
parts = line[7:].strip().split(' ')
direction = parts[0]
amount = parts[1] if len(parts) > 1 else '500'
if direction == 'DOWN':
js_code.append(f"await page.evaluate(() => window.scrollBy(0, {amount}));")
elif direction == 'UP':
js_code.append(f"await page.evaluate(() => window.scrollBy(0, -{amount}));")
elif line.startswith('IF '):
if 'THEN' not in line:
return {
'success': False,
'error': {
'line': i + 1,
'column': len(line),
'message': "Missing 'THEN' keyword after IF condition",
'suggestion': "Add 'THEN' after the condition",
'sourceLine': line
}
}
condition = line[3:line.index('THEN')].strip()
action = line[line.index('THEN') + 4:].strip()
if 'EXISTS' in condition:
selector_match = condition.split('`')
if len(selector_match) >= 2:
selector = selector_match[1]
action_selector = action.split('`')[1] if '`' in action else ''
js_code.append(
f"if (await page.$$('{selector}').length > 0) {{ "
f"await page.click('{action_selector}'); }}"
)
elif line.startswith('PRESS '):
key = line[6:].strip()
js_code.append(f"await page.keyboard.press('{key}');")
else:
# Unknown command
return {
'success': False,
'error': {
'line': i + 1,
'column': 1,
'message': f"Unknown command: {line.split()[0]}",
'suggestion': "Check command syntax",
'sourceLine': line
}
}
except Exception as e:
return {
'success': False,
'error': {
'line': i + 1,
'column': 1,
'message': f"Failed to parse: {str(e)}",
'suggestion': "Check syntax",
'sourceLine': line
}
}
return {
'success': True,
'jsCode': js_code,
'metadata': {
'lineCount': len(js_code),
'sourceLines': len(lines)
}
}
# Example scripts endpoint
@app.route('/api/examples')
def get_examples():
examples = [
{
'id': 'cookie-banner',
'name': 'Handle Cookie Banner',
'description': 'Accept cookies and close newsletter popup',
'script': '''# Handle cookie banner and newsletter
GO http://127.0.0.1:8080/playground/
WAIT `body` 2
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
IF (EXISTS `.newsletter-popup`) THEN CLICK `.close`'''
},
{
'id': 'login',
'name': 'Login Flow',
'description': 'Complete login with credentials',
'script': '''# Login to the site
CLICK `#login-btn`
WAIT `.login-form` 2
CLICK `#email`
TYPE "demo@example.com"
CLICK `#password`
TYPE "demo123"
IF (EXISTS `#remember-me`) THEN CLICK `#remember-me`
CLICK `button[type="submit"]`
WAIT `.welcome-message` 5'''
},
{
'id': 'infinite-scroll',
'name': 'Infinite Scroll',
'description': 'Load products with scrolling',
'script': '''# Navigate to catalog and scroll
CLICK `#catalog-link`
WAIT `.product-grid` 3
# Scroll multiple times to load products
SCROLL DOWN 1000
WAIT 1
SCROLL DOWN 1000
WAIT 1
SCROLL DOWN 1000'''
},
{
'id': 'form-wizard',
'name': 'Multi-step Form',
'description': 'Complete a multi-step survey',
'script': '''# Navigate to forms
CLICK `a[href="#forms"]`
WAIT `#survey-form` 2
# Step 1: Basic info
CLICK `#full-name`
TYPE "John Doe"
CLICK `#survey-email`
TYPE "john@example.com"
CLICK `.next-step`
WAIT 1
# Step 2: Preferences
CLICK `#interests`
CLICK `option[value="tech"]`
CLICK `option[value="music"]`
CLICK `.next-step`
WAIT 1
# Step 3: Submit
CLICK `#submit-survey`
WAIT `.success-message` 5'''
}
]
return jsonify(examples)
if __name__ == '__main__':
port = int(os.environ.get('PORT', 8080))
print(f"""
╔══════════════════════════════════════════════════════════╗
║ C4A-Script Interactive Tutorial Server ║
╠══════════════════════════════════════════════════════════╣
║ ║
║ Server running at: http://localhost:{port:<6}
║ ║
║ Features: ║
║ • C4A-Script compilation API ║
║ • Interactive playground ║
║ • Real-time execution visualization ║
║ ║
║ C4A Compiler: {'✓ Available' if C4A_AVAILABLE else '✗ Using mock compiler':<30}
║ ║
╚══════════════════════════════════════════════════════════╝
""")
app.run(host='0.0.0.0', port=port, debug=True)

View File

@@ -1,69 +0,0 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Blockly Test</title>
<style>
body {
margin: 0;
padding: 20px;
background: #0e0e10;
color: #e0e0e0;
font-family: monospace;
}
#blocklyDiv {
height: 600px;
width: 100%;
border: 1px solid #2a2a2c;
}
#output {
margin-top: 20px;
padding: 15px;
background: #1a1a1b;
border: 1px solid #2a2a2c;
white-space: pre-wrap;
}
</style>
</head>
<body>
<h1>C4A-Script Blockly Test</h1>
<div id="blocklyDiv"></div>
<div id="output">
<h3>Generated C4A-Script:</h3>
<pre id="code-output"></pre>
</div>
<script src="https://unpkg.com/blockly/blockly.min.js"></script>
<script src="assets/c4a-blocks.js"></script>
<script>
// Simple test
const workspace = Blockly.inject('blocklyDiv', {
toolbox: `
<xml>
<category name="Test" colour="#1E88E5">
<block type="c4a_go"></block>
<block type="c4a_wait_time"></block>
<block type="c4a_click"></block>
</category>
</xml>
`,
theme: Blockly.Theme.defineTheme('dark', {
'base': Blockly.Themes.Classic,
'componentStyles': {
'workspaceBackgroundColour': '#0e0e10',
'toolboxBackgroundColour': '#1a1a1b',
'toolboxForegroundColour': '#e0e0e0',
'flyoutBackgroundColour': '#1a1a1b',
'flyoutForegroundColour': '#e0e0e0',
}
})
});
workspace.addChangeListener((event) => {
const code = Blockly.JavaScript.workspaceToCode(workspace);
document.getElementById('code-output').textContent = code;
});
</script>
</body>
</html>

View File

@@ -1,6 +1,12 @@
import time, re
from crawl4ai.content_scraping_strategy import WebScrapingStrategy, LXMLWebScrapingStrategy
import time
import os
import sys
parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
sys.path.append(parent_dir)
__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
from crawl4ai.content_scraping_strategy import LXMLWebScrapingStrategy
import functools
from collections import defaultdict
@@ -57,7 +63,7 @@ methods_to_profile = [
# Apply decorators to both strategies
for strategy, name in [(WebScrapingStrategy, "Original"), (LXMLWebScrapingStrategy, "LXML")]:
for strategy, name in [(LXMLWebScrapingStrategy, "Original"), (LXMLWebScrapingStrategy, "LXML")]:
for method in methods_to_profile:
apply_decorators(strategy, method, name)
@@ -85,7 +91,7 @@ def generate_large_html(n_elements=1000):
def test_scraping():
# Initialize both scrapers
original_scraper = WebScrapingStrategy()
original_scraper = LXMLWebScrapingStrategy()
selected_scraper = LXMLWebScrapingStrategy()
# Generate test HTML

