This is sample content for testing Crawl4AI's raw HTML processing.
+ + """ + + # Save to file + file_path = Path("docs/examples/tmp/sample.html").absolute() + with open(file_path, "w") as f: + f.write(raw_html) + + async with AsyncWebCrawler() as crawler: + # Crawl raw HTML + raw_result = await crawler.arun( + url="raw:" + raw_html, config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS) + ) + print("Raw HTML processing:") + print(f" Markdown: {raw_result.markdown.raw_markdown[:50]}...") + + # Crawl local file + file_result = await crawler.arun( + url=f"file://{file_path}", + config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS), + ) + print("\nLocal file processing:") + print(f" Markdown: {file_result.markdown.raw_markdown[:50]}...") + + # Clean up + os.remove(file_path) + print(f"Processed both raw HTML and local file ({file_path})") + +async def main(): + """Run all demo functions sequentially""" + print("=== Comprehensive Crawl4AI Demo ===") + print("Note: Some examples require API keys or other configurations") + + # Run all demos + await demo_basic_crawl() + await demo_parallel_crawl() + await demo_fit_markdown() + await demo_llm_structured_extraction_no_schema() + await demo_css_structured_extraction_no_schema() + await demo_deep_crawl() + await demo_js_interaction() + await demo_media_and_links() + await demo_screenshot_and_pdf() + # # await demo_proxy_rotation() + await demo_raw_html_and_file() + + # Clean up any temp files that may have been created + print("\n=== Demo Complete ===") + print("Check for any generated files (screenshots, PDFs) in the current directory") + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/docs/examples/quickstart_examples_set_2.py b/docs/examples/quickstart_examples_set_2.py new file mode 100644 index 00000000..3adbfc0d --- /dev/null +++ b/docs/examples/quickstart_examples_set_2.py @@ -0,0 +1,562 @@ +import os, sys + +from crawl4ai.types import LLMConfig + +sys.path.append( + os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) +) + +import asyncio +import time +import json +import re +from typing import Dict +from bs4 import BeautifulSoup +from pydantic import BaseModel, Field +from crawl4ai import AsyncWebCrawler, CacheMode, BrowserConfig, CrawlerRunConfig +from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator +from crawl4ai.content_filter_strategy import PruningContentFilter +from crawl4ai.extraction_strategy import ( + JsonCssExtractionStrategy, + LLMExtractionStrategy, +) + +__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) + +print("Crawl4AI: Advanced Web Crawling and Data Extraction") +print("GitHub Repository: https://github.com/unclecode/crawl4ai") +print("Twitter: @unclecode") +print("Website: https://crawl4ai.com") + + +# Basic Example - Simple Crawl +async def simple_crawl(): + print("\n--- Basic Usage ---") + browser_config = BrowserConfig(headless=True) + crawler_config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS) + + async with AsyncWebCrawler(config=browser_config) as crawler: + result = await crawler.arun( + url="https://www.nbcnews.com/business", config=crawler_config + ) + print(result.markdown[:500]) + + +async def clean_content(): + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, + excluded_tags=["nav", "footer", "aside"], + remove_overlay_elements=True, + markdown_generator=DefaultMarkdownGenerator( + content_filter=PruningContentFilter( + threshold=0.48, threshold_type="fixed", min_word_threshold=0 + ), + options={"ignore_links": True}, + ), + ) + async with AsyncWebCrawler() as crawler: + result = await crawler.arun( + url="https://en.wikipedia.org/wiki/Apple", + config=crawler_config, + ) + full_markdown_length = len(result.markdown.raw_markdown) + fit_markdown_length = len(result.markdown.fit_markdown) + print(f"Full Markdown Length: {full_markdown_length}") + print(f"Fit Markdown Length: {fit_markdown_length}") + + +async def link_analysis(): + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.ENABLED, + exclude_external_links=True, + exclude_social_media_links=True, + ) + async with AsyncWebCrawler() as crawler: + result = await crawler.arun( + url="https://www.nbcnews.com/business", + config=crawler_config, + ) + print(f"Found {len(result.links['internal'])} internal links") + print(f"Found {len(result.links['external'])} external links") + + for link in result.links["internal"][:5]: + print(f"Href: {link['href']}\nText: {link['text']}\n") + + +# JavaScript Execution Example +async def simple_example_with_running_js_code(): + print("\n--- Executing JavaScript and Using CSS Selectors ---") + + browser_config = BrowserConfig(headless=True, java_script_enabled=True) + + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, + js_code="const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();", + # wait_for="() => { return Array.from(document.querySelectorAll('article.tease-card')).length > 10; }" + ) + + async with AsyncWebCrawler(config=browser_config) as crawler: + result = await crawler.arun( + url="https://www.nbcnews.com/business", config=crawler_config + ) + print(result.markdown[:500]) + + +# CSS Selector Example +async def simple_example_with_css_selector(): + print("\n--- Using CSS Selectors ---") + browser_config = BrowserConfig(headless=True) + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, css_selector=".wide-tease-item__description" + ) + + async with AsyncWebCrawler(config=browser_config) as crawler: + result = await crawler.arun( + url="https://www.nbcnews.com/business", config=crawler_config + ) + print(result.markdown[:500]) + + +async def media_handling(): + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, exclude_external_images=True, screenshot=True + ) + async with AsyncWebCrawler() as crawler: + result = await crawler.arun( + url="https://www.nbcnews.com/business", config=crawler_config + ) + for img in result.media["images"][:5]: + print(f"Image URL: {img['src']}, Alt: {img['alt']}, Score: {img['score']}") + + +async def custom_hook_workflow(verbose=True): + async with AsyncWebCrawler() as crawler: + # Set a 'before_goto' hook to run custom code just before navigation + crawler.crawler_strategy.set_hook( + "before_goto", + lambda page, context: print("[Hook] Preparing to navigate..."), + ) + + # Perform the crawl operation + result = await crawler.arun(url="https://crawl4ai.com") + print(result.markdown.raw_markdown[:500].replace("\n", " -- ")) + + +# Proxy Example +async def use_proxy(): + print("\n--- Using a Proxy ---") + browser_config = BrowserConfig( + headless=True, + proxy_config={ + "server": "http://proxy.example.com:8080", + "username": "username", + "password": "password", + }, + ) + crawler_config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS) + + async with AsyncWebCrawler(config=browser_config) as crawler: + result = await crawler.arun( + url="https://www.nbcnews.com/business", config=crawler_config + ) + if result.success: + print(result.markdown[:500]) + + +# Screenshot Example +async def capture_and_save_screenshot(url: str, output_path: str): + browser_config = BrowserConfig(headless=True) + crawler_config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS, screenshot=True) + + async with AsyncWebCrawler(config=browser_config) as crawler: + result = await crawler.arun(url=url, config=crawler_config) + + if result.success and result.screenshot: + import base64 + + screenshot_data = base64.b64decode(result.screenshot) + with open(output_path, "wb") as f: + f.write(screenshot_data) + print(f"Screenshot saved successfully to {output_path}") + else: + print("Failed to capture screenshot") + + +# LLM Extraction Example +class OpenAIModelFee(BaseModel): + model_name: str = Field(..., description="Name of the OpenAI model.") + input_fee: str = Field(..., description="Fee for input token for the OpenAI model.") + output_fee: str = Field( + ..., description="Fee for output token for the OpenAI model." + ) + + +async def extract_structured_data_using_llm( + provider: str, api_token: str = None, extra_headers: Dict[str, str] = None +): + print(f"\n--- Extracting Structured Data with {provider} ---") + + if api_token is None and provider != "ollama": + print(f"API token is required for {provider}. Skipping this example.") + return + + browser_config = BrowserConfig(headless=True) + + extra_args = {"temperature": 0, "top_p": 0.9, "max_tokens": 2000} + if extra_headers: + extra_args["extra_headers"] = extra_headers + + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, + word_count_threshold=1, + page_timeout=80000, + extraction_strategy=LLMExtractionStrategy( + llm_config=LLMConfig(provider=provider,api_token=api_token), + schema=OpenAIModelFee.model_json_schema(), + extraction_type="schema", + instruction="""From the crawled content, extract all mentioned model names along with their fees for input and output tokens. + Do not miss any models in the entire content.""", + extra_args=extra_args, + ), + ) + + async with AsyncWebCrawler(config=browser_config) as crawler: + result = await crawler.arun( + url="https://openai.com/api/pricing/", config=crawler_config + ) + print(result.extracted_content) + + +# CSS Extraction Example +async def extract_structured_data_using_css_extractor(): + print("\n--- Using JsonCssExtractionStrategy for Fast Structured Output ---") + schema = { + "name": "KidoCode Courses", + "baseSelector": "section.charge-methodology .framework-collection-item.w-dyn-item", + "fields": [ + { + "name": "section_title", + "selector": "h3.heading-50", + "type": "text", + }, + { + "name": "section_description", + "selector": ".charge-content", + "type": "text", + }, + { + "name": "course_name", + "selector": ".text-block-93", + "type": "text", + }, + { + "name": "course_description", + "selector": ".course-content-text", + "type": "text", + }, + { + "name": "course_icon", + "selector": ".image-92", + "type": "attribute", + "attribute": "src", + }, + ], + } + + browser_config = BrowserConfig(headless=True, java_script_enabled=True) + + js_click_tabs = """ + (async () => { + const tabs = document.querySelectorAll("section.charge-methodology .tabs-menu-3 > div"); + for(let tab of tabs) { + tab.scrollIntoView(); + tab.click(); + await new Promise(r => setTimeout(r, 500)); + } + })(); + """ + + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, + extraction_strategy=JsonCssExtractionStrategy(schema), + js_code=[js_click_tabs], + delay_before_return_html=1 + ) + + async with AsyncWebCrawler(config=browser_config) as crawler: + result = await crawler.arun( + url="https://www.kidocode.com/degrees/technology", config=crawler_config + ) + + companies = json.loads(result.extracted_content) + print(f"Successfully extracted {len(companies)} companies") + print(json.dumps(companies[0], indent=2)) + + +# Dynamic Content Examples - Method 1 +async def crawl_dynamic_content_pages_method_1(): + print("\n--- Advanced Multi-Page Crawling with JavaScript Execution ---") + first_commit = "" + + async def on_execution_started(page, **kwargs): + nonlocal first_commit + try: + while True: + await page.wait_for_selector("li.Box-sc-g0xbh4-0 h4") + commit = await page.query_selector("li.Box-sc-g0xbh4-0 h4") + commit = await commit.evaluate("(element) => element.textContent") + commit = re.sub(r"\s+", "", commit) + if commit and commit != first_commit: + first_commit = commit + break + await asyncio.sleep(0.5) + except Exception as e: + print(f"Warning: New content didn't appear after JavaScript execution: {e}") + + browser_config = BrowserConfig(headless=False, java_script_enabled=True) + + async with AsyncWebCrawler(config=browser_config) as crawler: + crawler.crawler_strategy.set_hook("on_execution_started", on_execution_started) + + url = "https://github.com/microsoft/TypeScript/commits/main" + session_id = "typescript_commits_session" + all_commits = [] + + js_next_page = """ + const button = document.querySelector('a[data-testid="pagination-next-button"]'); + if (button) button.click(); + """ + + for page in range(3): + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, + css_selector="li.Box-sc-g0xbh4-0", + js_code=js_next_page if page > 0 else None, + js_only=page > 0, + session_id=session_id, + ) + + result = await crawler.arun(url=url, config=crawler_config) + assert result.success, f"Failed to crawl page {page + 1}" + + soup = BeautifulSoup(result.cleaned_html, "html.parser") + commits = soup.select("li") + all_commits.extend(commits) + + print(f"Page {page + 1}: Found {len(commits)} commits") + + print(f"Successfully crawled {len(all_commits)} commits across 3 pages") + + +# Dynamic Content Examples - Method 2 +async def crawl_dynamic_content_pages_method_2(): + print("\n--- Advanced Multi-Page Crawling with JavaScript Execution ---") + + browser_config = BrowserConfig(headless=False, java_script_enabled=True) + + js_next_page_and_wait = """ + (async () => { + const getCurrentCommit = () => { + const commits = document.querySelectorAll('li.Box-sc-g0xbh4-0 h4'); + return commits.length > 0 ? commits[0].textContent.trim() : null; + }; + + const initialCommit = getCurrentCommit(); + const button = document.querySelector('a[data-testid="pagination-next-button"]'); + if (button) button.click(); + + while (true) { + await new Promise(resolve => setTimeout(resolve, 100)); + const newCommit = getCurrentCommit(); + if (newCommit && newCommit !== initialCommit) { + break; + } + } + })(); + """ + + schema = { + "name": "Commit Extractor", + "baseSelector": "li.Box-sc-g0xbh4-0", + "fields": [ + { + "name": "title", + "selector": "h4.markdown-title", + "type": "text", + "transform": "strip", + }, + ], + } + + async with AsyncWebCrawler(config=browser_config) as crawler: + url = "https://github.com/microsoft/TypeScript/commits/main" + session_id = "typescript_commits_session" + all_commits = [] + + extraction_strategy = JsonCssExtractionStrategy(schema) + + for page in range(3): + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, + css_selector="li.Box-sc-g0xbh4-0", + extraction_strategy=extraction_strategy, + js_code=js_next_page_and_wait if page > 0 else None, + js_only=page > 0, + session_id=session_id, + ) + + result = await crawler.arun(url=url, config=crawler_config) + assert result.success, f"Failed to crawl page {page + 1}" + + commits = json.loads(result.extracted_content) + all_commits.extend(commits) + print(f"Page {page + 1}: Found {len(commits)} commits") + + print(f"Successfully crawled {len(all_commits)} commits across 3 pages") + + +async def cosine_similarity_extraction(): + from crawl4ai.extraction_strategy import CosineStrategy + crawl_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, + extraction_strategy=CosineStrategy( + word_count_threshold=10, + max_dist=0.2, # Maximum distance between two words + linkage_method="ward", # Linkage method for hierarchical clustering (ward, complete, average, single) + top_k=3, # Number of top keywords to extract + sim_threshold=0.3, # Similarity threshold for clustering + semantic_filter="McDonald's economic impact, American consumer trends", # Keywords to filter the content semantically using embeddings + verbose=True, + ), + ) + async with AsyncWebCrawler() as crawler: + result = await crawler.arun( + url="https://www.nbcnews.com/business/consumer/how-mcdonalds-e-coli-crisis-inflation-politics-reflect-american-story-rcna177156", + config=crawl_config, + ) + print(json.loads(result.extracted_content)[:5]) + + +# Browser Comparison +async def crawl_custom_browser_type(): + print("\n--- Browser Comparison ---") + + # Firefox + browser_config_firefox = BrowserConfig(browser_type="firefox", headless=True) + start = time.time() + async with AsyncWebCrawler(config=browser_config_firefox) as crawler: + result = await crawler.arun( + url="https://www.example.com", + config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS), + ) + print("Firefox:", time.time() - start) + print(result.markdown[:500]) + + # WebKit + browser_config_webkit = BrowserConfig(browser_type="webkit", headless=True) + start = time.time() + async with AsyncWebCrawler(config=browser_config_webkit) as crawler: + result = await crawler.arun( + url="https://www.example.com", + config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS), + ) + print("WebKit:", time.time() - start) + print(result.markdown[:500]) + + # Chromium (default) + browser_config_chromium = BrowserConfig(browser_type="chromium", headless=True) + start = time.time() + async with AsyncWebCrawler(config=browser_config_chromium) as crawler: + result = await crawler.arun( + url="https://www.example.com", + config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS), + ) + print("Chromium:", time.time() - start) + print(result.markdown[:500]) + + +# Anti-Bot and User Simulation +async def crawl_with_user_simulation(): + browser_config = BrowserConfig( + headless=True, + user_agent_mode="random", + user_agent_generator_config={"device_type": "mobile", "os_type": "android"}, + ) + + crawler_config = CrawlerRunConfig( + cache_mode=CacheMode.BYPASS, + magic=True, + simulate_user=True, + override_navigator=True, + ) + + async with AsyncWebCrawler(config=browser_config) as crawler: + result = await crawler.arun(url="YOUR-URL-HERE", config=crawler_config) + print(result.markdown) + + +async def