File diff suppressed because it is too large Load Diff

View File

@@ -1,807 +0,0 @@
"""
BBC Sport Research Assistant Pipeline
=====================================
This example demonstrates how URLSeeder helps create an efficient research pipeline:
1. Discover all available URLs without crawling
2. Filter and rank them based on relevance
3. Crawl only the most relevant content
4. Generate comprehensive research insights
Pipeline Steps:
1. Get user query
2. Optionally enhance query using LLM
3. Use URLSeeder to discover and rank URLs
4. Crawl top K URLs with BM25 filtering
5. Generate detailed response with citations
Requirements:
- pip install crawl4ai
- pip install litellm
- export GEMINI_API_KEY="your-api-key"
Usage:
- Run normally: python bbc_sport_research_assistant.py
- Run test mode: python bbc_sport_research_assistant.py test
Note: AsyncUrlSeeder now uses context manager for automatic cleanup.
"""
import asyncio
import json
import os
import hashlib
import pickle
from typing import List, Dict, Optional, Tuple
from dataclasses import dataclass, asdict
from datetime import datetime
from pathlib import Path
# Rich for colored output
from rich.console import Console
from rich.text import Text
from rich.panel import Panel
from rich.table import Table
from rich.progress import Progress, SpinnerColumn, TextColumn
# Crawl4AI imports
from crawl4ai import (
AsyncWebCrawler,
BrowserConfig,
CrawlerRunConfig,
AsyncUrlSeeder,
SeedingConfig,
AsyncLogger
)
from crawl4ai.content_filter_strategy import PruningContentFilter
from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
# LiteLLM for AI communication
import litellm
# Initialize Rich console
console = Console()
# Get the current directory where this script is located
SCRIPT_DIR = Path(__file__).parent.resolve()
# Cache configuration - relative to script directory
CACHE_DIR = SCRIPT_DIR / "temp_cache"
CACHE_DIR.mkdir(parents=True, exist_ok=True)
# Testing limits
TESTING_MODE = True
MAX_URLS_DISCOVERY = 100 if TESTING_MODE else 1000
MAX_URLS_TO_CRAWL = 5 if TESTING_MODE else 10
def get_cache_key(prefix: str, *args) -> str:
"""Generate cache key from prefix and arguments"""
content = f"{prefix}:{'|'.join(str(arg) for arg in args)}"
return hashlib.md5(content.encode()).hexdigest()
def load_from_cache(cache_key: str) -> Optional[any]:
"""Load data from cache if exists"""
cache_path = CACHE_DIR / f"{cache_key}.pkl"
if cache_path.exists():
with open(cache_path, 'rb') as f:
return pickle.load(f)
return None
def save_to_cache(cache_key: str, data: any) -> None:
"""Save data to cache"""
cache_path = CACHE_DIR / f"{cache_key}.pkl"
with open(cache_path, 'wb') as f:
pickle.dump(data, f)
@dataclass
class ResearchConfig:
"""Configuration for research pipeline"""
# Core settings
domain: str = "www.bbc.com/sport"
max_urls_discovery: int = 100
max_urls_to_crawl: int = 10
top_k_urls: int = 10
# Scoring and filtering
score_threshold: float = 0.1
scoring_method: str = "bm25"
# Processing options
use_llm_enhancement: bool = True
extract_head_metadata: bool = True
live_check: bool = True
force_refresh: bool = False
# Crawler settings
max_concurrent_crawls: int = 5
timeout: int = 30000
headless: bool = True
# Output settings
save_json: bool = True
save_markdown: bool = True
output_dir: str = None # Will be set in __post_init__
# Development settings
test_mode: bool = False
interactive_mode: bool = False
verbose: bool = True
def __post_init__(self):
"""Adjust settings based on test mode"""
if self.test_mode:
self.max_urls_discovery = 50
self.max_urls_to_crawl = 3
self.top_k_urls = 5
# Set default output directory relative to script location
if self.output_dir is None:
self.output_dir = str(SCRIPT_DIR / "research_results")
@dataclass
class ResearchQuery:
"""Container for research query and metadata"""
original_query: str
enhanced_query: Optional[str] = None
search_patterns: List[str] = None
timestamp: str = None
@dataclass
class ResearchResult:
"""Container for research results"""
query: ResearchQuery
discovered_urls: List[Dict]
crawled_content: List[Dict]
synthesis: str
citations: List[Dict]
metadata: Dict
async def get_user_query() -> str:
"""
Get research query from user input
"""
query = input("\n🔍 Enter your research query: ")
return query.strip()
async def enhance_query_with_llm(query: str) -> ResearchQuery:
"""
Use LLM to enhance the research query:
- Extract key terms
- Generate search patterns
- Identify related topics
"""
# Check cache
cache_key = get_cache_key("enhanced_query", query)
cached_result = load_from_cache(cache_key)
if cached_result:
console.print("[dim cyan]📦 Using cached enhanced query[/dim cyan]")
return cached_result
try:
response = await litellm.acompletion(
model="gemini/gemini-2.5-flash-preview-04-17",
messages=[{
"role": "user",
"content": f"""Given this research query: "{query}"
Extract:
1. Key terms and concepts (as a list)
2. Related search terms
3. A more specific/enhanced version of the query
Return as JSON:
{{
"key_terms": ["term1", "term2"],
"related_terms": ["related1", "related2"],
"enhanced_query": "enhanced version of query"
}}"""
}],
# reasoning_effort="low",
temperature=0.3,
response_format={"type": "json_object"}
)
data = json.loads(response.choices[0].message.content)
# Create search patterns
all_terms = data["key_terms"] + data["related_terms"]
patterns = [f"*{term.lower()}*" for term in all_terms]
result = ResearchQuery(
original_query=query,
enhanced_query=data["enhanced_query"],
search_patterns=patterns[:10], # Limit patterns
timestamp=datetime.now().isoformat()
)
# Cache the result
save_to_cache(cache_key, result)
return result
except Exception as e:
console.print(f"[yellow]⚠️ LLM enhancement failed: {e}[/yellow]")
# Fallback to simple tokenization
return ResearchQuery(
original_query=query,
enhanced_query=query,
search_patterns=tokenize_query_to_patterns(query),
timestamp=datetime.now().isoformat()
)
def tokenize_query_to_patterns(query: str) -> List[str]:
"""
Convert query into URL patterns for URLSeeder
Example: "AI startups funding" -> ["*ai*", "*startup*", "*funding*"]
"""
# Simple tokenization - split and create patterns
words = query.lower().split()
# Filter out common words
stop_words = {'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for', 'that'}
keywords = [w for w in words if w not in stop_words and len(w) > 2]
# Create patterns
patterns = [f"*{keyword}*" for keyword in keywords]
return patterns[:8] # Limit to 8 patterns
async def discover_urls(domain: str, query: str, config: ResearchConfig) -> List[Dict]:
"""
Use URLSeeder to discover and rank URLs:
1. Fetch all URLs from domain
2. Filter by patterns
3. Extract metadata (titles, descriptions)
4. Rank by BM25 relevance score
5. Return top K URLs
"""
# Check cache
cache_key = get_cache_key("discovered_urls", domain, query, config.top_k_urls)
cached_result = load_from_cache(cache_key)
if cached_result and not config.force_refresh:
console.print("[dim cyan]📦 Using cached URL discovery[/dim cyan]")
return cached_result
console.print(f"\n[cyan]🔍 Discovering URLs from {domain}...[/cyan]")
# Initialize URL seeder with context manager
async with AsyncUrlSeeder(logger=AsyncLogger(verbose=config.verbose)) as seeder:
# Configure seeding
seeding_config = SeedingConfig(
source="sitemap+cc", # Use both sitemap and Common Crawl
extract_head=config.extract_head_metadata,
query=query,
scoring_method=config.scoring_method,
score_threshold=config.score_threshold,
max_urls=config.max_urls_discovery,
live_check=config.live_check,
force=config.force_refresh
)
try:
# Discover URLs
urls = await seeder.urls(domain, seeding_config)
# Sort by relevance score (descending)
sorted_urls = sorted(
urls,
key=lambda x: x.get('relevance_score', 0),
reverse=True
)
# Take top K
top_urls = sorted_urls[:config.top_k_urls]
console.print(f"[green]✅ Discovered {len(urls)} URLs, selected top {len(top_urls)}[/green]")
# Cache the result
save_to_cache(cache_key, top_urls)
return top_urls
except Exception as e:
console.print(f"[red]❌ URL discovery failed: {e}[/red]")
return []
async def crawl_selected_urls(urls: List[str], query: str, config: ResearchConfig) -> List[Dict]:
"""
Crawl selected URLs with content filtering:
- Use AsyncWebCrawler.arun_many()
- Apply content filter
- Generate clean markdown
"""
# Extract just URLs from the discovery results
url_list = [u['url'] for u in urls if 'url' in u][:config.max_urls_to_crawl]
if not url_list:
console.print("[red]❌ No URLs to crawl[/red]")
return []
console.print(f"\n[cyan]🕷️ Crawling {len(url_list)} URLs...[/cyan]")
# Check cache for each URL
crawled_results = []
urls_to_crawl = []
for url in url_list:
cache_key = get_cache_key("crawled_content", url, query)
cached_content = load_from_cache(cache_key)
if cached_content and not config.force_refresh:
crawled_results.append(cached_content)
else:
urls_to_crawl.append(url)
if urls_to_crawl:
console.print(f"[cyan]📥 Crawling {len(urls_to_crawl)} new URLs (cached: {len(crawled_results)})[/cyan]")
# Configure markdown generator with content filter
md_generator = DefaultMarkdownGenerator(
content_filter=PruningContentFilter(
threshold=0.48,
threshold_type="dynamic",
min_word_threshold=10
),
)
# Configure crawler
crawler_config = CrawlerRunConfig(
markdown_generator=md_generator,
exclude_external_links=True,
excluded_tags=['nav', 'header', 'footer', 'aside'],
)
# Create crawler with browser config
async with AsyncWebCrawler(
config=BrowserConfig(
headless=config.headless,
verbose=config.verbose
)
) as crawler:
# Crawl URLs
results = await crawler.arun_many(
urls_to_crawl,
config=crawler_config,
max_concurrent=config.max_concurrent_crawls
)
# Process results
for url, result in zip(urls_to_crawl, results):
if result.success:
content_data = {
'url': url,
'title': result.metadata.get('title', ''),
'markdown': result.markdown.fit_markdown or result.markdown.raw_markdown,
'raw_length': len(result.markdown.raw_markdown),
'fit_length': len(result.markdown.fit_markdown) if result.markdown.fit_markdown else len(result.markdown.raw_markdown),
'metadata': result.metadata
}
crawled_results.append(content_data)
# Cache the result
cache_key = get_cache_key("crawled_content", url, query)
save_to_cache(cache_key, content_data)
else:
console.print(f" [red]❌ Failed: {url[:50]}... - {result.error}[/red]")
console.print(f"[green]✅ Successfully crawled {len(crawled_results)} URLs[/green]")
return crawled_results
async def generate_research_synthesis(
query: str,
crawled_content: List[Dict]
) -> Tuple[str, List[Dict]]:
"""
Use LLM to synthesize research findings:
- Analyze all crawled content
- Generate comprehensive answer
- Extract citations and references
"""
if not crawled_content:
return "No content available for synthesis.", []
console.print("\n[cyan]🤖 Generating research synthesis...[/cyan]")
# Prepare content for LLM
content_sections = []
for i, content in enumerate(crawled_content, 1):
section = f"""
SOURCE {i}:
Title: {content['title']}
URL: {content['url']}
Content Preview:
{content['markdown'][:1500]}...
"""
content_sections.append(section)
combined_content = "\n---\n".join(content_sections)
try:
response = await litellm.acompletion(
model="gemini/gemini-2.5-flash-preview-04-17",
messages=[{
"role": "user",
"content": f"""Research Query: "{query}"
Based on the following sources, provide a comprehensive research synthesis.
{combined_content}
Please provide:
1. An executive summary (2-3 sentences)
2. Key findings (3-5 bullet points)
3. Detailed analysis (2-3 paragraphs)
4. Future implications or trends
Format your response with clear sections and cite sources using [Source N] notation.
Keep the total response under 800 words."""
}],
# reasoning_effort="medium",
temperature=0.7
)
synthesis = response.choices[0].message.content
# Extract citations from the synthesis
citations = []
for i, content in enumerate(crawled_content, 1):
if f"[Source {i}]" in synthesis or f"Source {i}" in synthesis:
citations.append({
'source_id': i,
'title': content['title'],
'url': content['url']
})
return synthesis, citations
except Exception as e:
console.print(f"[red]❌ Synthesis generation failed: {e}[/red]")
# Fallback to simple summary
summary = f"Research on '{query}' found {len(crawled_content)} relevant articles:\n\n"
for content in crawled_content[:3]:
summary += f"- {content['title']}\n {content['url']}\n\n"
return summary, []
def format_research_output(result: ResearchResult) -> str:
"""
Format the final research output with:
- Executive summary
- Key findings
- Detailed analysis
- Citations and sources
"""
output = []
output.append("\n" + "=" * 60)
output.append("🔬 RESEARCH RESULTS")
output.append("=" * 60)
# Query info
output.append(f"\n📋 Query: {result.query.original_query}")
if result.query.enhanced_query != result.query.original_query:
output.append(f" Enhanced: {result.query.enhanced_query}")
# Discovery stats
output.append(f"\n📊 Statistics:")
output.append(f" - URLs discovered: {len(result.discovered_urls)}")
output.append(f" - URLs crawled: {len(result.crawled_content)}")
output.append(f" - Processing time: {result.metadata.get('duration', 'N/A')}")
# Synthesis
output.append(f"\n📝 SYNTHESIS")
output.append("-" * 60)
output.append(result.synthesis)
# Citations
if result.citations:
output.append(f"\n📚 SOURCES")
output.append("-" * 60)
for citation in result.citations:
output.append(f"[{citation['source_id']}] {citation['title']}")
output.append(f" {citation['url']}")
return "\n".join(output)
async def save_research_results(result: ResearchResult, config: ResearchConfig) -> Tuple[str, str]:
"""
Save research results in JSON and Markdown formats
Returns:
Tuple of (json_path, markdown_path)
"""
# Create output directory
output_dir = Path(config.output_dir)
output_dir.mkdir(parents=True, exist_ok=True)
# Generate filename based on query and timestamp
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
query_slug = result.query.original_query[:50].replace(" ", "_").replace("/", "_")
base_filename = f"{timestamp}_{query_slug}"
json_path = None
md_path = None
# Save JSON
if config.save_json:
json_path = output_dir / f"{base_filename}.json"
with open(json_path, 'w') as f:
json.dump(asdict(result), f, indent=2, default=str)
console.print(f"\n[green]💾 JSON saved: {json_path}[/green]")
# Save Markdown
if config.save_markdown:
md_path = output_dir / f"{base_filename}.md"
# Create formatted markdown
md_content = [
f"# Research Report: {result.query.original_query}",
f"\n**Generated on:** {result.metadata.get('timestamp', 'N/A')}",
f"\n**Domain:** {result.metadata.get('domain', 'N/A')}",
f"\n**Processing time:** {result.metadata.get('duration', 'N/A')}",
"\n---\n",
"## Query Information",
f"- **Original Query:** {result.query.original_query}",
f"- **Enhanced Query:** {result.query.enhanced_query or 'N/A'}",
f"- **Search Patterns:** {', '.join(result.query.search_patterns or [])}",
"\n## Statistics",
f"- **URLs Discovered:** {len(result.discovered_urls)}",
f"- **URLs Crawled:** {len(result.crawled_content)}",
f"- **Sources Cited:** {len(result.citations)}",
"\n## Research Synthesis\n",
result.synthesis,
"\n## Sources\n"
]
# Add citations
for citation in result.citations:
md_content.append(f"### [{citation['source_id']}] {citation['title']}")
md_content.append(f"- **URL:** [{citation['url']}]({citation['url']})")
md_content.append("")
# Add discovered URLs summary
md_content.extend([
"\n## Discovered URLs (Top 10)\n",
"| Score | URL | Title |",
"|-------|-----|-------|"
])
for url_data in result.discovered_urls[:10]:
score = url_data.get('relevance_score', 0)
url = url_data.get('url', '')
title = 'N/A'
if 'head_data' in url_data and url_data['head_data']:
title = url_data['head_data'].get('title', 'N/A')[:60] + '...'
md_content.append(f"| {score:.3f} | {url[:50]}... | {title} |")
# Write markdown
with open(md_path, 'w') as f:
f.write('\n'.join(md_content))
console.print(f"[green]📄 Markdown saved: {md_path}[/green]")
return str(json_path) if json_path else None, str(md_path) if md_path else None
async def wait_for_user(message: str = "\nPress Enter to continue..."):
"""Wait for user input in interactive mode"""
input(message)
async def research_pipeline(
query: str,
config: ResearchConfig
) -> ResearchResult:
"""
Main research pipeline orchestrator with configurable settings
"""
start_time = datetime.now()
# Display pipeline header
header = Panel(
f"[bold cyan]Research Pipeline[/bold cyan]\n\n"
f"[dim]Domain:[/dim] {config.domain}\n"
f"[dim]Mode:[/dim] {'Test' if config.test_mode else 'Production'}\n"
f"[dim]Interactive:[/dim] {'Yes' if config.interactive_mode else 'No'}",
title="🚀 Starting",
border_style="cyan"
)
console.print(header)
# Step 1: Enhance query (optional)
console.print(f"\n[bold cyan]📝 Step 1: Query Processing[/bold cyan]")
if config.interactive_mode:
await wait_for_user()
if config.use_llm_enhancement:
research_query = await enhance_query_with_llm(query)
else:
research_query = ResearchQuery(
original_query=query,
enhanced_query=query,
search_patterns=tokenize_query_to_patterns(query),
timestamp=datetime.now().isoformat()
)
console.print(f" [green]✅ Query ready:[/green] {research_query.enhanced_query or query}")
# Step 2: Discover URLs
console.print(f"\n[bold cyan]🔍 Step 2: URL Discovery[/bold cyan]")
if config.interactive_mode:
await wait_for_user()
discovered_urls = await discover_urls(
domain=config.domain,
query=research_query.enhanced_query or query,
config=config
)
if not discovered_urls:
return ResearchResult(
query=research_query,
discovered_urls=[],
crawled_content=[],
synthesis="No relevant URLs found for the given query.",
citations=[],
metadata={'duration': str(datetime.now() - start_time)}
)
console.print(f" [green]✅ Found {len(discovered_urls)} relevant URLs[/green]")
# Step 3: Crawl selected URLs
console.print(f"\n[bold cyan]🕷️ Step 3: Content Crawling[/bold cyan]")
if config.interactive_mode:
await wait_for_user()
crawled_content = await crawl_selected_urls(
urls=discovered_urls,
query=research_query.enhanced_query or query,
config=config
)
console.print(f" [green]✅ Successfully crawled {len(crawled_content)} pages[/green]")
# Step 4: Generate synthesis
console.print(f"\n[bold cyan]🤖 Step 4: Synthesis Generation[/bold cyan]")
if config.interactive_mode:
await wait_for_user()
synthesis, citations = await generate_research_synthesis(
query=research_query.enhanced_query or query,
crawled_content=crawled_content
)
console.print(f" [green]✅ Generated synthesis with {len(citations)} citations[/green]")
# Step 5: Create result
result = ResearchResult(
query=research_query,
discovered_urls=discovered_urls,
crawled_content=crawled_content,
synthesis=synthesis,
citations=citations,
metadata={
'duration': str(datetime.now() - start_time),
'domain': config.domain,
'timestamp': datetime.now().isoformat(),
'config': asdict(config)
}
)
duration = datetime.now() - start_time
console.print(f"\n[bold green]✅ Research completed in {duration}[/bold green]")
return result
async def main():
"""
Main entry point for the BBC Sport Research Assistant
"""
# Example queries
example_queries = [
"Premier League transfer news and rumors",
"Champions League match results and analysis",
"World Cup qualifying updates",
"Football injury reports and return dates",
"Tennis grand slam tournament results"
]
# Display header
console.print(Panel.fit(
"[bold cyan]BBC Sport Research Assistant[/bold cyan]\n\n"
"This tool demonstrates efficient research using URLSeeder:\n"
"[dim]• Discover all URLs without crawling\n"
"• Filter and rank by relevance\n"
"• Crawl only the most relevant content\n"
"• Generate AI-powered insights with citations[/dim]\n\n"
f"[dim]📁 Working directory: {SCRIPT_DIR}[/dim]",
title="🔬 Welcome",
border_style="cyan"
))
# Configuration options table
config_table = Table(title="\n⚙️ Configuration Options", show_header=False, box=None)
config_table.add_column(style="bold cyan", width=3)
config_table.add_column()
config_table.add_row("1", "Quick Test Mode (3 URLs, fast)")
config_table.add_row("2", "Standard Mode (10 URLs, balanced)")
config_table.add_row("3", "Comprehensive Mode (20 URLs, thorough)")
config_table.add_row("4", "Custom Configuration")
console.print(config_table)
config_choice = input("\nSelect configuration (1-4): ").strip()
# Create config based on choice
if config_choice == "1":
config = ResearchConfig(test_mode=True, interactive_mode=False)
elif config_choice == "2":
config = ResearchConfig(max_urls_to_crawl=10, top_k_urls=10)
elif config_choice == "3":
config = ResearchConfig(max_urls_to_crawl=20, top_k_urls=20, max_urls_discovery=200)
else:
# Custom configuration
config = ResearchConfig()
config.test_mode = input("\nTest mode? (y/n): ").lower() == 'y'
config.interactive_mode = input("Interactive mode (pause between steps)? (y/n): ").lower() == 'y'
config.use_llm_enhancement = input("Use AI to enhance queries? (y/n): ").lower() == 'y'
if not config.test_mode:
try:
config.max_urls_to_crawl = int(input("Max URLs to crawl (default 10): ") or "10")
config.top_k_urls = int(input("Top K URLs to select (default 10): ") or "10")
except ValueError:
console.print("[yellow]Using default values[/yellow]")
# Display example queries
query_table = Table(title="\n📋 Example Queries", show_header=False, box=None)
query_table.add_column(style="bold cyan", width=3)
query_table.add_column()
for i, q in enumerate(example_queries, 1):
query_table.add_row(str(i), q)
console.print(query_table)
query_input = input("\nSelect a query (1-5) or enter your own: ").strip()
if query_input.isdigit() and 1 <= int(query_input) <= len(example_queries):
query = example_queries[int(query_input) - 1]
else:
query = query_input if query_input else example_queries[0]
console.print(f"\n[bold cyan]📝 Selected Query:[/bold cyan] {query}")
# Run the research pipeline
result = await research_pipeline(query=query, config=config)
# Display results
formatted_output = format_research_output(result)
# print(formatted_output)
console.print(Panel.fit(
formatted_output,
title="🔬 Research Results",
border_style="green"
))
# Save results
if config.save_json or config.save_markdown:
json_path, md_path = await save_research_results(result, config)
# print(f"\n✅ Results saved successfully!")
if json_path:
console.print(f"[green]JSON saved at:[/green] {json_path}")
if md_path:
console.print(f"[green]Markdown saved at:[/green] {md_path}")
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -1,155 +0,0 @@
#!/usr/bin/env python3
"""
Convert Crawl4AI URL Seeder tutorial markdown to Colab notebook format
"""
import json
import re
from pathlib import Path
def parse_markdown_to_cells(markdown_content):
"""Parse markdown content and convert to notebook cells"""
cells = []
# Split content by cell markers
lines = markdown_content.split('\n')
# Extract the header content before first cell marker
header_lines = []
i = 0
while i < len(lines) and not lines[i].startswith('# cell'):
header_lines.append(lines[i])
i += 1
# Add header as markdown cell if it exists
if header_lines:
header_content = '\n'.join(header_lines).strip()
if header_content:
cells.append({
"cell_type": "markdown",
"metadata": {},
"source": header_content.split('\n')
})
# Process cells marked with # cell X type:Y
current_cell_content = []
current_cell_type = None
while i < len(lines):
line = lines[i]
# Check for cell marker
cell_match = re.match(r'^# cell (\d+) type:(markdown|code)$', line)
if cell_match:
# Save previous cell if exists
if current_cell_content and current_cell_type:
content = '\n'.join(current_cell_content).strip()
if content:
if current_cell_type == 'code':
cells.append({
"cell_type": "code",
"execution_count": None,
"metadata": {},
"outputs": [],
"source": content.split('\n')
})
else:
cells.append({
"cell_type": "markdown",
"metadata": {},
"source": content.split('\n')
})
# Start new cell
current_cell_type = cell_match.group(2)
current_cell_content = []
else:
# Add line to current cell
current_cell_content.append(line)
i += 1
# Add last cell if exists
if current_cell_content and current_cell_type:
content = '\n'.join(current_cell_content).strip()
if content:
if current_cell_type == 'code':
cells.append({
"cell_type": "code",
"execution_count": None,
"metadata": {},
"outputs": [],
"source": content.split('\n')
})
else:
cells.append({
"cell_type": "markdown",
"metadata": {},
"source": content.split('\n')
})
return cells
def create_colab_notebook(cells):
"""Create a Colab notebook structure"""
notebook = {
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "Crawl4AI_URL_Seeder_Tutorial.ipynb",
"provenance": [],
"collapsed_sections": [],
"toc_visible": True
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": cells
}
return notebook
def main():
# Read the markdown file
md_path = Path("tutorial_url_seeder.md")
if not md_path.exists():
print(f"Error: {md_path} not found!")
return
print(f"Reading {md_path}...")
with open(md_path, 'r', encoding='utf-8') as f:
markdown_content = f.read()
# Parse markdown to cells
print("Parsing markdown content...")
cells = parse_markdown_to_cells(markdown_content)
print(f"Created {len(cells)} cells")
# Create notebook
print("Creating Colab notebook...")
notebook = create_colab_notebook(cells)
# Save notebook
output_path = Path("Crawl4AI_URL_Seeder_Tutorial.ipynb")
with open(output_path, 'w', encoding='utf-8') as f:
json.dump(notebook, f, indent=2, ensure_ascii=False)
print(f"✅ Successfully created {output_path}")
print(f" - Total cells: {len(cells)}")
print(f" - Markdown cells: {sum(1 for c in cells if c['cell_type'] == 'markdown')}")
print(f" - Code cells: {sum(1 for c in cells if c['cell_type'] == 'code')}")
if __name__ == "__main__":
main()