ssl_certification(): + # Configure crawler to fetch SSL certificate + config = CrawlerRunConfig( + fetch_ssl_certificate=True, + cache_mode=CacheMode.BYPASS, # Bypass cache to always get fresh certificates + ) + + async with AsyncWebCrawler() as crawler: + result = await crawler.arun(url="https://example.com", config=config) + + if result.success and result.ssl_certificate: + cert = result.ssl_certificate + + tmp_dir = os.path.join(__location__, "tmp") + os.makedirs(tmp_dir, exist_ok=True) + + # 1. Access certificate properties directly + print("\nCertificate Information:") + print(f"Issuer: {cert.issuer.get('CN', '')}") + print(f"Valid until: {cert.valid_until}") + print(f"Fingerprint: {cert.fingerprint}") + + # 2. Export certificate in different formats + cert.to_json(os.path.join(tmp_dir, "certificate.json")) # For analysis + print("\nCertificate exported to:") + print(f"- JSON: {os.path.join(tmp_dir, 'certificate.json')}") + + pem_data = cert.to_pem( + os.path.join(tmp_dir, "certificate.pem") + ) # For web servers + print(f"- PEM: {os.path.join(tmp_dir, 'certificate.pem')}") + + der_data = cert.to_der( + os.path.join(tmp_dir, "certificate.der") + ) # For Java apps + print(f"- DER: {os.path.join(tmp_dir, 'certificate.der')}") + + +# Main execution +async def main(): + # Basic examples + await simple_crawl() + await simple_example_with_running_js_code() + await simple_example_with_css_selector() + + # Advanced examples + await extract_structured_data_using_css_extractor() + await extract_structured_data_using_llm( + "openai/gpt-4o", os.getenv("OPENAI_API_KEY") + ) + await crawl_dynamic_content_pages_method_1() + await crawl_dynamic_content_pages_method_2() + + # Browser comparisons + await crawl_custom_browser_type() + + # Screenshot example + await capture_and_save_screenshot( + "https://www.example.com", + os.path.join(__location__, "tmp/example_screenshot.jpg") + ) + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/docs/examples/quickstart_sync.py b/docs/examples/quickstart_sync.py deleted file mode 100644 index 78f3e56c..00000000 --- a/docs/examples/quickstart_sync.py +++ /dev/null @@ -1,405 +0,0 @@ -import os -import time -from crawl4ai import LLMConfig -from crawl4ai.web_crawler import WebCrawler -from crawl4ai.chunking_strategy import * -from crawl4ai.extraction_strategy import * -from crawl4ai.crawler_strategy import * -from rich import print -from rich.console import Console -from functools import lru_cache - -console = Console() - - -@lru_cache() -def create_crawler(): - crawler = WebCrawler(verbose=True) - crawler.warmup() - return crawler - - -def print_result(result): - # Print each key in one line and just the first 10 characters of each one's value and three dots - console.print("\t[bold]Result:[/bold]") - for key, value in result.model_dump().items(): - if isinstance(value, str) and value: - console.print(f"\t{key}: [green]{value[:20]}...[/green]") - if result.extracted_content: - items = json.loads(result.extracted_content) - print(f"\t[bold]{len(items)} blocks is extracted![/bold]") - - -def cprint(message, press_any_key=False): - console.print(message) - if press_any_key: - console.print("Press any key to continue...", style="") - input() - - -def basic_usage(crawler): - cprint( - "🛠️ [bold cyan]Basic Usage: Simply provide a URL and let Crawl4ai do the magic![/bold cyan]" - ) - result = crawler.run(url="https://www.nbcnews.com/business", only_text=True) - cprint("[LOG] 📦 [bold yellow]Basic crawl result:[/bold yellow]") - print_result(result) - - -def basic_usage_some_params(crawler): - cprint( - "🛠️ [bold cyan]Basic Usage: Simply provide a URL and let Crawl4ai do the magic![/bold cyan]" - ) - result = crawler.run( - url="https://www.nbcnews.com/business", word_count_threshold=1, only_text=True - ) - cprint("[LOG] 📦 [bold yellow]Basic crawl result:[/bold yellow]") - print_result(result) - - -def screenshot_usage(crawler): - cprint("\n📸 [bold cyan]Let's take a screenshot of the page![/bold cyan]") - result = crawler.run(url="https://www.nbcnews.com/business", screenshot=True) - cprint("[LOG] 📦 [bold yellow]Screenshot result:[/bold yellow]") - # Save the screenshot to a file - with open("screenshot.png", "wb") as f: - f.write(base64.b64decode(result.screenshot)) - cprint("Screenshot saved to 'screenshot.png'!") - print_result(result) - - -def understanding_parameters(crawler): - cprint( - "\n🧠 [bold cyan]Understanding 'bypass_cache' and 'include_raw_html' parameters:[/bold cyan]" - ) - cprint( - "By default, Crawl4ai caches the results of your crawls. This means that subsequent crawls of the same URL will be much faster! Let's see this in action." - ) - - # First crawl (reads from cache) - cprint("1️⃣ First crawl (caches the result):", True) - start_time = time.time() - result = crawler.run(url="https://www.nbcnews.com/business") - end_time = time.time() - cprint( - f"[LOG] 📦 [bold yellow]First crawl took {end_time - start_time} seconds and result (from cache):[/bold yellow]" - ) - print_result(result) - - # Force to crawl again - cprint("2️⃣ Second crawl (Force to crawl again):", True) - start_time = time.time() - result = crawler.run(url="https://www.nbcnews.com/business", bypass_cache=True) - end_time = time.time() - cprint( - f"[LOG] 📦 [bold yellow]Second crawl took {end_time - start_time} seconds and result (forced to crawl):[/bold yellow]" - ) - print_result(result) - - -def add_chunking_strategy(crawler): - # Adding a chunking strategy: RegexChunking - cprint( - "\n🧩 [bold cyan]Let's add a chunking strategy: RegexChunking![/bold cyan]", - True, - ) - cprint( - "RegexChunking is a simple chunking strategy that splits the text based on a given regex pattern. Let's see it in action!" - ) - result = crawler.run( - url="https://www.nbcnews.com/business", - chunking_strategy=RegexChunking(patterns=["\n\n"]), - ) - cprint("[LOG] 📦 [bold yellow]RegexChunking result:[/bold yellow]") - print_result(result) - - # Adding another chunking strategy: NlpSentenceChunking - cprint( - "\n🔍 [bold cyan]Time to explore another chunking strategy: NlpSentenceChunking![/bold cyan]", - True, - ) - cprint( - "NlpSentenceChunking uses NLP techniques to split the text into sentences. Let's see how it performs!" - ) - result = crawler.run( - url="https://www.nbcnews.com/business", chunking_strategy=NlpSentenceChunking() - ) - cprint("[LOG] 📦 [bold yellow]NlpSentenceChunking result:[/bold yellow]") - print_result(result) - - -def add_extraction_strategy(crawler): - # Adding an extraction strategy: CosineStrategy - cprint( - "\n🧠 [bold cyan]Let's get smarter with an extraction strategy: CosineStrategy![/bold cyan]", - True, - ) - cprint( - "CosineStrategy uses cosine similarity to extract semantically similar blocks of text. Let's see it in action!" - ) - result = crawler.run( - url="https://www.nbcnews.com/business", - extraction_strategy=CosineStrategy( - word_count_threshold=10, - max_dist=0.2, - linkage_method="ward", - top_k=3, - sim_threshold=0.3, - verbose=True, - ), - ) - cprint("[LOG] 📦 [bold yellow]CosineStrategy result:[/bold yellow]") - print_result(result) - - # Using semantic_filter with CosineStrategy - cprint( - "You can pass other parameters like 'semantic_filter' to the CosineStrategy to extract semantically similar blocks of text. Let's see it in action!" - ) - result = crawler.run( - url="https://www.nbcnews.com/business", - extraction_strategy=CosineStrategy( - semantic_filter="inflation rent prices", - ), - ) - cprint( - "[LOG] 📦 [bold yellow]CosineStrategy result with semantic filter:[/bold yellow]" - ) - print_result(result) - - -def add_llm_extraction_strategy(crawler): - # Adding an LLM extraction strategy without instructions - cprint( - "\n🤖 [bold cyan]Time to bring in the big guns: LLMExtractionStrategy without instructions![/bold cyan]", - True, - ) - cprint( - "LLMExtractionStrategy uses a large language model to extract relevant information from the web page. Let's see it in action!" - ) - result = crawler.run( - url="https://www.nbcnews.com/business", - extraction_strategy=LLMExtractionStrategy( - llm_config = LLMConfig(provider="openai/gpt-4o", api_token=os.getenv("OPENAI_API_KEY")) - ), - ) - cprint( - "[LOG] 📦 [bold yellow]LLMExtractionStrategy (no instructions) result:[/bold yellow]" - ) - print_result(result) - - # Adding an LLM extraction strategy with instructions - cprint( - "\n📜 [bold cyan]Let's make it even more interesting: LLMExtractionStrategy with instructions![/bold cyan]", - True, - ) - cprint( - "Let's say we are only interested in financial news. Let's see how LLMExtractionStrategy performs with instructions!" - ) - result = crawler.run( - url="https://www.nbcnews.com/business", - extraction_strategy=LLMExtractionStrategy( - llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")), - instruction="I am interested in only financial news", - ), - ) - cprint( - "[LOG] 📦 [bold yellow]LLMExtractionStrategy (with instructions) result:[/bold yellow]" - ) - print_result(result) - - result = crawler.run( - url="https://www.nbcnews.com/business", - extraction_strategy=LLMExtractionStrategy( - llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")), - instruction="Extract only content related to technology", - ), - ) - cprint( - "[LOG] 📦 [bold yellow]LLMExtractionStrategy (with technology instruction) result:[/bold yellow]" - ) - print_result(result) - - -def targeted_extraction(crawler): - # Using a CSS selector to extract only H2 tags - cprint( - "\n🎯 [bold cyan]Targeted extraction: Let's use a CSS selector to extract only H2 tags![/bold cyan]", - True, - ) - result = crawler.run(url="https://www.nbcnews.com/business", css_selector="h2") - cprint("[LOG] 📦 [bold yellow]CSS Selector (H2 tags) result:[/bold yellow]") - print_result(result) - - -def interactive_extraction(crawler): - # Passing JavaScript code to interact with the page - cprint( - "\n🖱️ [bold cyan]Let's get interactive: Passing JavaScript code to click 'Load More' button![/bold cyan]", - True, - ) - cprint( - "In this example we try to click the 'Load More' button on the page using JavaScript code." - ) - js_code = """ - const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); - loadMoreButton && loadMoreButton.click(); - """ - # crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code) - # crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True) - result = crawler.run(url="https://www.nbcnews.com/business", js=js_code) - cprint( - "[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]" - ) - print_result(result) - - -def multiple_scrip(crawler): - # Passing JavaScript code to interact with the page - cprint( - "\n🖱️ [bold cyan]Let's get interactive: Passing JavaScript code to click 'Load More' button![/bold cyan]", - True, - ) - cprint( - "In this example we try to click the 'Load More' button on the page using JavaScript code." - ) - js_code = [ - """ - const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); - loadMoreButton && loadMoreButton.click(); - """ - ] * 2 - # crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code) - # crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True) - result = crawler.run(url="https://www.nbcnews.com/business", js=js_code) - cprint( - "[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]" - ) - print_result(result) - - -def using_crawler_hooks(crawler): - # Example usage of the hooks for authentication and setting a cookie - def on_driver_created(driver): - print("[HOOK] on_driver_created") - # Example customization: maximize the