File diff suppressed because it is too large Load Diff

View File

@@ -1,263 +0,0 @@
"""
URL Seeder Demo - Interactive showcase of Crawl4AI's URL discovery capabilities
This demo shows:
1. Basic URL discovery from sitemaps and Common Crawl
2. Cache management and forced refresh
3. Live URL validation and metadata extraction
4. BM25 relevance scoring for intelligent filtering
5. Integration with AsyncWebCrawler for the complete pipeline
6. Multi-domain discovery across multiple sites
Note: The AsyncUrlSeeder now supports context manager protocol for automatic cleanup.
"""
import asyncio
import time
from datetime import datetime
from rich.console import Console
from rich.table import Table
from rich.panel import Panel
from rich.progress import Progress, SpinnerColumn, BarColumn, TimeElapsedColumn
from rich.prompt import Prompt, Confirm
from crawl4ai import (
AsyncWebCrawler,
CrawlerRunConfig,
AsyncUrlSeeder,
SeedingConfig
)
console = Console()
console.rule("[bold green]🌐 Crawl4AI URL Seeder: Interactive Demo")
DOMAIN = "crawl4ai.com"
# Utils
def print_head_info(head_data):
table = Table(title="<head> Metadata", expand=True)
table.add_column("Key", style="cyan", no_wrap=True)
table.add_column("Value", style="magenta")
if not head_data:
console.print("[yellow]No head data found.")
return
if head_data.get("title"):
table.add_row("title", head_data["title"])
if head_data.get("charset"):
table.add_row("charset", head_data["charset"])
for k, v in head_data.get("meta", {}).items():
table.add_row(f"meta:{k}", v)
for rel, items in head_data.get("link", {}).items():
for item in items:
table.add_row(f"link:{rel}", item.get("href", ""))
console.print(table)
async def section_1_basic_exploration(seed: AsyncUrlSeeder):
console.rule("[bold cyan]1. Basic Seeding")
cfg = SeedingConfig(source="cc+sitemap", pattern="*", verbose=True)
start_time = time.time()
with Progress(SpinnerColumn(), "[progress.description]{task.description}") as p:
p.add_task(description="Fetching from Common Crawl + Sitemap...", total=None)
urls = await seed.urls(DOMAIN, cfg)
elapsed = time.time() - start_time
console.print(f"[green]✓ Fetched {len(urls)} URLs in {elapsed:.2f} seconds")
console.print(f"[dim] Speed: {len(urls)/elapsed:.0f} URLs/second[/dim]\n")
console.print("[bold]Sample URLs:[/bold]")
for u in urls[:5]:
console.print(f"{u['url']}")
async def section_2_cache_demo(seed: AsyncUrlSeeder):
console.rule("[bold cyan]2. Caching Demonstration")
console.print("[yellow]Using `force=True` to bypass cache and fetch fresh data.[/yellow]")
cfg = SeedingConfig(source="cc", pattern="*crawl4ai.com/core/*", verbose=False, force = True)
await seed.urls(DOMAIN, cfg)
async def section_3_live_head(seed: AsyncUrlSeeder):
console.rule("[bold cyan]3. Live Check + Head Extraction")
cfg = SeedingConfig(
extract_head=True,
concurrency=10,
hits_per_sec=5,
pattern="*crawl4ai.com/*",
max_urls=10,
verbose=False,
)
urls = await seed.urls(DOMAIN, cfg)
valid = [u for u in urls if u["status"] == "valid"]
console.print(f"[green]Valid: {len(valid)} / {len(urls)}")
if valid:
print_head_info(valid[0]["head_data"])
async def section_4_bm25_scoring(seed: AsyncUrlSeeder):
console.rule("[bold cyan]4. BM25 Relevance Scoring")
console.print("[yellow]Using AI-powered relevance scoring to find the most relevant content[/yellow]")
query = "markdown generation extraction strategies"
cfg = SeedingConfig(
source="sitemap",
extract_head=True,
query=query,
scoring_method="bm25",
score_threshold=0.3, # Only URLs with >30% relevance
max_urls=20,
verbose=False
)
with Progress(SpinnerColumn(), "[progress.description]{task.description}") as p:
p.add_task(description=f"Searching for: '{query}'", total=None)
urls = await seed.urls(DOMAIN, cfg)
console.print(f"[green]Found {len(urls)} relevant URLs (score > 0.3)")
# Show top results with scores
table = Table(title="Top 5 Most Relevant Pages", expand=True)
table.add_column("Score", style="cyan", width=8)
table.add_column("Title", style="magenta")
table.add_column("URL", style="blue", overflow="fold")
for url in urls[:5]:
score = f"{url['relevance_score']:.2f}"
title = url['head_data'].get('title', 'No title')[:60] + "..."
table.add_row(score, title, url['url'])
console.print(table)
async def section_5_keyword_filter_to_agent(seed: AsyncUrlSeeder):
console.rule("[bold cyan]5. Complete Pipeline: Discover → Filter → Crawl")
cfg = SeedingConfig(
extract_head=True,
concurrency=20,
hits_per_sec=10,
max_urls=10,
pattern="*crawl4ai.com/*",
force=True,
)
urls = await seed.urls(DOMAIN, cfg)
keywords = ["deep crawling", "markdown", "llm"]
selected = [u for u in urls if any(k in str(u["head_data"]).lower() for k in keywords)]
console.print(f"[cyan]Selected {len(selected)} URLs with relevant keywords:")
for u in selected[:10]:
console.print("", u["url"])
console.print("\n[yellow]Passing above URLs to arun_many() LLM agent for crawling...")
async with AsyncWebCrawler(verbose=True) as crawler:
crawl_run_config = CrawlerRunConfig(
# Example crawl settings for these URLs:
only_text=True, # Just get text content
screenshot=False,
pdf=False,
word_count_threshold=50, # Only process pages with at least 50 words
stream=True,
verbose=False # Keep logs clean for arun_many in this demo
)
# Extract just the URLs from the selected results
urls_to_crawl = [u["url"] for u in selected]
# We'll stream results for large lists, but collect them here for demonstration
crawled_results_stream = await crawler.arun_many(urls_to_crawl, config=crawl_run_config)
final_crawled_data = []
async for result in crawled_results_stream:
final_crawled_data.append(result)
if len(final_crawled_data) % 5 == 0:
print(f" Processed {len(final_crawled_data)}/{len(urls_to_crawl)} URLs...")
print(f"\n Successfully crawled {len(final_crawled_data)} URLs.")
if final_crawled_data:
print("\n Example of a crawled result's URL and Markdown (first successful one):")
for result in final_crawled_data:
if result.success and result.markdown.raw_markdown:
print(f" URL: {result.url}")
print(f" Markdown snippet: {result.markdown.raw_markdown[:200]}...")
break
else:
print(" No successful crawls with markdown found.")
else:
print(" No successful crawls found.")
async def section_6_multi_domain(seed: AsyncUrlSeeder):
console.rule("[bold cyan]6. Multi-Domain Discovery")
console.print("[yellow]Discovering Python tutorials across multiple educational sites[/yellow]\n")
domains = ["docs.python.org", "realpython.com", "docs.crawl4ai.com"]
cfg = SeedingConfig(
source="sitemap",
extract_head=True,
query="python tutorial guide",
scoring_method="bm25",
score_threshold=0.2,
max_urls=5 # Per domain
)
start_time = time.time()
with Progress(SpinnerColumn(), "[progress.description]{task.description}") as p:
task = p.add_task(description="Discovering across domains...", total=None)
results = await seed.many_urls(domains, cfg)
elapsed = time.time() - start_time
total_urls = sum(len(urls) for urls in results.values())
console.print(f"[green]✓ Found {total_urls} relevant URLs across {len(domains)} domains in {elapsed:.2f}s\n")
# Show results per domain
for domain, urls in results.items():
console.print(f"[bold]{domain}:[/bold] {len(urls)} relevant pages")
if urls:
top = urls[0]
console.print(f" Top result: [{top['relevance_score']:.2f}] {top['head_data'].get('title', 'No title')}")
async def main():
async with AsyncUrlSeeder() as seed:
# Interactive menu
sections = {
"1": ("Basic URL Discovery", section_1_basic_exploration),
"2": ("Cache Management Demo", section_2_cache_demo),
"3": ("Live Check & Metadata Extraction", section_3_live_head),
"4": ("BM25 Relevance Scoring", section_4_bm25_scoring),
"5": ("Complete Pipeline (Discover → Filter → Crawl)", section_5_keyword_filter_to_agent),
"6": ("Multi-Domain Discovery", section_6_multi_domain),
"7": ("Run All Demos", None)
}
console.print("\n[bold]Available Demos:[/bold]")
for key, (title, _) in sections.items():
console.print(f" {key}. {title}")
choice = Prompt.ask("\n[cyan]Which demo would you like to run?[/cyan]",
choices=list(sections.keys()),
default="7")
console.print()
if choice == "7":
# Run all demos
for key, (title, func) in sections.items():
if key != "7" and func:
await func(seed)
if key != "6": # Don't pause after the last demo
if not Confirm.ask("\n[yellow]Continue to next demo?[/yellow]", default=True):
break
console.print()
else:
# Run selected demo
_, func = sections[choice]
await func(seed)
console.rule("[bold green]Demo Complete ✔︎")
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -1,128 +0,0 @@
"""
🚀 URL Seeder + AsyncWebCrawler = Magic!
Quick demo showing discovery → filter → crawl pipeline
Note: Uses context manager for automatic cleanup of resources.
"""
import asyncio, os
from crawl4ai import AsyncUrlSeeder, AsyncWebCrawler, SeedingConfig, CrawlerRunConfig, AsyncLogger, DefaultMarkdownGenerator
from crawl4ai.content_filter_strategy import PruningContentFilter
CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
# 🔍 Example 1: Discover ALL → Filter → Crawl
async def discover_and_crawl():
"""Find Python module tutorials & extract them all!"""
async with AsyncUrlSeeder(logger=AsyncLogger()) as seeder:
# Step 1: See how many URLs exist (spoiler: A LOT!)
print("📊 Let's see what RealPython has...")
all_urls = await seeder.urls("realpython.com",
SeedingConfig(source="sitemap"))
print(f"😱 Found {len(all_urls)} total URLs!")
# Step 2: Filter for Python modules (perfect size ~13)
print("\n🎯 Filtering for 'python-modules' tutorials...")
module_urls = await seeder.urls("realpython.com",
SeedingConfig(
source="sitemap",
pattern="*python-modules*",
live_check=True # Make sure they're alive!
))
print(f"✨ Found {len(module_urls)} module tutorials")
for url in module_urls[:3]: # Show first 3
status = "" if url["status"] == "valid" else ""
print(f"{status} {url['url']}")
# Step 3: Crawl them all with pruning (keep it lean!)
print("\n🕷️ Crawling all module tutorials...")
async with AsyncWebCrawler() as crawler:
config = CrawlerRunConfig(
markdown_generator=DefaultMarkdownGenerator(
content_filter=PruningContentFilter( # Smart filtering!
threshold=0.48, # Remove fluff
threshold_type="fixed",
),
),
only_text=True,
stream=True,
)
# Extract just the URLs from the seeder results
urls_to_crawl = [u["url"] for u in module_urls[:5]]
results = await crawler.arun_many(urls_to_crawl, config=config)
# Process & save
saved = 0
async for result in results:
if result.success:
# Save each tutorial (name from URL)
name = result.url.split("/")[-2] + ".md"
name = os.path.join(CURRENT_DIR, name)
with open(name, "w") as f:
f.write(result.markdown.fit_markdown)
saved += 1
print(f"💾 Saved: {name}")
print(f"\n🎉 Successfully saved {saved} tutorials!")
# 🔍 Example 2: Beautiful Soup articles with metadata peek
async def explore_beautifulsoup():
"""Discover BeautifulSoup content & peek at metadata"""
async with AsyncUrlSeeder(logger=AsyncLogger()) as seeder:
print("🍲 Looking for Beautiful Soup articles...")
soup_urls = await seeder.urls("realpython.com",
SeedingConfig(
source="sitemap",
pattern="*beautiful-soup*",
extract_head=True # Get the metadata!
))
print(f"\n📚 Found {len(soup_urls)} Beautiful Soup articles:\n")
# Show what we discovered
for i, url in enumerate(soup_urls, 1):
meta = url["head_data"]["meta"]
print(f"{i}. {url['head_data']['title']}")
print(f" 📝 {meta.get('description', 'No description')[:60]}...")
print(f" 👤 By: {meta.get('author', 'Unknown')}")
print(f" 🔗 {url['url']}\n")
# 🔍 Example 3: Smart search with BM25 relevance scoring
async def smart_search_with_bm25():
"""Use AI-powered relevance scoring to find the best content"""
async with AsyncUrlSeeder(logger=AsyncLogger()) as seeder:
print("🧠 Smart search: 'web scraping tutorial quiz'")
# Search with BM25 scoring - AI finds the best matches!
results = await seeder.urls("realpython.com",
SeedingConfig(
source="sitemap",
pattern="*beautiful-soup*",
extract_head=True,
query="web scraping tutorial quiz", # Our search
scoring_method="bm25",
score_threshold=0.2 # Quality filter
))
print(f"\n🎯 Top {len(results)} most relevant results:\n")
# Show ranked results with relevance scores
for i, result in enumerate(results[:3], 1):
print(f"{i}. [{result['relevance_score']:.2f}] {result['head_data']['title']}")
print(f" 🔗 {result['url'][:60]}...")
print("\n✨ BM25 automatically ranked by relevance!")
# 🎬 Run the show!
async def main():
print("=" * 60)
await discover_and_crawl()
print("\n" + "=" * 60 + "\n")
await explore_beautifulsoup()
print("\n" + "=" * 60 + "\n")
await smart_search_with_bm25()
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -1,992 +0,0 @@
# C4A-Script API Reference
Complete reference for all C4A-Script commands, syntax, and advanced features.
## Command Categories
### 🧭 Navigation Commands
Navigate between pages and manage browser history.
#### `GO <url>`
Navigate to a specific URL.
**Syntax:**
```c4a
GO <url>
```
**Parameters:**
- `url` - Target URL (string)
**Examples:**
```c4a
GO https://example.com
GO https://api.example.com/login
GO /relative/path
```
**Notes:**
- Supports both absolute and relative URLs
- Automatically handles protocol detection
- Waits for page load to complete
---
#### `RELOAD`
Refresh the current page.
**Syntax:**
```c4a
RELOAD
```
**Examples:**
```c4a
RELOAD
```
**Notes:**
- Equivalent to pressing F5 or clicking browser refresh
- Waits for page reload to complete
- Preserves current URL
---
#### `BACK`
Navigate back in browser history.
**Syntax:**
```c4a
BACK
```
**Examples:**
```c4a
BACK
```
**Notes:**
- Equivalent to clicking browser back button
- Does nothing if no previous page exists
- Waits for navigation to complete
---
#### `FORWARD`
Navigate forward in browser history.
**Syntax:**
```c4a
FORWARD
```
**Examples:**
```c4a
FORWARD
```
**Notes:**
- Equivalent to clicking browser forward button
- Does nothing if no next page exists
- Waits for navigation to complete
### ⏱️ Wait Commands
Control timing and synchronization with page elements.
#### `WAIT <time>`
Wait for a specified number of seconds.
**Syntax:**
```c4a
WAIT <seconds>
```
**Parameters:**
- `seconds` - Number of seconds to wait (number)
**Examples:**
```c4a
WAIT 3
WAIT 1.5
WAIT 10
```
**Notes:**
- Accepts decimal values
- Useful for giving dynamic content time to load
- Non-blocking for other browser operations
---
#### `WAIT <selector> <timeout>`
Wait for an element to appear on the page.
**Syntax:**
```c4a
WAIT `<selector>` <timeout>
```
**Parameters:**
- `selector` - CSS selector for the element (string in backticks)
- `timeout` - Maximum seconds to wait (number)
**Examples:**
```c4a
WAIT `#content` 10
WAIT `.loading-spinner` 5
WAIT `button[type="submit"]` 15
WAIT `.results .item:first-child` 8
```
**Notes:**
- Fails if element doesn't appear within timeout
- More reliable than fixed time waits
- Supports complex CSS selectors
---
#### `WAIT "<text>" <timeout>`
Wait for specific text to appear anywhere on the page.
**Syntax:**
```c4a
WAIT "<text>" <timeout>
```
**Parameters:**
- `text` - Text content to wait for (string in quotes)
- `timeout` - Maximum seconds to wait (number)
**Examples:**
```c4a
WAIT "Loading complete" 10
WAIT "Welcome back" 5
WAIT "Search results" 15
```
**Notes:**
- Case-sensitive text matching
- Searches entire page content
- Useful for dynamic status messages
### 🖱️ Mouse Commands
Simulate mouse interactions and movements.
#### `CLICK <selector>`
Click on an element specified by CSS selector.
**Syntax:**
```c4a
CLICK `<selector>`
```
**Parameters:**
- `selector` - CSS selector for the element (string in backticks)
**Examples:**
```c4a
CLICK `#submit-button`
CLICK `.menu-item:first-child`
CLICK `button[data-action="save"]`
CLICK `a[href="/dashboard"]`
```
**Notes:**
- Waits for element to be clickable
- Scrolls element into view if necessary
- Handles overlapping elements intelligently
---
#### `CLICK <x> <y>`
Click at specific coordinates on the page.
**Syntax:**
```c4a
CLICK <x> <y>
```
**Parameters:**
- `x` - X coordinate in pixels (number)
- `y` - Y coordinate in pixels (number)
**Examples:**
```c4a
CLICK 100 200
CLICK 500 300
CLICK 0 0
```
**Notes:**
- Coordinates are relative to viewport
- Useful when element selectors are unreliable
- Consider responsive design implications
---
#### `DOUBLE_CLICK <selector>`
Double-click on an element.
**Syntax:**
```c4a
DOUBLE_CLICK `<selector>`
```
**Parameters:**
- `selector` - CSS selector for the element (string in backticks)
**Examples:**
```c4a
DOUBLE_CLICK `.file-icon`
DOUBLE_CLICK `#editable-cell`
DOUBLE_CLICK `.expandable-item`
```
**Notes:**
- Triggers dblclick event
- Common for opening files or editing inline content
- Timing between clicks is automatically handled
---
#### `RIGHT_CLICK <selector>`
Right-click on an element to open context menu.
**Syntax:**
```c4a
RIGHT_CLICK `<selector>`
```
**Parameters:**
- `selector` - CSS selector for the element (string in backticks)
**Examples:**
```c4a
RIGHT_CLICK `#context-target`
RIGHT_CLICK `.menu-trigger`
RIGHT_CLICK `img.thumbnail`
```
**Notes:**
- Opens browser/application context menu
- Useful for testing context menu interactions
- May be blocked by some applications
---
#### `SCROLL <direction> <amount>`
Scroll the page in a specified direction.
**Syntax:**
```c4a
SCROLL <direction> <amount>
```
**Parameters:**
- `direction` - Direction to scroll: `UP`, `DOWN`, `LEFT`, `RIGHT`
- `amount` - Number of pixels to scroll (number)
**Examples:**
```c4a
SCROLL DOWN 500
SCROLL UP 200
SCROLL LEFT 100
SCROLL RIGHT 300
```
**Notes:**
- Smooth scrolling animation
- Useful for infinite scroll pages
- Amount can be larger than viewport
---
#### `MOVE <x> <y>`
Move mouse cursor to specific coordinates.
**Syntax:**
```c4a
MOVE <x> <y>
```
**Parameters:**
- `x` - X coordinate in pixels (number)
- `y` - Y coordinate in pixels (number)
**Examples:**
```c4a
MOVE 200 100
MOVE 500 400
```
**Notes:**
- Triggers hover effects
- Useful for testing mouseover interactions
- Does not click, only moves cursor
---
#### `DRAG <x1> <y1> <x2> <y2>`
Drag from one point to another.
**Syntax:**
```c4a
DRAG <x1> <y1> <x2> <y2>
```
**Parameters:**
- `x1`, `y1` - Starting coordinates (numbers)
- `x2`, `y2` - Ending coordinates (numbers)
**Examples:**
```c4a
DRAG 100 100 500 300
DRAG 0 200 400 200
```
**Notes:**
- Simulates click, drag, and release
- Useful for sliders, resizing, reordering
- Smooth drag animation
### ⌨️ Keyboard Commands
Simulate keyboard input and key presses.
#### `TYPE "<text>"`
Type text into the currently focused element.
**Syntax:**
```c4a
TYPE "<text>"
```
**Parameters:**
- `text` - Text to type (string in quotes)
**Examples:**
```c4a
TYPE "Hello, World!"
TYPE "user@example.com"
TYPE "Password123!"
```
**Notes:**
- Requires an input element to be focused
- Types character by character with realistic timing
- Supports special characters and Unicode
---
#### `TYPE $<variable>`
Type the value of a variable.
**Syntax:**
```c4a
TYPE $<variable>
```
**Parameters:**
- `variable` - Variable name (without quotes)
**Examples:**
```c4a
SETVAR email = "user@example.com"
TYPE $email
```
**Notes:**
- Variable must be defined with SETVAR first
- Variable values are strings
- Useful for reusable credentials or data
---
#### `PRESS <key>`
Press and release a special key.
**Syntax:**
```c4a
PRESS <key>
```
**Parameters:**
- `key` - Key name (see supported keys below)
**Supported Keys:**
- `Tab`, `Enter`, `Escape`, `Space`
- `ArrowUp`, `ArrowDown`, `ArrowLeft`, `ArrowRight`
- `Delete`, `Backspace`
- `Home`, `End`, `PageUp`, `PageDown`
**Examples:**
```c4a
PRESS Tab
PRESS Enter
PRESS Escape
PRESS ArrowDown
```
**Notes:**
- Simulates actual key press and release
- Useful for form navigation and shortcuts
- Case-sensitive key names
---
#### `KEY_DOWN <key>`
Hold down a modifier key.
**Syntax:**
```c4a
KEY_DOWN <key>
```
**Parameters:**
- `key` - Modifier key: `Shift`, `Control`, `Alt`, `Meta`
**Examples:**
```c4a
KEY_DOWN Shift
KEY_DOWN Control
```
**Notes:**
- Must be paired with KEY_UP
- Useful for key combinations
- Meta key is Cmd on Mac, Windows key on PC
---
#### `KEY_UP <key>`
Release a modifier key.
**Syntax:**
```c4a
KEY_UP <key>
```
**Parameters:**
- `key` - Modifier key: `Shift`, `Control`, `Alt`, `Meta`
**Examples:**
```c4a
KEY_UP Shift
KEY_UP Control
```
**Notes:**
- Must be paired with KEY_DOWN
- Releases the specified modifier key
- Good practice to always release held keys
---
#### `CLEAR <selector>`
Clear the content of an input field.
**Syntax:**
```c4a
CLEAR `<selector>`
```
**Parameters:**
- `selector` - CSS selector for input element (string in backticks)
**Examples:**
```c4a
CLEAR `#search-box`
CLEAR `input[name="email"]`
CLEAR `.form-input:first-child`
```
**Notes:**
- Works with input, textarea elements
- Faster than selecting all and deleting
- Triggers appropriate change events
---
#### `SET <selector> "<value>"`
Set the value of an input field directly.
**Syntax:**
```c4a
SET `<selector>` "<value>"
```
**Parameters:**
- `selector` - CSS selector for input element (string in backticks)
- `value` - Value to set (string in quotes)
**Examples:**
```c4a
SET `#email` "user@example.com"
SET `#age` "25"
SET `textarea#message` "Hello, this is a test message."
```
**Notes:**
- Directly sets value without typing animation
- Faster than TYPE for long text
- Triggers change and input events
### 🔀 Control Flow Commands
Add conditional logic and loops to your scripts.
#### `IF (EXISTS <selector>) THEN <command>`
Execute command if element exists.
**Syntax:**
```c4a
IF (EXISTS `<selector>`) THEN <command>
```
**Parameters:**
- `selector` - CSS selector to check (string in backticks)
- `command` - Command to execute if condition is true
**Examples:**
```c4a
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-cookies`
IF (EXISTS `#popup-modal`) THEN CLICK `.close-button`
IF (EXISTS `.error-message`) THEN RELOAD
```
**Notes:**
- Checks for element existence at time of execution
- Does not wait for element to appear
- Can be combined with ELSE
---
#### `IF (EXISTS <selector>) THEN <command> ELSE <command>`
Execute command based on element existence.
**Syntax:**
```c4a
IF (EXISTS `<selector>`) THEN <command> ELSE <command>
```
**Parameters:**
- `selector` - CSS selector to check (string in backticks)
- First `command` - Execute if condition is true
- Second `command` - Execute if condition is false
**Examples:**
```c4a
IF (EXISTS `.user-menu`) THEN CLICK `.logout` ELSE CLICK `.login`
IF (EXISTS `.loading`) THEN WAIT 5 ELSE CLICK `#continue`
```
**Notes:**
- Exactly one command will be executed
- Useful for handling different page states
- Commands must be on same line
---
#### `IF (NOT EXISTS <selector>) THEN <command>`
Execute command if element does not exist.
**Syntax:**
```c4a
IF (NOT EXISTS `<selector>`) THEN <command>
```
**Parameters:**
- `selector` - CSS selector to check (string in backticks)
- `command` - Command to execute if element doesn't exist
**Examples:**
```c4a
IF (NOT EXISTS `.logged-in`) THEN GO /login
IF (NOT EXISTS `.results`) THEN CLICK `#search-button`
```
**Notes:**
- Inverse of EXISTS condition
- Useful for error handling
- Can check for missing required elements
---
#### `IF (<javascript>) THEN <command>`
Execute command based on JavaScript condition.
**Syntax:**
```c4a
IF (`<javascript>`) THEN <command>
```
**Parameters:**
- `javascript` - JavaScript expression that returns boolean (string in backticks)
- `command` - Command to execute if condition is true
**Examples:**
```c4a
IF (`window.innerWidth < 768`) THEN CLICK `.mobile-menu`
IF (`document.readyState === "complete"`) THEN CLICK `#start`
IF (`localStorage.getItem("user")`) THEN GO /dashboard
```
**Notes:**
- JavaScript executes in browser context
- Must return boolean value
- Access to all browser APIs and globals
---
#### `REPEAT (<command>, <count>)`
Repeat a command a specific number of times.
**Syntax:**
```c4a
REPEAT (<command>, <count>)
```
**Parameters:**
- `command` - Command to repeat
- `count` - Number of times to repeat (number)
**Examples:**
```c4a
REPEAT (SCROLL DOWN 300, 5)
REPEAT (PRESS Tab, 3)
REPEAT (CLICK `.load-more`, 10)
```
**Notes:**
- Executes command exactly count times
- Useful for pagination, scrolling, navigation
- No delay between repetitions (add WAIT if needed)
---
#### `REPEAT (<command>, <condition>)`
Repeat a command while condition is true.
**Syntax:**
```c4a
REPEAT (<command>, `<condition>`)
```
**Parameters:**
- `command` - Command to repeat
- `condition` - JavaScript condition to check (string in backticks)
**Examples:**
```c4a
REPEAT (SCROLL DOWN 500, `document.querySelector(".load-more")`)
REPEAT (PRESS ArrowDown, `window.scrollY < document.body.scrollHeight`)
```
**Notes:**
- Condition checked before each iteration
- JavaScript condition must return boolean
- Be careful to avoid infinite loops
### 💾 Variables and Data
Store and manipulate data within scripts.
#### `SETVAR <name> = "<value>"`
Create or update a variable.
**Syntax:**
```c4a
SETVAR <name> = "<value>"
```
**Parameters:**
- `name` - Variable name (alphanumeric, underscore)
- `value` - Variable value (string in quotes)
**Examples:**
```c4a
SETVAR username = "john@example.com"
SETVAR password = "secret123"
SETVAR base_url = "https://api.example.com"
SETVAR counter = "0"
```
**Notes:**
- Variables are global within script scope
- Values are always strings
- Can be used with TYPE command using $variable syntax
---
#### `EVAL <javascript>`
Execute arbitrary JavaScript code.
**Syntax:**
```c4a
EVAL `<javascript>`
```
**Parameters:**
- `javascript` - JavaScript code to execute (string in backticks)
**Examples:**
```c4a
EVAL `console.log("Script started")`
EVAL `window.scrollTo(0, 0)`
EVAL `localStorage.setItem("test", "value")`
EVAL `document.title = "Automated Test"`
```
**Notes:**
- Full access to browser JavaScript APIs
- Useful for custom logic and debugging
- Return values are not captured
- Be careful with security implications
### 📝 Comments and Documentation
#### `# <comment>`
Add comments to scripts for documentation.
**Syntax:**
```c4a
# <comment text>
```
**Examples:**
```c4a
# This script logs into the application
# Step 1: Navigate to login page
GO /login
# Step 2: Fill credentials
TYPE "user@example.com"
```
**Notes:**
- Comments are ignored during execution
- Useful for documentation and debugging
- Can appear anywhere in script
- Supports multi-line documentation blocks
### 🔧 Procedures (Advanced)
Define reusable command sequences.
#### `PROC <name> ... ENDPROC`
Define a reusable procedure.
**Syntax:**
```c4a
PROC <name>
<commands>
ENDPROC
```
**Parameters:**
- `name` - Procedure name (alphanumeric, underscore)
- `commands` - Commands to include in procedure
**Examples:**
```c4a
PROC login
CLICK `#email`
TYPE $email
CLICK `#password`
TYPE $password
CLICK `#submit`
ENDPROC
PROC handle_popups
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
IF (EXISTS `.newsletter-modal`) THEN CLICK `.close`
ENDPROC
```
**Notes:**
- Procedures must be defined before use
- Support nested command structures
- Variables are shared with main script scope
---
#### `<procedure_name>`
Call a defined procedure.
**Syntax:**
```c4a
<procedure_name>
```
**Examples:**
```c4a
# Define procedure first
PROC setup
GO /login
WAIT `#form` 5
ENDPROC
# Call procedure
setup
login
```
**Notes:**
- Procedure must be defined before calling
- Can be called multiple times
- No parameters supported (use variables instead)
## Error Handling Best Practices
### 1. Always Use Waits
```c4a
# Bad - element might not be ready
CLICK `#button`
# Good - wait for element first
WAIT `#button` 5
CLICK `#button`
```
### 2. Handle Optional Elements
```c4a
# Check before interacting
IF (EXISTS `.popup`) THEN CLICK `.close`
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
# Then proceed with main flow
CLICK `#main-action`
```
### 3. Use Descriptive Variables
```c4a
# Set up reusable data
SETVAR admin_email = "admin@company.com"
SETVAR test_password = "TestPass123!"
SETVAR staging_url = "https://staging.example.com"
# Use throughout script
GO $staging_url
TYPE $admin_email
```
### 4. Add Debugging Information
```c4a
# Log progress
EVAL `console.log("Starting login process")`
GO /login
# Verify page state
IF (`document.title.includes("Login")`) THEN EVAL `console.log("On login page")`
# Continue with login
TYPE $username
```
## Common Patterns
### Login Flow
```c4a
# Complete login automation
SETVAR email = "user@example.com"
SETVAR password = "mypassword"
GO /login
WAIT `#login-form` 5
# Handle optional cookie banner
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-cookies`
# Fill and submit form
CLICK `#email`
TYPE $email
PRESS Tab
TYPE $password
CLICK `button[type="submit"]`
# Wait for redirect
WAIT `.dashboard` 10
```
### Infinite Scroll
```c4a
# Load all content with infinite scroll
GO /products
# Scroll and load more content
REPEAT (SCROLL DOWN 500, `document.querySelector(".load-more")`)
# Alternative: Fixed number of scrolls
REPEAT (SCROLL DOWN 800, 10)
WAIT 2
```
### Form Validation
```c4a
# Handle form with validation
SET `#email` "invalid-email"
CLICK `#submit`
# Check for validation error
IF (EXISTS `.error-email`) THEN SET `#email` "valid@example.com"
# Retry submission
CLICK `#submit`
WAIT `.success-message` 5
```
### Multi-step Process
```c4a
# Complex multi-step workflow
PROC navigate_to_step
CLICK `.next-button`
WAIT `.step-content` 5
ENDPROC
# Step 1
WAIT `.step-1` 5
SET `#name` "John Doe"
navigate_to_step
# Step 2
SET `#email` "john@example.com"
navigate_to_step
# Step 3
CLICK `#submit-final`
WAIT `.confirmation` 10
```
## Integration with Crawl4AI
Use C4A-Script with Crawl4AI for dynamic content interaction:
```python
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
# Define interaction script
script = """
# Handle dynamic content loading
WAIT `.content` 5
IF (EXISTS `.load-more-button`) THEN CLICK `.load-more-button`
WAIT `.additional-content` 5
# Accept cookies if needed
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept-all`
"""
config = CrawlerRunConfig(
c4a_script=script,
wait_for=".content",
screenshot=True
)
async with AsyncWebCrawler() as crawler:
result = await crawler.arun("https://example.com", config=config)
print(result.markdown)
```
This reference covers all available C4A-Script commands and patterns. For interactive learning, try the [tutorial](../examples/c4a_script/tutorial/) or [live demo](https://docs.crawl4ai.com/c4a-script/demo).

View File

@@ -1,396 +0,0 @@
# C4A-Script Interactive Tutorial
A comprehensive web-based tutorial for learning and experimenting with C4A-Script - Crawl4AI's visual web automation language.
## 🚀 Quick Start
### Prerequisites
- Python 3.7+
- Modern web browser (Chrome, Firefox, Safari, Edge)
### Running the Tutorial
1. **Clone and Navigate**
```bash
git clone https://github.com/unclecode/crawl4ai.git
cd crawl4ai/docs/examples/c4a_script/tutorial/
```
2. **Install Dependencies**
```bash
pip install flask
```
3. **Launch the Server**
```bash
python server.py
```
4. **Open in Browser**
```
http://localhost:8080
```
**🌐 Try Online**: [Live Demo](https://docs.crawl4ai.com/c4a-script/demo)
### 2. Try Your First Script
```c4a
# Basic interaction
GO playground/
WAIT `body` 2
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
CLICK `#start-tutorial`
```
## 🎯 What You'll Learn
### Core Features
- **📝 Text Editor**: Write C4A-Script with syntax highlighting
- **🧩 Visual Editor**: Build scripts using drag-and-drop Blockly interface
- **🎬 Recording Mode**: Capture browser actions and auto-generate scripts
- **⚡ Live Execution**: Run scripts in real-time with instant feedback
- **📊 Timeline View**: Visualize and edit automation steps
## 📚 Tutorial Content
### Basic Commands
- **Navigation**: `GO url`
- **Waiting**: `WAIT selector timeout` or `WAIT seconds`
- **Clicking**: `CLICK selector`
- **Typing**: `TYPE "text"`
- **Scrolling**: `SCROLL DOWN/UP amount`
### Control Flow
- **Conditionals**: `IF (condition) THEN action`
- **Loops**: `REPEAT (action, condition)`
- **Procedures**: Define reusable command sequences
### Advanced Features
- **JavaScript evaluation**: `EVAL code`
- **Variables**: `SET name = "value"`
- **Complex selectors**: CSS selectors in backticks
## 🎮 Interactive Playground Features
The tutorial includes a fully interactive web app with:
### 1. **Authentication System**
- Login form with validation
- Session management
- Protected content
### 2. **Dynamic Content**
- Infinite scroll products
- Pagination controls
- Load more buttons
### 3. **Complex Forms**
- Multi-step wizards
- Dynamic field visibility
- Form validation
### 4. **Interactive Elements**
- Tabs and accordions
- Modals and popups
- Expandable content
### 5. **Data Tables**
- Sortable columns
- Search functionality
- Export options
## 🛠️ Tutorial Features
### Live Code Editor
- Syntax highlighting
- Real-time compilation
- Error messages with suggestions
### JavaScript Output Viewer
- See generated JavaScript code
- Edit and test JS directly
- Understand the compilation
### Visual Execution
- Step-by-step progress
- Element highlighting
- Console output
### Example Scripts
Load pre-written examples demonstrating:
- Cookie banner handling
- Login workflows
- Infinite scroll automation
- Multi-step form completion
- Complex interaction sequences
## 📖 Tutorial Sections
### 1. Getting Started
Learn basic commands and syntax:
```c4a
GO https://example.com
WAIT `.content` 5
CLICK `.button`
```
### 2. Handling Dynamic Content
Master waiting strategies and conditionals:
```c4a
IF (EXISTS `.popup`) THEN CLICK `.close`
WAIT `.results` 10
```
### 3. Form Automation
Fill and submit forms:
```c4a
CLICK `#email`
TYPE "user@example.com"
CLICK `button[type="submit"]`
```
### 4. Advanced Workflows
Build complex automation flows:
```c4a
PROC login
CLICK `#username`
TYPE $username
CLICK `#password`
TYPE $password
CLICK `#login-btn`
ENDPROC
SET username = "demo"
SET password = "pass123"
login
```
## 🎯 Practice Challenges
### Challenge 1: Cookie & Popups
Handle the cookie banner and newsletter popup that appear on page load.
### Challenge 2: Complete Login
Successfully log into the application using the demo credentials.
### Challenge 3: Load All Products
Use infinite scroll to load all 100 products in the catalog.
### Challenge 4: Multi-step Survey
Complete the entire multi-step survey form.
### Challenge 5: Full Workflow
Create a script that logs in, browses products, and exports data.
## 💡 Tips & Tricks
### 1. Use Specific Selectors
```c4a
# Good - specific
CLICK `button.submit-order`
# Bad - too generic
CLICK `button`
```
### 2. Always Handle Popups
```c4a
# Check for common popups
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
IF (EXISTS `.newsletter-modal`) THEN CLICK `.close`
```
### 3. Add Appropriate Waits
```c4a
# Wait for elements before interacting
WAIT `.form` 5
CLICK `#submit`
```
### 4. Use Procedures for Reusability
```c4a
PROC handle_popups
IF (EXISTS `.popup`) THEN CLICK `.close`
IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
ENDPROC
# Use anywhere
handle_popups
```
## 🔧 Troubleshooting
### Common Issues
1. **"Element not found"**
- Add a WAIT before clicking
- Check selector specificity
- Verify element exists with IF
2. **"Timeout waiting for selector"**
- Increase timeout value
- Check if element is dynamically loaded
- Verify selector is correct
3. **"Missing THEN keyword"**
- All IF statements need THEN
- Format: `IF (condition) THEN action`
## 🚀 Using with Crawl4AI
Once you've mastered C4A-Script in the tutorial, use it with Crawl4AI:
```python
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
config = CrawlerRunConfig(
url="https://example.com",
c4a_script="""
WAIT `.content` 5
IF (EXISTS `.load-more`) THEN CLICK `.load-more`
WAIT `.new-content` 3
"""
)
async with AsyncWebCrawler() as crawler:
result = await crawler.arun(config=config)
```
## 📝 Example Scripts
Check the `scripts/` folder for complete examples:
- `01-basic-interaction.c4a` - Getting started
- `02-login-flow.c4a` - Authentication
- `03-infinite-scroll.c4a` - Dynamic content
- `04-multi-step-form.c4a` - Complex forms
- `05-complex-workflow.c4a` - Full automation
## 🏗️ Developer Guide
### Project Architecture
```
tutorial/
├── server.py # Flask application server
├── assets/ # Tutorial-specific assets
│ ├── app.js # Main application logic
│ ├── c4a-blocks.js # Custom Blockly blocks
│ ├── c4a-generator.js # Code generation
│ ├── blockly-manager.js # Blockly integration
│ └── styles.css # Main styling
├── playground/ # Interactive demo environment
│ ├── index.html # Demo web application
│ ├── app.js # Demo app logic
│ └── styles.css # Demo styling
├── scripts/ # Example C4A scripts
└── index.html # Main tutorial interface
```
### Key Components
#### 1. TutorialApp (`assets/app.js`)
Main application controller managing:
- Code editor integration (CodeMirror)
- Script execution and browser preview
- Tutorial navigation and lessons
- State management and persistence
#### 2. BlocklyManager (`assets/blockly-manager.js`)
Visual programming interface:
- Custom C4A-Script block definitions
- Bidirectional sync between visual blocks and text
- Real-time code generation
- Dark theme integration
#### 3. Recording System
Powers the recording functionality:
- Browser event capture
- Smart event grouping and filtering
- Automatic C4A-Script generation
- Timeline visualization
### Customization
#### Adding New Commands
1. **Define Block** (`assets/c4a-blocks.js`)
2. **Add Generator** (`assets/c4a-generator.js`)
3. **Update Parser** (`assets/blockly-manager.js`)
#### Themes and Styling
- Main styles: `assets/styles.css`
- Theme variables: CSS custom properties
- Dark mode: Auto-applied based on system preference
### Configuration
```python
# server.py configuration
PORT = 8080
DEBUG = True
THREADED = True
```
### API Endpoints
- `GET /` - Main tutorial interface
- `GET /playground/` - Interactive demo environment
- `POST /execute` - Script execution endpoint
- `GET /examples/<script>` - Load example scripts
## 🔧 Troubleshooting
### Common Issues
**Port Already in Use**
```bash
# Kill existing process
lsof -ti:8080 | xargs kill -9
# Or use different port
python server.py --port 8081
```
**Blockly Not Loading**
- Check browser console for JavaScript errors
- Verify all static files are served correctly
- Ensure proper script loading order
**Recording Issues**
- Verify iframe permissions
- Check cross-origin communication
- Ensure event listeners are attached
### Debug Mode
Enable detailed logging by setting `DEBUG = True` in `assets/app.js`
## 📚 Additional Resources
- **[C4A-Script Documentation](../../md_v2/core/c4a-script.md)** - Complete language guide
- **[API Reference](../../md_v2/api/c4a-script-reference.md)** - Detailed command documentation
- **[Live Demo](https://docs.crawl4ai.com/c4a-script/demo)** - Try without installation
- **[Example Scripts](../)** - More automation examples
## 🤝 Contributing
### Bug Reports
1. Check existing issues on GitHub
2. Provide minimal reproduction steps
3. Include browser and system information
4. Add relevant console logs
### Feature Requests
1. Fork the repository
2. Create feature branch: `git checkout -b feature/my-feature`
3. Test thoroughly with different browsers
4. Update documentation
5. Submit pull request
### Code Style
- Use consistent indentation (2 spaces for JS, 4 for Python)
- Add comments for complex logic
- Follow existing naming conventions
- Test with multiple browsers
---
**Happy Automating!** 🎉
Need help? Check our [documentation](https://docs.crawl4ai.com) or open an issue on [GitHub](https://github.com/unclecode/crawl4ai).