window - driver.maximize_window() - - # Example customization: logging in to a hypothetical website - driver.get("https://example.com/login") - - from selenium.webdriver.support.ui import WebDriverWait - from selenium.webdriver.common.by import By - from selenium.webdriver.support import expected_conditions as EC - - WebDriverWait(driver, 10).until( - EC.presence_of_element_located((By.NAME, "username")) - ) - driver.find_element(By.NAME, "username").send_keys("testuser") - driver.find_element(By.NAME, "password").send_keys("password123") - driver.find_element(By.NAME, "login").click() - WebDriverWait(driver, 10).until( - EC.presence_of_element_located((By.ID, "welcome")) - ) - # Add a custom cookie - driver.add_cookie({"name": "test_cookie", "value": "cookie_value"}) - return driver - - def before_get_url(driver): - print("[HOOK] before_get_url") - # Example customization: add a custom header - # Enable Network domain for sending headers - driver.execute_cdp_cmd("Network.enable", {}) - # Add a custom header - driver.execute_cdp_cmd( - "Network.setExtraHTTPHeaders", {"headers": {"X-Test-Header": "test"}} - ) - return driver - - def after_get_url(driver): - print("[HOOK] after_get_url") - # Example customization: log the URL - print(driver.current_url) - return driver - - def before_return_html(driver, html): - print("[HOOK] before_return_html") - # Example customization: log the HTML - print(len(html)) - return driver - - cprint( - "\n🔗 [bold cyan]Using Crawler Hooks: Let's see how we can customize the crawler using hooks![/bold cyan]", - True, - ) - - crawler_strategy = LocalSeleniumCrawlerStrategy(verbose=True) - crawler_strategy.set_hook("on_driver_created", on_driver_created) - crawler_strategy.set_hook("before_get_url", before_get_url) - crawler_strategy.set_hook("after_get_url", after_get_url) - crawler_strategy.set_hook("before_return_html", before_return_html) - - crawler = WebCrawler(verbose=True, crawler_strategy=crawler_strategy) - crawler.warmup() - result = crawler.run(url="https://example.com") - - cprint("[LOG] 📦 [bold yellow]Crawler Hooks result:[/bold yellow]") - print_result(result=result) - - -def using_crawler_hooks_dleay_example(crawler): - def delay(driver): - print("Delaying for 5 seconds...") - time.sleep(5) - print("Resuming...") - - def create_crawler(): - crawler_strategy = LocalSeleniumCrawlerStrategy(verbose=True) - crawler_strategy.set_hook("after_get_url", delay) - crawler = WebCrawler(verbose=True, crawler_strategy=crawler_strategy) - crawler.warmup() - return crawler - - cprint( - "\n🔗 [bold cyan]Using Crawler Hooks: Let's add a delay after fetching the url to make sure entire page is fetched.[/bold cyan]" - ) - crawler = create_crawler() - result = crawler.run(url="https://google.com", bypass_cache=True) - - cprint("[LOG] 📦 [bold yellow]Crawler Hooks result:[/bold yellow]") - print_result(result) - - -def main(): - cprint( - "🌟 [bold green]Welcome to the Crawl4ai Quickstart Guide! Let's dive into some web crawling fun! 🌐[/bold green]" - ) - cprint( - "⛳️ [bold cyan]First Step: Create an instance of WebCrawler and call the `warmup()` function.[/bold cyan]" - ) - cprint( - "If this is the first time you're running Crawl4ai, this might take a few seconds to load required model files." - ) - - crawler = create_crawler() - - crawler.always_by_pass_cache = True - basic_usage(crawler) - # basic_usage_some_params(crawler) - understanding_parameters(crawler) - - crawler.always_by_pass_cache = True - screenshot_usage(crawler) - add_chunking_strategy(crawler) - add_extraction_strategy(crawler) - add_llm_extraction_strategy(crawler) - targeted_extraction(crawler) - interactive_extraction(crawler) - multiple_scrip(crawler) - - cprint( - "\n🎉 [bold green]Congratulations! You've made it through the Crawl4ai Quickstart Guide! Now go forth and crawl the web like a pro! 🕸️[/bold green]" - ) - - -if __name__ == "__main__": - main() diff --git a/docs/examples/quickstart_v0.ipynb b/docs/examples/quickstart_v0.ipynb deleted file mode 100644 index 0282aa12..00000000 --- a/docs/examples/quickstart_v0.ipynb +++ /dev/null @@ -1,735 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "6yLvrXn7yZQI" - }, - "source": [ - "# Crawl4AI: Advanced Web Crawling and Data Extraction\n", - "\n", - "Welcome to this interactive notebook showcasing Crawl4AI, an advanced asynchronous web crawling and data extraction library.\n", - "\n", - "- GitHub Repository: [https://github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)\n", - "- Twitter: [@unclecode](https://twitter.com/unclecode)\n", - "- Website: [https://crawl4ai.com](https://crawl4ai.com)\n", - "\n", - "Let's explore the powerful features of Crawl4AI!" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "KIn_9nxFyZQK" - }, - "source": [ - "## Installation\n", - "\n", - "First, let's install Crawl4AI from GitHub:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "mSnaxLf3zMog" - }, - "outputs": [], - "source": [ - "!sudo apt-get update && sudo apt-get install -y libwoff1 libopus0 libwebp6 libwebpdemux2 libenchant1c2a libgudev-1.0-0 libsecret-1-0 libhyphen0 libgdk-pixbuf2.0-0 libegl1 libnotify4 libxslt1.1 libevent-2.1-7 libgles2 libvpx6 libxcomposite1 libatk1.0-0 libatk-bridge2.0-0 libepoxy0 libgtk-3-0 libharfbuzz-icu0" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "xlXqaRtayZQK" - }, - "outputs": [], - "source": [ - "!pip install crawl4ai\n", - "!pip install nest-asyncio\n", - "!playwright install" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "qKCE7TI7yZQL" - }, - "source": [ - "Now, let's import the necessary libraries:" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": { - "id": "I67tr7aAyZQL" - }, - "outputs": [], - "source": [ - "import asyncio\n", - "import nest_asyncio\n", - "from crawl4ai import AsyncWebCrawler\n", - "from crawl4ai.extraction_strategy import JsonCssExtractionStrategy, LLMExtractionStrategy\n", - "import json\n", - "import time\n", - "from pydantic import BaseModel, Field\n", - "\n", - "nest_asyncio.apply()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "h7yR_Rt_yZQM" - }, - "source": [ - "## Basic Usage\n", - "\n", - "Let's start with a simple crawl example:" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "yBh6hf4WyZQM", - "outputId": "0f83af5c-abba-4175-ed95-70b7512e6bcc" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[LOG] 🌤️ Warming up the AsyncWebCrawler\n", - "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n", - "[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.05 seconds\n", - "[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.05 seconds.