View File

@@ -1,906 +0,0 @@
/* ================================================================
C4A-Script Tutorial - App Layout CSS
Terminal theme with Dank Mono font
================================================================ */
/* CSS Variables */
:root {
--bg-primary: #070708;
--bg-secondary: #0e0e10;
--bg-tertiary: #1a1a1b;
--border-color: #2a2a2c;
--border-hover: #3a3a3c;
--text-primary: #e0e0e0;
--text-secondary: #8b8b8d;
--text-muted: #606065;
--primary-color: #0fbbaa;
--primary-hover: #0da89a;
--primary-dim: #0a8577;
--error-color: #ff5555;
--warning-color: #ffb86c;
--success-color: #50fa7b;
--info-color: #8be9fd;
--code-bg: #1e1e20;
--modal-overlay: rgba(0, 0, 0, 0.8);
}
/* Base Reset */
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
/* Fonts */
@font-face {
font-family: 'Dank Mono';
src: url('DankMono-Regular.woff2') format('woff2');
font-weight: 400;
font-style: normal;
}
@font-face {
font-family: 'Dank Mono';
src: url('DankMono-Bold.woff2') format('woff2');
font-weight: 700;
font-style: normal;
}
@font-face {
font-family: 'Dank Mono';
src: url('DankMono-Italic.woff2') format('woff2');
font-weight: 400;
font-style: italic;
}
/* Body & App Container */
body {
font-family: 'Dank Mono', 'Monaco', 'Consolas', monospace;
background: var(--bg-primary);
color: var(--text-primary);
font-size: 14px;
line-height: 1.6;
overflow: hidden;
}
.app-container {
display: flex;
height: 100vh;
width: 100vw;
overflow: hidden;
}
/* Panels */
.editor-panel,
.playground-panel {
display: flex;
flex-direction: column;
height: 100%;
overflow: hidden;
}
.editor-panel {
flex: 1;
background: var(--bg-secondary);
border-right: 1px solid var(--border-color);
min-width: 400px;
}
.playground-panel {
flex: 1;
background: var(--bg-primary);
min-width: 400px;
}
/* Panel Headers */
.panel-header {
display: flex;
justify-content: space-between;
align-items: center;
padding: 12px 16px;
background: var(--bg-tertiary);
border-bottom: 1px solid var(--border-color);
flex-shrink: 0;
}
.panel-header h2 {
font-size: 16px;
font-weight: 600;
color: var(--primary-color);
margin: 0;
}
.header-actions {
display: flex;
gap: 8px;
}
/* Action Buttons */
.action-btn {
display: flex;
align-items: center;
gap: 6px;
padding: 6px 12px;
background: var(--bg-secondary);
color: var(--text-secondary);
border: 1px solid var(--border-color);
border-radius: 4px;
font-family: inherit;
font-size: 13px;
cursor: pointer;
transition: all 0.2s;
}
.action-btn:hover {
background: var(--bg-tertiary);
color: var(--text-primary);
border-color: var(--border-hover);
}
.action-btn.primary {
background: var(--primary-color);
color: var(--bg-primary);
border-color: var(--primary-color);
}
.action-btn.primary:hover {
background: var(--primary-hover);
border-color: var(--primary-hover);
}
.action-btn .icon {
font-size: 16px;
}
/* Editor Wrapper */
.editor-wrapper {
flex: 1;
display: flex;
overflow: hidden;
position: relative;
z-index: 1; /* Ensure it's above any potential overlays */
}
.editor-wrapper .CodeMirror {
flex: 1;
height: 100%;
font-family: 'Dank Mono', monospace;
font-size: 14px;
line-height: 1.5;
}
/* Ensure CodeMirror is interactive */
.CodeMirror {
background: var(--bg-primary) !important;
}
.CodeMirror-scroll {
overflow: auto !important;
}
/* Make cursor more visible */
.CodeMirror-cursor {
border-left: 2px solid var(--primary-color) !important;
border-left-width: 2px !important;
opacity: 1 !important;
visibility: visible !important;
}
/* Ensure cursor is visible when focused */
.CodeMirror-focused .CodeMirror-cursor {
visibility: visible !important;
}
/* Fix for CodeMirror in flex container */
.CodeMirror-sizer {
min-height: auto !important;
}
/* Remove aggressive pointer-events override */
.CodeMirror-code {
cursor: text;
}
.editor-wrapper textarea {
display: none;
}
/* Output Section (Bottom of Editor) */
.output-section {
height: 250px;
border-top: 1px solid var(--border-color);
display: flex;
flex-direction: column;
flex-shrink: 0;
}
/* Tabs */
.tabs {
display: flex;
background: var(--bg-tertiary);
border-bottom: 1px solid var(--border-color);
flex-shrink: 0;
}
.tab {
padding: 8px 20px;
background: transparent;
color: var(--text-secondary);
border: none;
border-bottom: 2px solid transparent;
font-family: inherit;
font-size: 13px;
cursor: pointer;
transition: all 0.2s;
}
.tab:hover {
color: var(--text-primary);
background: var(--bg-secondary);
}
.tab.active {
color: var(--primary-color);
border-bottom-color: var(--primary-color);
}
/* Tab Content */
.tab-content {
flex: 1;
overflow: hidden;
}
.tab-pane {
display: none;
height: 100%;
overflow-y: auto;
}
.tab-pane.active {
display: block;
}
/* Console */
.console {
padding: 12px;
background: var(--bg-primary);
font-size: 13px;
min-height: 100%;
}
.console-line {
margin-bottom: 8px;
display: flex;
align-items: flex-start;
gap: 8px;
}
.console-prompt {
color: var(--primary-color);
flex-shrink: 0;
}
.console-text {
color: var(--text-primary);
}
.console-error {
color: var(--error-color);
}
.console-warning {
color: var(--warning-color);
}
.console-success {
color: var(--success-color);
}
/* JavaScript Output */
.js-output-header {
display: flex;
justify-content: flex-end;
padding: 8px 12px;
background: var(--bg-tertiary);
border-bottom: 1px solid var(--border-color);
}
.js-actions {
display: flex;
gap: 8px;
}
.mini-btn {
padding: 4px 8px;
background: var(--bg-secondary);
color: var(--text-secondary);
border: 1px solid var(--border-color);
border-radius: 3px;
font-size: 12px;
cursor: pointer;
transition: all 0.2s;
}
.mini-btn:hover {
background: var(--bg-primary);
color: var(--text-primary);
}
.js-output {
padding: 12px;
background: var(--code-bg);
color: var(--text-primary);
font-family: 'Dank Mono', monospace;
font-size: 13px;
line-height: 1.5;
white-space: pre-wrap;
margin: 0;
min-height: calc(100% - 44px);
}
/* Execution Progress */
.execution-progress {
padding: 12px;
background: var(--bg-primary);
}
.progress-item {
display: flex;
align-items: center;
gap: 8px;
margin-bottom: 8px;
font-size: 13px;
}
.progress-icon {
color: var(--text-muted);
}
.progress-item.active .progress-icon {
color: var(--info-color);
animation: pulse 1s infinite;
}
.progress-item.completed .progress-icon {
color: var(--success-color);
}
.progress-item.error .progress-icon {
color: var(--error-color);
}
/* Playground */
.playground-wrapper {
flex: 1;
overflow: hidden;
}
#playground-frame {
width: 100%;
height: 100%;
border: none;
background: var(--bg-secondary);
}
/* Tutorial Intro Modal */
.tutorial-intro-modal {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: var(--modal-overlay);
display: flex;
align-items: center;
justify-content: center;
z-index: 2000;
transition: opacity 0.3s;
}
.tutorial-intro-modal.hidden {
display: none;
}
.intro-content {
background: var(--bg-tertiary);
border: 1px solid var(--border-color);
border-radius: 8px;
padding: 32px;
max-width: 500px;
box-shadow: 0 16px 48px rgba(0, 0, 0, 0.6);
}
.intro-content h2 {
color: var(--primary-color);
margin-bottom: 16px;
font-size: 24px;
}
.intro-content p {
color: var(--text-primary);
margin-bottom: 16px;
line-height: 1.6;
}
.intro-content ul {
list-style: none;
margin-bottom: 24px;
}
.intro-content li {
color: var(--text-secondary);
margin-bottom: 8px;
padding-left: 20px;
position: relative;
}
.intro-content li:before {
content: "▸";
position: absolute;
left: 0;
color: var(--primary-color);
}
.intro-actions {
display: flex;
gap: 12px;
justify-content: flex-end;
}
.intro-btn {
padding: 10px 24px;
background: var(--bg-secondary);
color: var(--text-primary);
border: 1px solid var(--border-color);
border-radius: 4px;
font-family: inherit;
font-size: 14px;
cursor: pointer;
transition: all 0.2s;
}
.intro-btn:hover {
background: var(--bg-primary);
border-color: var(--border-hover);
}
.intro-btn.primary {
background: var(--primary-color);
color: var(--bg-primary);
border-color: var(--primary-color);
}
.intro-btn.primary:hover {
background: var(--primary-hover);
border-color: var(--primary-hover);
}
/* Tutorial Navigation Bar */
.tutorial-nav {
position: fixed;
top: 0;
left: 0;
right: 0;
background: var(--bg-tertiary);
border-bottom: 1px solid var(--primary-color);
z-index: 1000;
transition: transform 0.3s;
}
.tutorial-nav.hidden {
transform: translateY(-100%);
}
.tutorial-nav-content {
display: flex;
align-items: center;
justify-content: space-between;
padding: 16px 24px;
}
.tutorial-left {
flex: 1;
}
.tutorial-step-title {
display: flex;
align-items: center;
gap: 16px;
margin-bottom: 8px;
}
.tutorial-step-title span:first-child {
color: var(--text-secondary);
font-size: 12px;
text-transform: uppercase;
}
.tutorial-step-title span:last-child {
color: var(--primary-color);
font-weight: 600;
font-size: 16px;
}
.tutorial-description {
color: var(--text-primary);
margin: 0;
font-size: 14px;
max-width: 600px;
}
.tutorial-right {
display: flex;
align-items: center;
}
.tutorial-progress-bar {
height: 3px;
background: var(--bg-secondary);
position: absolute;
bottom: 0;
left: 0;
right: 0;
}
.tutorial-progress-bar .progress-fill {
height: 100%;
background: var(--primary-color);
transition: width 0.3s;
}
/* Adjust app container when tutorial is active */
.app-container.tutorial-active {
padding-top: 80px;
}
.tutorial-controls {
display: flex;
gap: 12px;
}
.nav-btn {
padding: 8px 16px;
background: var(--bg-secondary);
color: var(--text-primary);
border: 1px solid var(--border-color);
border-radius: 4px;
font-family: inherit;
font-size: 13px;
cursor: pointer;
transition: all 0.2s;
}
.nav-btn:hover:not(:disabled) {
background: var(--bg-primary);
border-color: var(--border-hover);
}
.nav-btn:disabled {
opacity: 0.5;
cursor: not-allowed;
}
.nav-btn.primary {
background: var(--primary-color);
color: var(--bg-primary);
border-color: var(--primary-color);
}
.nav-btn.primary:hover {
background: var(--primary-hover);
border-color: var(--primary-hover);
}
.exit-btn {
width: 32px;
height: 32px;
background: transparent;
color: var(--text-secondary);
border: none;
font-size: 20px;
cursor: pointer;
border-radius: 4px;
transition: all 0.2s;
margin-left: 16px;
}
.exit-btn:hover {
background: var(--bg-secondary);
color: var(--text-primary);
}
/* Fullscreen Mode */
.playground-panel.fullscreen {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
z-index: 1500;
}
/* Animations */
@keyframes pulse {
0%, 100% { opacity: 1; }
50% { opacity: 0.5; }
}
/* Scrollbar Styling */
::-webkit-scrollbar {
width: 10px;
height: 10px;
}
::-webkit-scrollbar-track {
background: var(--bg-secondary);
}
::-webkit-scrollbar-thumb {
background: var(--border-color);
border-radius: 5px;
}
::-webkit-scrollbar-thumb:hover {
background: var(--border-hover);
}
/* Responsive */
@media (max-width: 768px) {
.app-container {
flex-direction: column;
}
.editor-panel,
.playground-panel {
min-width: auto;
width: 100%;
}
.editor-panel {
border-right: none;
border-bottom: 1px solid var(--border-color);
}
.output-section {
height: 200px;
}
}
/* ================================================================
Recording Timeline Styles
================================================================ */
.action-btn.record {
background: var(--bg-tertiary);
border-color: var(--error-color);
}
.action-btn.record:hover {
background: var(--error-color);
border-color: var(--error-color);
}
.action-btn.record.recording {
background: var(--error-color);
animation: pulse 1.5s infinite;
}
.action-btn.record.recording .icon {
animation: blink 1s infinite;
}
@keyframes pulse {
0%, 100% { opacity: 1; }
50% { opacity: 0.8; }
}
@keyframes blink {
0%, 100% { opacity: 1; }
50% { opacity: 0.3; }
}
.editor-container {
flex: 1;
display: flex;
flex-direction: column;
overflow: hidden;
}
#editor-view,
#timeline-view {
flex: 1;
display: flex;
flex-direction: column;
overflow: hidden;
}
.recording-timeline {
background: var(--bg-secondary);
display: flex;
flex-direction: column;
height: 100%;
}
.timeline-header {
display: flex;
justify-content: space-between;
align-items: center;
padding: 10px 15px;
border-bottom: 1px solid var(--border-color);
background: var(--bg-tertiary);
}
.timeline-header h3 {
font-size: 14px;
font-weight: 600;
color: var(--text-primary);
margin: 0;
}
.timeline-actions {
display: flex;
gap: 8px;
}
.timeline-events {
flex: 1;
overflow-y: auto;
padding: 10px;
}
.timeline-event {
display: flex;
align-items: center;
padding: 8px 10px;
margin-bottom: 6px;
background: var(--bg-tertiary);
border: 1px solid var(--border-color);
border-radius: 4px;
transition: all 0.2s;
cursor: pointer;
}
.timeline-event:hover {
border-color: var(--border-hover);
background: var(--code-bg);
}
.timeline-event.selected {
border-color: var(--primary-color);
background: rgba(15, 187, 170, 0.1);
}
.event-checkbox {
margin-right: 10px;
width: 16px;
height: 16px;
cursor: pointer;
}
.event-time {
font-size: 11px;
color: var(--text-muted);
margin-right: 10px;
font-family: 'Dank Mono', monospace;
min-width: 45px;
}
.event-command {
flex: 1;
font-family: 'Dank Mono', monospace;
font-size: 13px;
color: var(--text-primary);
}
.event-command .cmd-name {
color: var(--primary-color);
font-weight: 600;
}
.event-command .cmd-selector {
color: var(--info-color);
}
.event-command .cmd-value {
color: var(--warning-color);
}
.event-command .cmd-detail {
color: var(--text-secondary);
font-size: 11px;
margin-left: 5px;
}
.event-edit {
margin-left: 10px;
padding: 2px 8px;
font-size: 11px;
background: var(--bg-secondary);
border: 1px solid var(--border-color);
color: var(--text-secondary);
cursor: pointer;
border-radius: 3px;
transition: all 0.2s;
}
.event-edit:hover {
border-color: var(--primary-color);
color: var(--primary-color);
}
/* Event Editor Modal */
.modal-overlay {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: var(--modal-overlay);
z-index: 999;
}
.event-editor-modal {
position: fixed;
top: 50%;
left: 50%;
transform: translate(-50%, -50%);
background: var(--bg-secondary);
border: 1px solid var(--border-color);
border-radius: 8px;
padding: 20px;
z-index: 1000;
min-width: 400px;
}
.event-editor-modal h4 {
margin: 0 0 15px 0;
color: var(--text-primary);
font-family: 'Dank Mono', monospace;
}
.editor-field {
margin-bottom: 15px;
}
.editor-field label {
display: block;
margin-bottom: 5px;
font-size: 12px;
color: var(--text-secondary);
font-family: 'Dank Mono', monospace;
}
.editor-field input,
.editor-field select {
width: 100%;
padding: 8px;
background: var(--bg-tertiary);
border: 1px solid var(--border-color);
color: var(--text-primary);
border-radius: 4px;
font-family: 'Dank Mono', monospace;
font-size: 13px;
}
.editor-field input:focus,
.editor-field select:focus {
outline: none;
border-color: var(--primary-color);
}
.editor-actions {
display: flex;
justify-content: flex-end;
gap: 10px;
margin-top: 20px;
}
/* Blockly Button */
#blockly-btn .icon {
font-size: 16px;
}
/* Hidden State */
.hidden {
display: none !important;
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,591 +0,0 @@
// Blockly Manager for C4A-Script
// Handles Blockly workspace, code generation, and synchronization with text editor
class BlocklyManager {
constructor(tutorialApp) {
this.app = tutorialApp;
this.workspace = null;
this.isUpdating = false; // Prevent circular updates
this.blocklyVisible = false;
this.toolboxXml = this.generateToolbox();
this.init();
}
init() {
this.setupBlocklyContainer();
this.initializeWorkspace();
this.setupEventHandlers();
this.setupSynchronization();
}
setupBlocklyContainer() {
// Create blockly container div
const editorContainer = document.querySelector('.editor-container');
const blocklyDiv = document.createElement('div');
blocklyDiv.id = 'blockly-view';
blocklyDiv.className = 'blockly-workspace hidden';
blocklyDiv.style.height = '100%';
blocklyDiv.style.width = '100%';
editorContainer.appendChild(blocklyDiv);
}
generateToolbox() {
return `
<xml id="toolbox" style="display: none">
<category name="Navigation" colour="${BlockColors.NAVIGATION}">
<block type="c4a_go"></block>
<block type="c4a_reload"></block>
<block type="c4a_back"></block>
<block type="c4a_forward"></block>
</category>
<category name="Wait" colour="${BlockColors.WAIT}">
<block type="c4a_wait_time">
<field name="SECONDS">3</field>
</block>
<block type="c4a_wait_selector">
<field name="SELECTOR">#content</field>
<field name="TIMEOUT">10</field>
</block>
<block type="c4a_wait_text">
<field name="TEXT">Loading complete</field>
<field name="TIMEOUT">5</field>
</block>
</category>
<category name="Mouse Actions" colour="${BlockColors.ACTIONS}">
<block type="c4a_click">
<field name="SELECTOR">button.submit</field>
</block>
<block type="c4a_click_xy"></block>
<block type="c4a_double_click"></block>
<block type="c4a_right_click"></block>
<block type="c4a_move"></block>
<block type="c4a_drag"></block>
<block type="c4a_scroll">
<field name="DIRECTION">DOWN</field>
<field name="AMOUNT">500</field>
</block>
</category>
<category name="Keyboard" colour="${BlockColors.KEYBOARD}">
<block type="c4a_type">
<field name="TEXT">hello@example.com</field>
</block>
<block type="c4a_type_var">
<field name="VAR">email</field>
</block>
<block type="c4a_clear"></block>
<block type="c4a_set">
<field name="SELECTOR">#email</field>
<field name="VALUE">user@example.com</field>
</block>
<block type="c4a_press">
<field name="KEY">Tab</field>
</block>
<block type="c4a_key_down">
<field name="KEY">Shift</field>
</block>
<block type="c4a_key_up">
<field name="KEY">Shift</field>
</block>
</category>
<category name="Control Flow" colour="${BlockColors.CONTROL}">
<block type="c4a_if_exists">
<field name="SELECTOR">.cookie-banner</field>
</block>
<block type="c4a_if_exists_else">
<field name="SELECTOR">#user</field>
</block>
<block type="c4a_if_not_exists">
<field name="SELECTOR">.modal</field>
</block>
<block type="c4a_if_js">
<field name="CONDITION">window.innerWidth < 768</field>
</block>
<block type="c4a_repeat_times">
<field name="TIMES">5</field>
</block>
<block type="c4a_repeat_while">
<field name="CONDITION">document.querySelector('.load-more')</field>
</block>
</category>
<category name="Variables" colour="${BlockColors.VARIABLES}">
<block type="c4a_setvar">
<field name="NAME">username</field>
<field name="VALUE">john@example.com</field>
</block>
<block type="c4a_eval">
<field name="CODE">console.log('Hello')</field>
</block>
</category>
<category name="Procedures" colour="${BlockColors.PROCEDURES}">
<block type="c4a_proc_def">
<field name="NAME">login</field>
</block>
<block type="c4a_proc_call">
<field name="NAME">login</field>
</block>
</category>
<category name="Comments" colour="#9E9E9E">
<block type="c4a_comment">
<field name="TEXT">Add comment here</field>
</block>
</category>
</xml>`;
}
initializeWorkspace() {
const blocklyDiv = document.getElementById('blockly-view');
// Dark theme configuration
const theme = Blockly.Theme.defineTheme('c4a-dark', {
'base': Blockly.Themes.Classic,
'componentStyles': {
'workspaceBackgroundColour': '#0e0e10',
'toolboxBackgroundColour': '#1a1a1b',
'toolboxForegroundColour': '#e0e0e0',
'flyoutBackgroundColour': '#1a1a1b',
'flyoutForegroundColour': '#e0e0e0',
'flyoutOpacity': 0.9,
'scrollbarColour': '#2a2a2c',
'scrollbarOpacity': 0.5,
'insertionMarkerColour': '#0fbbaa',
'insertionMarkerOpacity': 0.3,
'markerColour': '#0fbbaa',
'cursorColour': '#0fbbaa',
'selectedGlowColour': '#0fbbaa',
'selectedGlowOpacity': 0.4,
'replacementGlowColour': '#0fbbaa',
'replacementGlowOpacity': 0.5
},
'fontStyle': {
'family': 'Dank Mono, Monaco, Consolas, monospace',
'weight': 'normal',
'size': 13
}
});
this.workspace = Blockly.inject(blocklyDiv, {
toolbox: this.toolboxXml,
theme: theme,
grid: {
spacing: 20,
length: 3,
colour: '#2a2a2c',
snap: true
},
zoom: {
controls: true,
wheel: true,
startScale: 1.0,
maxScale: 3,
minScale: 0.3,
scaleSpeed: 1.2
},
trashcan: true,
sounds: false,
media: 'https://unpkg.com/blockly/media/'
});
// Add workspace change listener
this.workspace.addChangeListener((event) => {
if (!this.isUpdating && event.type !== Blockly.Events.UI) {
this.syncBlocksToCode();
}
});
}
setupEventHandlers() {
// Add blockly toggle button
const headerActions = document.querySelector('.editor-panel .header-actions');
const blocklyBtn = document.createElement('button');
blocklyBtn.id = 'blockly-btn';
blocklyBtn.className = 'action-btn';
blocklyBtn.title = 'Toggle Blockly Mode';
blocklyBtn.innerHTML = '<span class="icon">🧩</span>';
// Insert before the Run button
const runBtn = document.getElementById('run-btn');
headerActions.insertBefore(blocklyBtn, runBtn);
blocklyBtn.addEventListener('click', () => this.toggleBlocklyView());
}
setupSynchronization() {
// Listen to CodeMirror changes
this.app.editor.on('change', (instance, changeObj) => {
if (!this.isUpdating && this.blocklyVisible && changeObj.origin !== 'setValue') {
this.syncCodeToBlocks();
}
});
}
toggleBlocklyView() {
const editorView = document.getElementById('editor-view');
const blocklyView = document.getElementById('blockly-view');
const timelineView = document.getElementById('timeline-view');
const blocklyBtn = document.getElementById('blockly-btn');
this.blocklyVisible = !this.blocklyVisible;
if (this.blocklyVisible) {
// Show Blockly
editorView.classList.add('hidden');
timelineView.classList.add('hidden');
blocklyView.classList.remove('hidden');
blocklyBtn.classList.add('active');
// Resize workspace
Blockly.svgResize(this.workspace);
// Sync current code to blocks
this.syncCodeToBlocks();
} else {
// Show editor
blocklyView.classList.add('hidden');
editorView.classList.remove('hidden');
blocklyBtn.classList.remove('active');
// Refresh CodeMirror
setTimeout(() => this.app.editor.refresh(), 100);
}
}
syncBlocksToCode() {
if (this.isUpdating) return;
try {
this.isUpdating = true;
// Generate C4A-Script from blocks using our custom generator
if (typeof c4aGenerator !== 'undefined') {
const code = c4aGenerator.workspaceToCode(this.workspace);
// Process the code to maintain proper formatting
const lines = code.split('\n');
const formattedLines = [];
let lastWasComment = false;
for (let i = 0; i < lines.length; i++) {
const line = lines[i].trim();
if (!line) continue;
const isComment = line.startsWith('#');
// Add blank line when transitioning between comments and commands
if (formattedLines.length > 0 && lastWasComment !== isComment) {
formattedLines.push('');
}
formattedLines.push(line);
lastWasComment = isComment;
}
const cleanCode = formattedLines.join('\n');
// Update CodeMirror
this.app.editor.setValue(cleanCode);
}
} catch (error) {
console.error('Error syncing blocks to code:', error);
} finally {
this.isUpdating = false;
}
}
syncCodeToBlocks() {
if (this.isUpdating) return;
try {
this.isUpdating = true;
// Clear workspace
this.workspace.clear();
// Parse C4A-Script and generate blocks
const code = this.app.editor.getValue();
const blocks = this.parseC4AToBlocks(code);
if (blocks) {
Blockly.Xml.domToWorkspace(blocks, this.workspace);
}
} catch (error) {
console.error('Error syncing code to blocks:', error);
// Show error in console
this.app.addConsoleMessage(`Blockly sync error: ${error.message}`, 'warning');
} finally {
this.isUpdating = false;
}
}
parseC4AToBlocks(code) {
const lines = code.split('\n');
const xml = document.createElement('xml');
let yPos = 20;
let previousBlock = null;
let rootBlock = null;
for (let i = 0; i < lines.length; i++) {
const line = lines[i].trim();
// Skip empty lines
if (!line) continue;
// Handle comments
if (line.startsWith('#')) {
const commentBlock = this.parseLineToBlock(line, i, lines);
if (commentBlock) {
if (previousBlock) {
// Connect to previous block
const next = document.createElement('next');
next.appendChild(commentBlock);
previousBlock.appendChild(next);
} else {
// First block - set position
commentBlock.setAttribute('x', 20);
commentBlock.setAttribute('y', yPos);
xml.appendChild(commentBlock);
rootBlock = commentBlock;
yPos += 60;
}
previousBlock = commentBlock;
}
continue;
}
const block = this.parseLineToBlock(line, i, lines);
if (block) {
if (previousBlock) {
// Connect to previous block using <next>
const next = document.createElement('next');
next.appendChild(block);
previousBlock.appendChild(next);
} else {
// First block - set position
block.setAttribute('x', 20);
block.setAttribute('y', yPos);
xml.appendChild(block);
rootBlock = block;
yPos += 60;
}
previousBlock = block;
}
}
return xml;
}
parseLineToBlock(line, index, allLines) {
// Navigation commands
if (line.startsWith('GO ')) {
const url = line.substring(3).trim();
return this.createBlock('c4a_go', { 'URL': url });
}
if (line === 'RELOAD') {
return this.createBlock('c4a_reload');
}
if (line === 'BACK') {
return this.createBlock('c4a_back');
}
if (line === 'FORWARD') {
return this.createBlock('c4a_forward');
}
// Wait commands
if (line.startsWith('WAIT ')) {
const parts = line.substring(5).trim();
// Check if it's just a number (wait time)
if (/^\d+(\.\d+)?$/.test(parts)) {
return this.createBlock('c4a_wait_time', { 'SECONDS': parts });
}
// Check for selector wait
const selectorMatch = parts.match(/^`([^`]+)`\s+(\d+)$/);
if (selectorMatch) {
return this.createBlock('c4a_wait_selector', {
'SELECTOR': selectorMatch[1],
'TIMEOUT': selectorMatch[2]
});
}
// Check for text wait
const textMatch = parts.match(/^"([^"]+)"\s+(\d+)$/);
if (textMatch) {
return this.createBlock('c4a_wait_text', {
'TEXT': textMatch[1],
'TIMEOUT': textMatch[2]
});
}
}
// Click commands
if (line.startsWith('CLICK ')) {
const target = line.substring(6).trim();
// Check for coordinates
const coordMatch = target.match(/^(\d+)\s+(\d+)$/);
if (coordMatch) {
return this.createBlock('c4a_click_xy', {
'X': coordMatch[1],
'Y': coordMatch[2]
});
}
// Selector click
const selectorMatch = target.match(/^`([^`]+)`$/);
if (selectorMatch) {
return this.createBlock('c4a_click', {
'SELECTOR': selectorMatch[1]
});
}
}
// Other mouse actions
if (line.startsWith('DOUBLE_CLICK ')) {
const selector = line.substring(13).trim().match(/^`([^`]+)`$/);
if (selector) {
return this.createBlock('c4a_double_click', {
'SELECTOR': selector[1]
});
}
}
if (line.startsWith('RIGHT_CLICK ')) {
const selector = line.substring(12).trim().match(/^`([^`]+)`$/);
if (selector) {
return this.createBlock('c4a_right_click', {
'SELECTOR': selector[1]
});
}
}
// Scroll
if (line.startsWith('SCROLL ')) {
const match = line.match(/^SCROLL\s+(UP|DOWN|LEFT|RIGHT)(?:\s+(\d+))?$/);
if (match) {
return this.createBlock('c4a_scroll', {
'DIRECTION': match[1],
'AMOUNT': match[2] || '500'
});
}
}
// Type commands
if (line.startsWith('TYPE ')) {
const content = line.substring(5).trim();
// Variable type
if (content.startsWith('$')) {
return this.createBlock('c4a_type_var', {
'VAR': content.substring(1)
});
}
// Text type
const textMatch = content.match(/^"([^"]*)"$/);
if (textMatch) {
return this.createBlock('c4a_type', {
'TEXT': textMatch[1]
});
}
}
// SET command
if (line.startsWith('SET ')) {
const match = line.match(/^SET\s+`([^`]+)`\s+"([^"]*)"$/);
if (match) {
return this.createBlock('c4a_set', {
'SELECTOR': match[1],
'VALUE': match[2]
});
}
}
// CLEAR command
if (line.startsWith('CLEAR ')) {
const match = line.match(/^CLEAR\s+`([^`]+)`$/);
if (match) {
return this.createBlock('c4a_clear', {
'SELECTOR': match[1]
});
}
}
// SETVAR command
if (line.startsWith('SETVAR ')) {
const match = line.match(/^SETVAR\s+(\w+)\s*=\s*"([^"]*)"$/);
if (match) {
return this.createBlock('c4a_setvar', {
'NAME': match[1],
'VALUE': match[2]
});
}
}
// IF commands (simplified - only single line)
if (line.startsWith('IF ')) {
// IF EXISTS
const existsMatch = line.match(/^IF\s+\(EXISTS\s+`([^`]+)`\)\s+THEN\s+(.+?)(?:\s+ELSE\s+(.+))?$/);
if (existsMatch) {
if (existsMatch[3]) {
// Has ELSE
const block = this.createBlock('c4a_if_exists_else', {
'SELECTOR': existsMatch[1]
});
// Parse then and else commands - simplified for now
return block;
} else {
// No ELSE
const block = this.createBlock('c4a_if_exists', {
'SELECTOR': existsMatch[1]
});
return block;
}
}
// IF NOT EXISTS
const notExistsMatch = line.match(/^IF\s+\(NOT\s+EXISTS\s+`([^`]+)`\)\s+THEN\s+(.+)$/);
if (notExistsMatch) {
const block = this.createBlock('c4a_if_not_exists', {
'SELECTOR': notExistsMatch[1]
});
return block;
}
}
// Comments
if (line.startsWith('#')) {
return this.createBlock('c4a_comment', {
'TEXT': line.substring(1).trim()
});
}
// If we can't parse it, return null
return null;
}
createBlock(type, fields = {}) {
const block = document.createElement('block');
block.setAttribute('type', type);
// Add fields
for (const [name, value] of Object.entries(fields)) {
const field = document.createElement('field');
field.setAttribute('name', name);
field.textContent = value;
block.appendChild(field);
}
return block;
}
}

View File

@@ -1,238 +0,0 @@
/* Blockly Theme CSS for C4A-Script */
/* Blockly workspace container */
.blockly-workspace {
position: relative;
width: 100%;
height: 100%;
background: var(--bg-primary);
}
/* Blockly button active state */
#blockly-btn.active {
background: var(--primary-color);
color: var(--bg-primary);
border-color: var(--primary-color);
}
#blockly-btn.active:hover {
background: var(--primary-hover);
border-color: var(--primary-hover);
}
/* Override Blockly's default styles for dark theme */
.blocklyToolboxDiv {
background-color: var(--bg-tertiary) !important;
border-right: 1px solid var(--border-color) !important;
}
.blocklyFlyout {
background-color: var(--bg-secondary) !important;
}
.blocklyFlyoutBackground {
fill: var(--bg-secondary) !important;
}
.blocklyMainBackground {
stroke: none !important;
}
.blocklyTreeRow {
color: var(--text-primary) !important;
font-family: 'Dank Mono', monospace !important;
padding: 4px 16px !important;
margin: 2px 0 !important;
}
.blocklyTreeRow:hover {
background-color: var(--bg-secondary) !important;
}
.blocklyTreeSelected {
background-color: var(--primary-dim) !important;
}
.blocklyTreeLabel {
cursor: pointer;
}
/* Blockly scrollbars */
.blocklyScrollbarHorizontal,
.blocklyScrollbarVertical {
background-color: transparent !important;
}
.blocklyScrollbarHandle {
fill: var(--border-color) !important;
opacity: 0.5 !important;
}
.blocklyScrollbarHandle:hover {
fill: var(--border-hover) !important;
opacity: 0.8 !important;
}
/* Blockly zoom controls */
.blocklyZoom > image {
opacity: 0.6;
}
.blocklyZoom > image:hover {
opacity: 1;
}
/* Blockly trash can */
.blocklyTrash {
opacity: 0.6;
}
.blocklyTrash:hover {
opacity: 1;
}
/* Blockly context menus */
.blocklyContextMenu {
background-color: var(--bg-tertiary) !important;
border: 1px solid var(--border-color) !important;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.3) !important;
}
.blocklyMenuItem {
color: var(--text-primary) !important;
font-family: 'Dank Mono', monospace !important;
}
.blocklyMenuItemDisabled {
color: var(--text-muted) !important;
}
.blocklyMenuItem:hover {
background-color: var(--bg-secondary) !important;
}
/* Blockly text inputs */
.blocklyHtmlInput {
background-color: var(--bg-tertiary) !important;
color: var(--text-primary) !important;
border: 1px solid var(--border-color) !important;
font-family: 'Dank Mono', monospace !important;
font-size: 13px !important;
padding: 4px 8px !important;
}
.blocklyHtmlInput:focus {
border-color: var(--primary-color) !important;
outline: none !important;
}
/* Blockly dropdowns */
.blocklyDropDownDiv {
background-color: var(--bg-tertiary) !important;
border: 1px solid var(--border-color) !important;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.3) !important;
}
.blocklyDropDownContent {
color: var(--text-primary) !important;
}
.blocklyDropDownDiv .goog-menuitem {
color: var(--text-primary) !important;
font-family: 'Dank Mono', monospace !important;
padding: 4px 16px !important;
}
.blocklyDropDownDiv .goog-menuitem-highlight,
.blocklyDropDownDiv .goog-menuitem-hover {
background-color: var(--bg-secondary) !important;
}
/* Custom block colors are defined in the block definitions */
/* Block text styling */
.blocklyText {
fill: #ffffff !important;
font-family: 'Dank Mono', monospace !important;
font-size: 13px !important;
}
.blocklyEditableText > .blocklyText {
fill: #ffffff !important;
}
.blocklyEditableText:hover > rect {
stroke: var(--primary-color) !important;
stroke-width: 2px !important;
}
/* Improve visibility of connection highlights */
.blocklyHighlightedConnectionPath {
stroke: var(--primary-color) !important;
stroke-width: 4px !important;
}
.blocklyInsertionMarker > .blocklyPath {
fill-opacity: 0.3 !important;
stroke-opacity: 0.6 !important;
}
/* Workspace grid pattern */
.blocklyWorkspace > .blocklyBlockCanvas > .blocklyGridCanvas {
opacity: 0.1;
}
/* Smooth transitions */
.blocklyDraggable {
transition: transform 0.1s ease;
}
/* Field labels */
.blocklyFieldLabel {
font-weight: normal !important;
}
/* Comment blocks styling */
.blocklyCommentText {
font-style: italic !important;
}
/* Make comment blocks slightly transparent */
g[data-category="Comments"] .blocklyPath {
fill-opacity: 0.8 !important;
}
/* Better visibility for disabled blocks */
.blocklyDisabled > .blocklyPath {
fill-opacity: 0.3 !important;
}
.blocklyDisabled > .blocklyText {
fill-opacity: 0.5 !important;
}
/* Warning and error text */
.blocklyWarningText,
.blocklyErrorText {
font-family: 'Dank Mono', monospace !important;
font-size: 12px !important;
}
/* Workspace scrollbar improvement for dark theme */
::-webkit-scrollbar {
width: 10px;
height: 10px;
}
::-webkit-scrollbar-track {
background: var(--bg-secondary);
}
::-webkit-scrollbar-thumb {
background: var(--border-color);
border-radius: 5px;
}
::-webkit-scrollbar-thumb:hover {
background: var(--border-hover);
}