\n", - "18102\n" - ] - } - ], - "source": [ - "async def simple_crawl():\n", - " async with AsyncWebCrawler(verbose=True) as crawler:\n", - " result = await crawler.arun(url=\"https://www.nbcnews.com/business\")\n", - " print(len(result.markdown))\n", - "await simple_crawl()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "9rtkgHI28uI4" - }, - "source": [ - "💡 By default, **Crawl4AI** caches the result of every URL, so the next time you call it, you’ll get an instant result. But if you want to bypass the cache, just set `bypass_cache=True`." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "MzZ0zlJ9yZQM" - }, - "source": [ - "## Advanced Features\n", - "\n", - "### Executing JavaScript and Using CSS Selectors" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "gHStF86xyZQM", - "outputId": "34d0fb6d-4dec-4677-f76e-85a1f082829b" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[LOG] 🌤️ Warming up the AsyncWebCrawler\n", - "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n", - "[LOG] 🕸️ Crawling https://www.nbcnews.com/business using AsyncPlaywrightCrawlerStrategy...\n", - "[LOG] ✅ Crawled https://www.nbcnews.com/business successfully!\n", - "[LOG] 🚀 Crawling done for https://www.nbcnews.com/business, success: True, time taken: 6.06 seconds\n", - "[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.10 seconds\n", - "[LOG] 🔥 Extracting semantic blocks for https://www.nbcnews.com/business, Strategy: AsyncWebCrawler\n", - "[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.11 seconds.\n", - "41135\n" - ] - } - ], - "source": [ - "async def js_and_css():\n", - " async with AsyncWebCrawler(verbose=True) as crawler:\n", - " js_code = [\"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();\"]\n", - " result = await crawler.arun(\n", - " url=\"https://www.nbcnews.com/business\",\n", - " js_code=js_code,\n", - " # css_selector=\"YOUR_CSS_SELECTOR_HERE\",\n", - " bypass_cache=True\n", - " )\n", - " print(len(result.markdown))\n", - "\n", - "await js_and_css()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "cqE_W4coyZQM" - }, - "source": [ - "### Using a Proxy\n", - "\n", - "Note: You'll need to replace the proxy URL with a working proxy for this example to run successfully." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "QjAyiAGqyZQM" - }, - "outputs": [], - "source": [ - "async def use_proxy():\n", - " async with AsyncWebCrawler(verbose=True, proxy=\"http://your-proxy-url:port\") as crawler:\n", - " result = await crawler.arun(\n", - " url=\"https://www.nbcnews.com/business\",\n", - " bypass_cache=True\n", - " )\n", - " print(result.markdown[:500]) # Print first 500 characters\n", - "\n", - "# Uncomment the following line to run the proxy example\n", - "# await use_proxy()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "XTZ88lbayZQN" - }, - "source": [ - "### Extracting Structured Data with OpenAI\n", - "\n", - "Note: You'll need to set your OpenAI API key as an environment variable for this example to work." - ] - }, - { - "cell_type": "code", - "execution_count": 14, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "fIOlDayYyZQN", - "outputId": "cb8359cc-dee0-4762-9698-5dfdcee055b8" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[LOG] 🌤️ Warming up the AsyncWebCrawler\n", - "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n", - "[LOG] 🕸️ Crawling https://openai.com/api/pricing/ using AsyncPlaywrightCrawlerStrategy...\n", - "[LOG] ✅ Crawled https://openai.com/api/pricing/ successfully!\n", - "[LOG] 🚀 Crawling done for https://openai.com/api/pricing/, success: True, time taken: 3.77 seconds\n", - "[LOG] 🚀 Content extracted for https://openai.com/api/pricing/, success: True, time taken: 0.21 seconds\n", - "[LOG] 🔥 Extracting semantic blocks for https://openai.com/api/pricing/, Strategy: AsyncWebCrawler\n", - "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 0\n", - "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 1\n", - "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 2\n", - "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 3\n", - "[LOG] Extracted 4 blocks from URL: https://openai.com/api/pricing/ block index: 3\n", - "[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 4\n", - "[LOG] Extracted 5 blocks from URL: https://openai.com/api/pricing/ block index: 0\n", - "[LOG] Extracted 1 blocks from URL: https://openai.com/api/pricing/ block index: 4\n", - "[LOG] Extracted 8 blocks from URL: https://openai.com/api/pricing/ block index: 1\n", - "[LOG] Extracted 12 blocks from URL: https://openai.com/api/pricing/ block index: 2\n", - "[LOG] 🚀 Extraction done for https://openai.com/api/pricing/, time taken: 8.55 seconds.\n", - "5029\n" - ] - } - ], - "source": [ - "import os\n", - "from google.colab import userdata\n", - "os.environ['OPENAI_API_KEY'] = userdata.get('OPENAI_API_KEY')\n", - "\n", - "class OpenAIModelFee(BaseModel):\n", - " model_name: str = Field(..., description=\"Name of the OpenAI model.