View File

@@ -1,549 +0,0 @@
// C4A-Script Blockly Block Definitions
// This file defines all custom blocks for C4A-Script commands
// Color scheme for different block categories
const BlockColors = {
NAVIGATION: '#1E88E5', // Blue
ACTIONS: '#43A047', // Green
CONTROL: '#FB8C00', // Orange
VARIABLES: '#8E24AA', // Purple
WAIT: '#E53935', // Red
KEYBOARD: '#00ACC1', // Cyan
PROCEDURES: '#6A1B9A' // Deep Purple
};
// Helper to create selector input with backticks
Blockly.Blocks['c4a_selector_input'] = {
init: function() {
this.appendDummyInput()
.appendField("`")
.appendField(new Blockly.FieldTextInput("selector"), "SELECTOR")
.appendField("`");
this.setOutput(true, "Selector");
this.setColour(BlockColors.ACTIONS);
this.setTooltip("CSS selector for element");
}
};
// ============================================
// NAVIGATION BLOCKS
// ============================================
Blockly.Blocks['c4a_go'] = {
init: function() {
this.appendDummyInput()
.appendField("GO")
.appendField(new Blockly.FieldTextInput("https://example.com"), "URL");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.NAVIGATION);
this.setTooltip("Navigate to URL");
}
};
Blockly.Blocks['c4a_reload'] = {
init: function() {
this.appendDummyInput()
.appendField("RELOAD");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.NAVIGATION);
this.setTooltip("Reload current page");
}
};
Blockly.Blocks['c4a_back'] = {
init: function() {
this.appendDummyInput()
.appendField("BACK");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.NAVIGATION);
this.setTooltip("Go back in browser history");
}
};
Blockly.Blocks['c4a_forward'] = {
init: function() {
this.appendDummyInput()
.appendField("FORWARD");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.NAVIGATION);
this.setTooltip("Go forward in browser history");
}
};
// ============================================
// WAIT BLOCKS
// ============================================
Blockly.Blocks['c4a_wait_time'] = {
init: function() {
this.appendDummyInput()
.appendField("WAIT")
.appendField(new Blockly.FieldNumber(1, 0), "SECONDS")
.appendField("seconds");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.WAIT);
this.setTooltip("Wait for specified seconds");
}
};
Blockly.Blocks['c4a_wait_selector'] = {
init: function() {
this.appendDummyInput()
.appendField("WAIT for")
.appendField("`")
.appendField(new Blockly.FieldTextInput("selector"), "SELECTOR")
.appendField("`")
.appendField("max")
.appendField(new Blockly.FieldNumber(10, 1), "TIMEOUT")
.appendField("sec");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.WAIT);
this.setTooltip("Wait for element to appear");
}
};
Blockly.Blocks['c4a_wait_text'] = {
init: function() {
this.appendDummyInput()
.appendField("WAIT for text")
.appendField(new Blockly.FieldTextInput("Loading complete"), "TEXT")
.appendField("max")
.appendField(new Blockly.FieldNumber(5, 1), "TIMEOUT")
.appendField("sec");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.WAIT);
this.setTooltip("Wait for text to appear on page");
}
};
// ============================================
// MOUSE ACTION BLOCKS
// ============================================
Blockly.Blocks['c4a_click'] = {
init: function() {
this.appendDummyInput()
.appendField("CLICK")
.appendField("`")
.appendField(new Blockly.FieldTextInput("button"), "SELECTOR")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Click on element");
}
};
Blockly.Blocks['c4a_click_xy'] = {
init: function() {
this.appendDummyInput()
.appendField("CLICK at")
.appendField("X:")
.appendField(new Blockly.FieldNumber(100, 0), "X")
.appendField("Y:")
.appendField(new Blockly.FieldNumber(100, 0), "Y");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Click at coordinates");
}
};
Blockly.Blocks['c4a_double_click'] = {
init: function() {
this.appendDummyInput()
.appendField("DOUBLE_CLICK")
.appendField("`")
.appendField(new Blockly.FieldTextInput(".item"), "SELECTOR")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Double click on element");
}
};
Blockly.Blocks['c4a_right_click'] = {
init: function() {
this.appendDummyInput()
.appendField("RIGHT_CLICK")
.appendField("`")
.appendField(new Blockly.FieldTextInput("#menu"), "SELECTOR")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Right click on element");
}
};
Blockly.Blocks['c4a_move'] = {
init: function() {
this.appendDummyInput()
.appendField("MOVE to")
.appendField("X:")
.appendField(new Blockly.FieldNumber(500, 0), "X")
.appendField("Y:")
.appendField(new Blockly.FieldNumber(300, 0), "Y");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Move mouse to position");
}
};
Blockly.Blocks['c4a_drag'] = {
init: function() {
this.appendDummyInput()
.appendField("DRAG from")
.appendField("X:")
.appendField(new Blockly.FieldNumber(100, 0), "X1")
.appendField("Y:")
.appendField(new Blockly.FieldNumber(100, 0), "Y1");
this.appendDummyInput()
.appendField("to")
.appendField("X:")
.appendField(new Blockly.FieldNumber(500, 0), "X2")
.appendField("Y:")
.appendField(new Blockly.FieldNumber(300, 0), "Y2");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Drag from one point to another");
}
};
Blockly.Blocks['c4a_scroll'] = {
init: function() {
this.appendDummyInput()
.appendField("SCROLL")
.appendField(new Blockly.FieldDropdown([
["DOWN", "DOWN"],
["UP", "UP"],
["LEFT", "LEFT"],
["RIGHT", "RIGHT"]
]), "DIRECTION")
.appendField(new Blockly.FieldNumber(500, 0), "AMOUNT")
.appendField("pixels");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.ACTIONS);
this.setTooltip("Scroll in direction");
}
};
// ============================================
// KEYBOARD BLOCKS
// ============================================
Blockly.Blocks['c4a_type'] = {
init: function() {
this.appendDummyInput()
.appendField("TYPE")
.appendField(new Blockly.FieldTextInput("text to type"), "TEXT");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Type text");
}
};
Blockly.Blocks['c4a_type_var'] = {
init: function() {
this.appendDummyInput()
.appendField("TYPE")
.appendField("$")
.appendField(new Blockly.FieldTextInput("variable"), "VAR");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Type variable value");
}
};
Blockly.Blocks['c4a_clear'] = {
init: function() {
this.appendDummyInput()
.appendField("CLEAR")
.appendField("`")
.appendField(new Blockly.FieldTextInput("input"), "SELECTOR")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Clear input field");
}
};
Blockly.Blocks['c4a_set'] = {
init: function() {
this.appendDummyInput()
.appendField("SET")
.appendField("`")
.appendField(new Blockly.FieldTextInput("#input"), "SELECTOR")
.appendField("`")
.appendField("to")
.appendField(new Blockly.FieldTextInput("value"), "VALUE");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Set input field value");
}
};
Blockly.Blocks['c4a_press'] = {
init: function() {
this.appendDummyInput()
.appendField("PRESS")
.appendField(new Blockly.FieldDropdown([
["Tab", "Tab"],
["Enter", "Enter"],
["Escape", "Escape"],
["Space", "Space"],
["ArrowUp", "ArrowUp"],
["ArrowDown", "ArrowDown"],
["ArrowLeft", "ArrowLeft"],
["ArrowRight", "ArrowRight"],
["Delete", "Delete"],
["Backspace", "Backspace"]
]), "KEY");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Press and release key");
}
};
Blockly.Blocks['c4a_key_down'] = {
init: function() {
this.appendDummyInput()
.appendField("KEY_DOWN")
.appendField(new Blockly.FieldDropdown([
["Shift", "Shift"],
["Control", "Control"],
["Alt", "Alt"],
["Meta", "Meta"]
]), "KEY");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Hold key down");
}
};
Blockly.Blocks['c4a_key_up'] = {
init: function() {
this.appendDummyInput()
.appendField("KEY_UP")
.appendField(new Blockly.FieldDropdown([
["Shift", "Shift"],
["Control", "Control"],
["Alt", "Alt"],
["Meta", "Meta"]
]), "KEY");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.KEYBOARD);
this.setTooltip("Release key");
}
};
// ============================================
// CONTROL FLOW BLOCKS
// ============================================
Blockly.Blocks['c4a_if_exists'] = {
init: function() {
this.appendDummyInput()
.appendField("IF EXISTS")
.appendField("`")
.appendField(new Blockly.FieldTextInput(".element"), "SELECTOR")
.appendField("`")
.appendField("THEN");
this.appendStatementInput("THEN")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("If element exists, then do something");
}
};
Blockly.Blocks['c4a_if_exists_else'] = {
init: function() {
this.appendDummyInput()
.appendField("IF EXISTS")
.appendField("`")
.appendField(new Blockly.FieldTextInput(".element"), "SELECTOR")
.appendField("`")
.appendField("THEN");
this.appendStatementInput("THEN")
.setCheck(null);
this.appendDummyInput()
.appendField("ELSE");
this.appendStatementInput("ELSE")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("If element exists, then do something, else do something else");
}
};
Blockly.Blocks['c4a_if_not_exists'] = {
init: function() {
this.appendDummyInput()
.appendField("IF NOT EXISTS")
.appendField("`")
.appendField(new Blockly.FieldTextInput(".element"), "SELECTOR")
.appendField("`")
.appendField("THEN");
this.appendStatementInput("THEN")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("If element does not exist, then do something");
}
};
Blockly.Blocks['c4a_if_js'] = {
init: function() {
this.appendDummyInput()
.appendField("IF")
.appendField("`")
.appendField(new Blockly.FieldTextInput("window.innerWidth < 768"), "CONDITION")
.appendField("`")
.appendField("THEN");
this.appendStatementInput("THEN")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("If JavaScript condition is true");
}
};
Blockly.Blocks['c4a_repeat_times'] = {
init: function() {
this.appendDummyInput()
.appendField("REPEAT")
.appendField(new Blockly.FieldNumber(5, 1), "TIMES")
.appendField("times");
this.appendStatementInput("DO")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("Repeat commands N times");
}
};
Blockly.Blocks['c4a_repeat_while'] = {
init: function() {
this.appendDummyInput()
.appendField("REPEAT WHILE")
.appendField("`")
.appendField(new Blockly.FieldTextInput("document.querySelector('.load-more')"), "CONDITION")
.appendField("`");
this.appendStatementInput("DO")
.setCheck(null);
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.CONTROL);
this.setTooltip("Repeat while condition is true");
}
};
// ============================================
// VARIABLE BLOCKS
// ============================================
Blockly.Blocks['c4a_setvar'] = {
init: function() {
this.appendDummyInput()
.appendField("SETVAR")
.appendField(new Blockly.FieldTextInput("username"), "NAME")
.appendField("=")
.appendField(new Blockly.FieldTextInput("value"), "VALUE");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.VARIABLES);
this.setTooltip("Set variable value");
}
};
// ============================================
// ADVANCED BLOCKS
// ============================================
Blockly.Blocks['c4a_eval'] = {
init: function() {
this.appendDummyInput()
.appendField("EVAL")
.appendField("`")
.appendField(new Blockly.FieldTextInput("console.log('Hello')"), "CODE")
.appendField("`");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.VARIABLES);
this.setTooltip("Execute JavaScript code");
}
};
Blockly.Blocks['c4a_comment'] = {
init: function() {
this.appendDummyInput()
.appendField("#")
.appendField(new Blockly.FieldTextInput("Comment", null, {
spellcheck: false,
class: 'blocklyCommentText'
}), "TEXT");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour("#616161");
this.setTooltip("Add a comment");
this.setStyle('comment_blocks');
}
};
// ============================================
// PROCEDURE BLOCKS
// ============================================
Blockly.Blocks['c4a_proc_def'] = {
init: function() {
this.appendDummyInput()
.appendField("PROC")
.appendField(new Blockly.FieldTextInput("procedure_name"), "NAME");
this.appendStatementInput("BODY")
.setCheck(null);
this.appendDummyInput()
.appendField("ENDPROC");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.PROCEDURES);
this.setTooltip("Define a procedure");
}
};
Blockly.Blocks['c4a_proc_call'] = {
init: function() {
this.appendDummyInput()
.appendField("Call")
.appendField(new Blockly.FieldTextInput("procedure_name"), "NAME");
this.setPreviousStatement(true, null);
this.setNextStatement(true, null);
this.setColour(BlockColors.PROCEDURES);
this.setTooltip("Call a procedure");
}
};
// Code generators have been moved to c4a-generator.js

View File

@@ -1,261 +0,0 @@
// C4A-Script Code Generator for Blockly
// Compatible with latest Blockly API
// Create a custom code generator for C4A-Script
const c4aGenerator = new Blockly.Generator('C4A');
// Helper to get field value with proper escaping
c4aGenerator.getFieldValue = function(block, fieldName) {
return block.getFieldValue(fieldName);
};
// Navigation generators
c4aGenerator.forBlock['c4a_go'] = function(block, generator) {
const url = generator.getFieldValue(block, 'URL');
return `GO ${url}\n`;
};
c4aGenerator.forBlock['c4a_reload'] = function(block, generator) {
return 'RELOAD\n';
};
c4aGenerator.forBlock['c4a_back'] = function(block, generator) {
return 'BACK\n';
};
c4aGenerator.forBlock['c4a_forward'] = function(block, generator) {
return 'FORWARD\n';
};
// Wait generators
c4aGenerator.forBlock['c4a_wait_time'] = function(block, generator) {
const seconds = generator.getFieldValue(block, 'SECONDS');
return `WAIT ${seconds}\n`;
};
c4aGenerator.forBlock['c4a_wait_selector'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const timeout = generator.getFieldValue(block, 'TIMEOUT');
return `WAIT \`${selector}\` ${timeout}\n`;
};
c4aGenerator.forBlock['c4a_wait_text'] = function(block, generator) {
const text = generator.getFieldValue(block, 'TEXT');
const timeout = generator.getFieldValue(block, 'TIMEOUT');
return `WAIT "${text}" ${timeout}\n`;
};
// Mouse action generators
c4aGenerator.forBlock['c4a_click'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
return `CLICK \`${selector}\`\n`;
};
c4aGenerator.forBlock['c4a_click_xy'] = function(block, generator) {
const x = generator.getFieldValue(block, 'X');
const y = generator.getFieldValue(block, 'Y');
return `CLICK ${x} ${y}\n`;
};
c4aGenerator.forBlock['c4a_double_click'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
return `DOUBLE_CLICK \`${selector}\`\n`;
};
c4aGenerator.forBlock['c4a_right_click'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
return `RIGHT_CLICK \`${selector}\`\n`;
};
c4aGenerator.forBlock['c4a_move'] = function(block, generator) {
const x = generator.getFieldValue(block, 'X');
const y = generator.getFieldValue(block, 'Y');
return `MOVE ${x} ${y}\n`;
};
c4aGenerator.forBlock['c4a_drag'] = function(block, generator) {
const x1 = generator.getFieldValue(block, 'X1');
const y1 = generator.getFieldValue(block, 'Y1');
const x2 = generator.getFieldValue(block, 'X2');
const y2 = generator.getFieldValue(block, 'Y2');
return `DRAG ${x1} ${y1} ${x2} ${y2}\n`;
};
c4aGenerator.forBlock['c4a_scroll'] = function(block, generator) {
const direction = generator.getFieldValue(block, 'DIRECTION');
const amount = generator.getFieldValue(block, 'AMOUNT');
return `SCROLL ${direction} ${amount}\n`;
};
// Keyboard generators
c4aGenerator.forBlock['c4a_type'] = function(block, generator) {
const text = generator.getFieldValue(block, 'TEXT');
return `TYPE "${text}"\n`;
};
c4aGenerator.forBlock['c4a_type_var'] = function(block, generator) {
const varName = generator.getFieldValue(block, 'VAR');
return `TYPE $${varName}\n`;
};
c4aGenerator.forBlock['c4a_clear'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
return `CLEAR \`${selector}\`\n`;
};
c4aGenerator.forBlock['c4a_set'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const value = generator.getFieldValue(block, 'VALUE');
return `SET \`${selector}\` "${value}"\n`;
};
c4aGenerator.forBlock['c4a_press'] = function(block, generator) {
const key = generator.getFieldValue(block, 'KEY');
return `PRESS ${key}\n`;
};
c4aGenerator.forBlock['c4a_key_down'] = function(block, generator) {
const key = generator.getFieldValue(block, 'KEY');
return `KEY_DOWN ${key}\n`;
};
c4aGenerator.forBlock['c4a_key_up'] = function(block, generator) {
const key = generator.getFieldValue(block, 'KEY');
return `KEY_UP ${key}\n`;
};
// Control flow generators
c4aGenerator.forBlock['c4a_if_exists'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const thenCode = generator.statementToCode(block, 'THEN').trim();
if (thenCode.includes('\n')) {
// Multi-line then block
const lines = thenCode.split('\n').filter(line => line.trim());
return lines.map(line => `IF (EXISTS \`${selector}\`) THEN ${line}`).join('\n') + '\n';
} else if (thenCode) {
// Single line
return `IF (EXISTS \`${selector}\`) THEN ${thenCode}\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_if_exists_else'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const thenCode = generator.statementToCode(block, 'THEN').trim();
const elseCode = generator.statementToCode(block, 'ELSE').trim();
// For simplicity, only handle single-line then/else
const thenLine = thenCode.split('\n')[0];
const elseLine = elseCode.split('\n')[0];
if (thenLine && elseLine) {
return `IF (EXISTS \`${selector}\`) THEN ${thenLine} ELSE ${elseLine}\n`;
} else if (thenLine) {
return `IF (EXISTS \`${selector}\`) THEN ${thenLine}\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_if_not_exists'] = function(block, generator) {
const selector = generator.getFieldValue(block, 'SELECTOR');
const thenCode = generator.statementToCode(block, 'THEN').trim();
if (thenCode.includes('\n')) {
const lines = thenCode.split('\n').filter(line => line.trim());
return lines.map(line => `IF (NOT EXISTS \`${selector}\`) THEN ${line}`).join('\n') + '\n';
} else if (thenCode) {
return `IF (NOT EXISTS \`${selector}\`) THEN ${thenCode}\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_if_js'] = function(block, generator) {
const condition = generator.getFieldValue(block, 'CONDITION');
const thenCode = generator.statementToCode(block, 'THEN').trim();
if (thenCode.includes('\n')) {
const lines = thenCode.split('\n').filter(line => line.trim());
return lines.map(line => `IF (\`${condition}\`) THEN ${line}`).join('\n') + '\n';
} else if (thenCode) {
return `IF (\`${condition}\`) THEN ${thenCode}\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_repeat_times'] = function(block, generator) {
const times = generator.getFieldValue(block, 'TIMES');
const doCode = generator.statementToCode(block, 'DO').trim();
if (doCode) {
// Get first command for repeat
const firstLine = doCode.split('\n')[0];
return `REPEAT (${firstLine}, ${times})\n`;
}
return '';
};
c4aGenerator.forBlock['c4a_repeat_while'] = function(block, generator) {
const condition = generator.getFieldValue(block, 'CONDITION');
const doCode = generator.statementToCode(block, 'DO').trim();
if (doCode) {
// Get first command for repeat
const firstLine = doCode.split('\n')[0];
return `REPEAT (${firstLine}, \`${condition}\`)\n`;
}
return '';
};
// Variable generators
c4aGenerator.forBlock['c4a_setvar'] = function(block, generator) {
const name = generator.getFieldValue(block, 'NAME');
const value = generator.getFieldValue(block, 'VALUE');
return `SETVAR ${name} = "${value}"\n`;
};
// Advanced generators
c4aGenerator.forBlock['c4a_eval'] = function(block, generator) {
const code = generator.getFieldValue(block, 'CODE');
return `EVAL \`${code}\`\n`;
};
c4aGenerator.forBlock['c4a_comment'] = function(block, generator) {
const text = generator.getFieldValue(block, 'TEXT');
return `# ${text}\n`;
};
// Procedure generators
c4aGenerator.forBlock['c4a_proc_def'] = function(block, generator) {
const name = generator.getFieldValue(block, 'NAME');
const body = generator.statementToCode(block, 'BODY');
return `PROC ${name}\n${body}ENDPROC\n`;
};
c4aGenerator.forBlock['c4a_proc_call'] = function(block, generator) {
const name = generator.getFieldValue(block, 'NAME');
return `${name}\n`;
};
// Override scrub_ to handle our custom format
c4aGenerator.scrub_ = function(block, code, opt_thisOnly) {
const nextBlock = block.nextConnection && block.nextConnection.targetBlock();
let nextCode = '';
if (nextBlock) {
if (!opt_thisOnly) {
nextCode = c4aGenerator.blockToCode(nextBlock);
// Add blank line between comment and non-comment blocks
const currentIsComment = block.type === 'c4a_comment';
const nextIsComment = nextBlock.type === 'c4a_comment';
// Add blank line when transitioning from command to comment or vice versa
if (currentIsComment !== nextIsComment && code.trim() && nextCode.trim()) {
nextCode = '\n' + nextCode;
}
}
}
return code + nextCode;
};

View File

@@ -1,531 +0,0 @@
/* DankMono Font Faces */
@font-face {
font-family: 'DankMono';
src: url('DankMono-Regular.woff2') format('woff2');
font-weight: 400;
font-style: normal;
}
@font-face {
font-family: 'DankMono';
src: url('DankMono-Bold.woff2') format('woff2');
font-weight: 700;
font-style: normal;
}
@font-face {
font-family: 'DankMono';
src: url('DankMono-Italic.woff2') format('woff2');
font-weight: 400;
font-style: italic;
}
/* Root Variables - Matching docs theme */
:root {
--global-font-size: 14px;
--global-code-font-size: 13px;
--global-line-height: 1.5em;
--global-space: 10px;
--font-stack: DankMono, Monaco, Courier New, monospace;
--mono-font-stack: DankMono, Monaco, Courier New, monospace;
--background-color: #070708;
--font-color: #e8e9ed;
--invert-font-color: #222225;
--secondary-color: #d5cec0;
--tertiary-color: #a3abba;
--primary-color: #0fbbaa;
--error-color: #ff3c74;
--progress-bar-background: #3f3f44;
--progress-bar-fill: #09b5a5;
--code-bg-color: #3f3f44;
--block-background-color: #202020;
--header-height: 55px;
}
/* Base Styles */
* {
box-sizing: border-box;
}
body {
margin: 0;
padding: 0;
font-family: var(--font-stack);
font-size: var(--global-font-size);
line-height: var(--global-line-height);
color: var(--font-color);
background-color: var(--background-color);
}
/* Terminal Framework */
.terminal {
min-height: 100vh;
}
.container {
width: 100%;
margin: 0 auto;
}
/* Header */
.header-container {
position: fixed;
top: 0;
left: 0;
right: 0;
height: var(--header-height);
background-color: var(--background-color);
border-bottom: 1px solid var(--progress-bar-background);
z-index: 1000;
padding: 0 calc(var(--global-space) * 2);
}
.terminal-nav {
display: flex;
align-items: center;
justify-content: space-between;
height: 100%;
}
.terminal-logo h1 {
margin: 0;
font-size: 1.2em;
color: var(--primary-color);
font-weight: 400;
}
.terminal-menu ul {
list-style: none;
margin: 0;
padding: 0;
display: flex;
gap: 2em;
}
.terminal-menu a {
color: var(--secondary-color);
text-decoration: none;
transition: color 0.2s;
}
.terminal-menu a:hover,
.terminal-menu a.active {
color: var(--primary-color);
}
/* Main Container */
.main-container {
padding-top: calc(var(--header-height) + 2em);
padding-left: 2em;
padding-right: 2em;
max-width: 1400px;
margin: 0 auto;
}
/* Tutorial Grid */
.tutorial-grid {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 2em;
align-items: start;
}
/* Terminal Cards */
.terminal-card {
background-color: var(--block-background-color);
border: 1px solid var(--progress-bar-background);
margin-bottom: 1.5em;
}
.terminal-card header {
background-color: var(--progress-bar-background);
padding: 0.8em 1em;
font-weight: 700;
color: var(--font-color);
display: flex;
justify-content: space-between;
align-items: center;
}
.terminal-card > div {
padding: 1.5em;
}
/* Editor Section */
.editor-controls {
display: flex;
gap: 0.5em;
}
.editor-container {
height: 300px;
overflow: hidden;
}
#c4a-editor {
width: 100%;
height: 100%;
font-family: var(--mono-font-stack);
font-size: var(--global-code-font-size);
background-color: var(--code-bg-color);
color: var(--font-color);
border: none;
padding: 1em;
resize: none;
}
/* JS Output */
.js-output-container {
max-height: 300px;
overflow-y: auto;
}
.js-output-container pre {
margin: 0;
padding: 1em;
background-color: var(--code-bg-color);
}
.js-output-container code {
font-family: var(--mono-font-stack);
font-size: var(--global-code-font-size);
color: var(--font-color);
white-space: pre-wrap;
}
/* Console Output */
.console-output {
font-family: var(--mono-font-stack);
font-size: var(--global-code-font-size);
max-height: 200px;
overflow-y: auto;
padding: 1em;
}
.console-line {
margin-bottom: 0.5em;
}
.console-prompt {
color: var(--primary-color);
margin-right: 0.5em;
}
.console-text {
color: var(--font-color);
}
.console-error {
color: var(--error-color);
}
.console-success {
color: var(--primary-color);
}
/* Playground */
.playground-container {
height: 600px;
background-color: #fff;
border: 1px solid var(--progress-bar-background);
}
#playground-frame {
width: 100%;
height: 100%;
border: none;
}
/* Execution Progress */
.execution-progress {
padding: 1em;
}
.progress-item {
display: flex;
align-items: center;
gap: 0.8em;
margin-bottom: 0.8em;
color: var(--secondary-color);
}
.progress-item.active {
color: var(--primary-color);
}
.progress-item.completed {
color: var(--tertiary-color);
}
.progress-item.error {
color: var(--error-color);
}
.progress-icon {
font-size: 1.2em;
}
/* Buttons */
.btn {
background-color: var(--primary-color);
color: var(--background-color);
border: none;
padding: 0.5em 1em;
font-family: var(--font-stack);
font-size: 0.9em;
cursor: pointer;
transition: all 0.2s;
}
.btn:hover {
background-color: var(--progress-bar-fill);
}
.btn-sm {
padding: 0.3em 0.8em;
font-size: 0.85em;
}
.btn-ghost {
background-color: transparent;
color: var(--secondary-color);
border: 1px solid var(--progress-bar-background);
}
.btn-ghost:hover {
background-color: var(--progress-bar-background);
color: var(--font-color);
}
/* Scrollbars */
::-webkit-scrollbar {
width: 8px;
height: 8px;
}
::-webkit-scrollbar-track {
background: var(--block-background-color);
}
::-webkit-scrollbar-thumb {
background: var(--progress-bar-background);
}
::-webkit-scrollbar-thumb:hover {
background: var(--secondary-color);
}
/* CodeMirror Theme Override */
.CodeMirror {
font-family: var(--mono-font-stack) !important;
font-size: var(--global-code-font-size) !important;
background-color: var(--code-bg-color) !important;
color: var(--font-color) !important;
height: 100% !important;
}
.CodeMirror-gutters {
background-color: var(--progress-bar-background) !important;
border-right: 1px solid var(--progress-bar-background) !important;
}
/* Responsive */
@media (max-width: 1200px) {
.tutorial-grid {
grid-template-columns: 1fr;
}
.playground-section {
order: -1;
}
}
/* Links */
a {
color: var(--primary-color);
text-decoration: none;
}
a:hover {
text-decoration: underline;
}
/* Lists */
ul, ol {
padding-left: 2em;
}
li {
margin-bottom: 0.5em;
}
/* Code */
code {
background-color: var(--code-bg-color);
padding: 0.2em 0.4em;
font-family: var(--mono-font-stack);
font-size: 0.9em;
}
/* Headings */
h1, h2, h3, h4, h5, h6 {
font-weight: 700;
margin-top: 1.5em;
margin-bottom: 0.8em;
}
h3 {
color: var(--primary-color);
font-size: 1.1em;
}
/* Tutorial Panel */
.tutorial-panel {
position: absolute;
top: 60px;
right: 20px;
width: 380px;
background: #1a1a1b;
border: 1px solid #2a2a2c;
border-radius: 8px;
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.5);
z-index: 1000;
transition: all 0.3s ease;
}
.tutorial-panel.hidden {
display: none;
}
.tutorial-header {
display: flex;
justify-content: space-between;
align-items: center;
padding: 16px 20px;
border-bottom: 1px solid #2a2a2c;
}
.tutorial-header h3 {
margin: 0;
color: #0fbbaa;
font-size: 18px;
}
.close-btn {
background: none;
border: none;
color: #8b8b8d;
font-size: 24px;
cursor: pointer;
padding: 0;
width: 30px;
height: 30px;
display: flex;
align-items: center;
justify-content: center;
border-radius: 4px;
transition: all 0.2s;
}
.close-btn:hover {
background: #2a2a2c;
color: #e0e0e0;
}
.tutorial-content {
padding: 20px;
}
.tutorial-content p {
margin: 0 0 16px 0;
color: #e0e0e0;
line-height: 1.6;
}
.tutorial-progress {
margin-top: 16px;
}
.tutorial-progress span {
display: block;
margin-bottom: 8px;
color: #8b8b8d;
font-size: 12px;
text-transform: uppercase;
}
.progress-bar {
height: 4px;
background: #2a2a2c;
border-radius: 2px;
overflow: hidden;
}
.progress-fill {
height: 100%;
background: #0fbbaa;
transition: width 0.3s ease;
}
.tutorial-actions {
display: flex;
gap: 12px;
padding: 0 20px 20px;
}
.tutorial-btn {
flex: 1;
padding: 10px 16px;
background: #2a2a2c;
color: #e0e0e0;
border: 1px solid #3a3a3c;
border-radius: 6px;
font-size: 14px;
cursor: pointer;
transition: all 0.2s;
}
.tutorial-btn:hover:not(:disabled) {
background: #3a3a3c;
transform: translateY(-1px);
}
.tutorial-btn:disabled {
opacity: 0.5;
cursor: not-allowed;
}
.tutorial-btn.primary {
background: #0fbbaa;
color: #070708;
border-color: #0fbbaa;
}
.tutorial-btn.primary:hover {
background: #0da89a;
border-color: #0da89a;
}
/* Tutorial Highlights */
.tutorial-highlight {
position: relative;
animation: pulse 2s infinite;
}
@keyframes pulse {
0% {
box-shadow: 0 0 0 0 rgba(15, 187, 170, 0.4);
}
50% {
box-shadow: 0 0 0 10px rgba(15, 187, 170, 0);
}
100% {
box-shadow: 0 0 0 0 rgba(15, 187, 170, 0);
}
}
.editor-card {
position: relative;
}

View File

@@ -1,21 +0,0 @@
# Demo: Login Flow with Blockly
# This script can be created visually using Blockly blocks
GO https://example.com/login
WAIT `#login-form` 5
# Check if already logged in
IF (EXISTS `.user-avatar`) THEN GO https://example.com/dashboard
# Fill login form
CLICK `#email`
TYPE "demo@example.com"
CLICK `#password`
TYPE "password123"
# Submit form
CLICK `button[type="submit"]`
WAIT `.dashboard` 10
# Success message
EVAL `console.log('Login successful!')`

View File

@@ -1,205 +0,0 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>C4A-Script Interactive Tutorial | Crawl4AI</title>
<link rel="stylesheet" href="assets/app.css">
<link rel="stylesheet" href="assets/blockly-theme.css">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/codemirror/6.65.7/codemirror.min.css">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/codemirror/6.65.7/theme/material-darker.min.css">
</head>
<body>
<!-- Tutorial Intro Modal -->
<div id="tutorial-intro" class="tutorial-intro-modal">
<div class="intro-content">
<h2>Welcome to C4A-Script Tutorial!</h2>
<p>C4A-Script is a simple language for web automation. This interactive tutorial will teach you:</p>
<ul>
<li>How to handle popups and banners</li>
<li>Form filling and navigation</li>
<li>Advanced automation techniques</li>
</ul>
<div class="intro-actions">
<button id="start-tutorial-btn" class="intro-btn primary">Start Tutorial</button>
<button id="skip-tutorial-btn" class="intro-btn">Skip</button>
</div>
</div>
</div>
<!-- Event Editor Modal -->
<div id="event-editor-overlay" class="modal-overlay hidden"></div>
<div id="event-editor-modal" class="event-editor-modal hidden">
<h4>Edit Event</h4>
<div class="editor-field">
<label>Command Type</label>
<select id="edit-command-type" disabled>
<option value="CLICK">CLICK</option>
<option value="DOUBLE_CLICK">DOUBLE_CLICK</option>
<option value="RIGHT_CLICK">RIGHT_CLICK</option>
<option value="TYPE">TYPE</option>
<option value="SET">SET</option>
<option value="SCROLL">SCROLL</option>
<option value="WAIT">WAIT</option>
</select>
</div>
<div id="edit-selector-field" class="editor-field">
<label>Selector</label>
<input type="text" id="edit-selector" placeholder=".class or #id">
</div>
<div id="edit-value-field" class="editor-field">
<label>Value</label>
<input type="text" id="edit-value" placeholder="Text or number">
</div>
<div id="edit-direction-field" class="editor-field hidden">
<label>Direction</label>
<select id="edit-direction">
<option value="UP">UP</option>
<option value="DOWN">DOWN</option>
<option value="LEFT">LEFT</option>
<option value="RIGHT">RIGHT</option>
</select>
</div>
<div class="editor-actions">
<button id="edit-cancel" class="mini-btn">Cancel</button>
<button id="edit-save" class="mini-btn primary">Save</button>
</div>
</div>
<!-- Main App Layout -->
<div class="app-container">
<!-- Left Panel: Editor -->
<div class="editor-panel">
<div class="panel-header">
<h2>C4A-Script Editor</h2>
<div class="header-actions">
<button id="tutorial-btn" class="action-btn" title="Tutorial">
<span class="icon">📚</span>
</button>
<button id="examples-btn" class="action-btn" title="Examples">
<span class="icon">📋</span>
</button>
<button id="clear-btn" class="action-btn" title="Clear">
<span class="icon">🗑</span>
</button>
<button id="run-btn" class="action-btn primary">
<span class="icon"></span>Run
</button>
<button id="record-btn" class="action-btn record">
<span class="icon"></span>Record
</button>
<button id="timeline-btn" class="action-btn timeline hidden" title="View Timeline">
<span class="icon">📊</span>
</button>
</div>
</div>
<div class="editor-container">
<div id="editor-view" class="editor-wrapper">
<textarea id="c4a-editor" placeholder="# Write your C4A script here..."></textarea>
</div>
<!-- Recording Timeline -->
<div id="timeline-view" class="recording-timeline hidden">
<div class="timeline-header">
<h3>Recording Timeline</h3>
<div class="timeline-actions">
<button id="back-to-editor" class="mini-btn">← Back</button>
<button id="select-all-events" class="mini-btn">Select All</button>
<button id="clear-events" class="mini-btn">Clear</button>
<button id="generate-script" class="mini-btn primary">Generate Script</button>
</div>
</div>
<div id="timeline-events" class="timeline-events">
<!-- Events will be added here dynamically -->
</div>
</div>
</div>
<!-- Bottom: Output Tabs -->
<div class="output-section">
<div class="tabs">
<button class="tab active" data-tab="console">Console</button>
<button class="tab" data-tab="javascript">Generated JS</button>
</div>
<div class="tab-content">
<div id="console-tab" class="tab-pane active">
<div id="console-output" class="console">
<div class="console-line">
<span class="console-prompt">$</span>
<span class="console-text">Ready to run C4A scripts...</span>
</div>
</div>
</div>
<div id="javascript-tab" class="tab-pane">
<div class="js-output-header">
<div class="js-actions">
<button id="copy-js-btn" class="mini-btn" title="Copy">
<span>📋</span>
</button>
<button id="edit-js-btn" class="mini-btn" title="Edit">
<span>✏️</span>
</button>
</div>
</div>
<pre id="js-output" class="js-output">// JavaScript will appear here...</pre>
</div>
</div>
</div>
</div>
<!-- Right Panel: Playground -->
<div class="playground-panel">
<div class="panel-header">
<h2>Playground</h2>
<div class="header-actions">
<button id="reset-playground" class="action-btn" title="Reset">
<span class="icon">🔄</span>
</button>
<button id="fullscreen-btn" class="action-btn" title="Fullscreen">
<span class="icon"></span>
</button>
</div>
</div>
<div class="playground-wrapper">
<iframe id="playground-frame" src="playground/" title="Playground"></iframe>
</div>
</div>
</div>
<!-- Tutorial Navigation Bar -->
<div id="tutorial-nav" class="tutorial-nav hidden">
<div class="tutorial-nav-content">
<div class="tutorial-left">
<div class="tutorial-step-title">
<span id="tutorial-step-info">Step 1 of 9</span>
<span id="tutorial-title">Welcome</span>
</div>
<p id="tutorial-description" class="tutorial-description">Let's start by waiting for the page to load.</p>
</div>
<div class="tutorial-right">
<div class="tutorial-controls">
<button id="tutorial-prev" class="nav-btn" disabled>← Previous</button>
<button id="tutorial-next" class="nav-btn primary">Next →</button>
</div>
<button id="tutorial-exit" class="exit-btn" title="Exit Tutorial">×</button>
</div>
</div>
<div class="tutorial-progress-bar">
<div id="tutorial-progress-fill" class="progress-fill"></div>
</div>
</div>
<!-- Scripts -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/codemirror/6.65.7/codemirror.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/codemirror/6.65.7/mode/javascript/javascript.min.js"></script>
<!-- Blockly -->
<script src="https://unpkg.com/blockly/blockly.min.js"></script>
<script src="assets/c4a-blocks.js"></script>
<script src="assets/c4a-generator.js"></script>
<script src="assets/blockly-manager.js"></script>
<script src="assets/app.js"></script>
</body>
</html>

Some files were not shown because too many files have changed in this diff Show More