\")\n", - " input_fee: str = Field(..., description=\"Fee for input token for the OpenAI model.\")\n", - " output_fee: str = Field(..., description=\"Fee for output token for the OpenAI model.\")\n", - "\n", - "async def extract_openai_fees():\n", - " async with AsyncWebCrawler(verbose=True) as crawler:\n", - " result = await crawler.arun(\n", - " url='https://openai.com/api/pricing/',\n", - " word_count_threshold=1,\n", - " extraction_strategy=LLMExtractionStrategy(\n", - " provider=\"openai/gpt-4o\", api_token=os.getenv('OPENAI_API_KEY'),\n", - " schema=OpenAIModelFee.schema(),\n", - " extraction_type=\"schema\",\n", - " instruction=\"\"\"From the crawled content, extract all mentioned model names along with their fees for input and output tokens.\n", - " Do not miss any models in the entire content. One extracted model JSON format should look like this:\n", - " {\"model_name\": \"GPT-4\", \"input_fee\": \"US$10.00 / 1M tokens\", \"output_fee\": \"US$30.00 / 1M tokens\"}.\"\"\"\n", - " ),\n", - " bypass_cache=True,\n", - " )\n", - " print(len(result.extracted_content))\n", - "\n", - "# Uncomment the following line to run the OpenAI extraction example\n", - "await extract_openai_fees()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "BypA5YxEyZQN" - }, - "source": [ - "### Advanced Multi-Page Crawling with JavaScript Execution" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "tfkcVQ0b7mw-" - }, - "source": [ - "## Advanced Multi-Page Crawling with JavaScript Execution\n", - "\n", - "This example demonstrates Crawl4AI's ability to handle complex crawling scenarios, specifically extracting commits from multiple pages of a GitHub repository. The challenge here is that clicking the \"Next\" button doesn't load a new page, but instead uses asynchronous JavaScript to update the content. This is a common hurdle in modern web crawling.\n", - "\n", - "To overcome this, we use Crawl4AI's custom JavaScript execution to simulate clicking the \"Next\" button, and implement a custom hook to detect when new data has loaded. Our strategy involves comparing the first commit's text before and after \"clicking\" Next, waiting until it changes to confirm new data has rendered. This showcases Crawl4AI's flexibility in handling dynamic content and its ability to implement custom logic for even the most challenging crawling tasks." - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "qUBKGpn3yZQN", - "outputId": "3e555b6a-ed33-42f4-cce9-499a923fbe17" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[LOG] 🌤️ Warming up the AsyncWebCrawler\n", - "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n", - "[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n", - "[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n", - "[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 5.16 seconds\n", - "[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.28 seconds\n", - "[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n", - "[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.28 seconds.\n", - "Page 1: Found 35 commits\n", - "[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n", - "[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n", - "[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.78 seconds\n", - "[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.90 seconds\n", - "[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n", - "[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.90 seconds.\n", - "Page 2: Found 35 commits\n", - "[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n", - "[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n", - "[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 2.00 seconds\n", - "[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.74 seconds\n", - "[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n", - "[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.75 seconds.\n", - "Page 3: Found 35 commits\n", - "Successfully crawled 105 commits across 3 pages\n" - ] - } - ], - "source": [ - "import re\n", - "from bs4 import BeautifulSoup\n", - "\n", - "async def crawl_typescript_commits():\n", - " first_commit = \"\"\n", - " async def on_execution_started(page):\n", - " nonlocal first_commit\n", - " try:\n", - " while True:\n", - " await page.wait_for_selector('li.Box-sc-g0xbh4-0 h4')\n", - " commit = await page.query_selector('li.Box-sc-g0xbh4-0 h4')\n", - " commit = await commit.evaluate('(element) => element.textContent')\n", - " commit = re.sub(r'\\s+', '', commit)\n", - " if commit and commit != first_commit:\n", - " first_commit = commit\n", - " break\n", - " await asyncio.sleep(0.5)\n", - " except Exception as e:\n", - " print(f\"Warning: New content didn't appear after JavaScript execution: {e}\")\n", - "\n", - " async with AsyncWebCrawler(verbose=True) as crawler:\n", - " crawler.crawler_strategy.set_hook('on_execution_started', on_execution_started)\n", - "\n", - " url = \"https://github.com/microsoft/TypeScript/commits/main\"\n", - " session_id = \"typescript_commits_session\"\n", - " all_commits = []\n", - "\n", - " js_next_page = \"\"\"\n", - " const button = document.querySelector('a[data-testid=\"pagination-next-button\"]');\n", - " if (button) button.click();\n", - " \"\"\"\n", - "\n", - " for page in range(3): # Crawl 3 pages\n", - " result = await crawler.arun(\n", - " url=url,\n", - " session_id=session_id,\n", - " css_selector=\"li.Box-sc-g0xbh4-0\",\n", - " js=js_next_page if page > 0 else None,\n", - " bypass_cache=True,\n", - " js_only=page > 0\n", - " )\n", - "\n", - " assert result.success, f\"Failed to crawl page {page + 1}\"\n", - "\n", - " soup = BeautifulSoup(result.cleaned_html, 'html.parser')\n", - " commits = soup.select(\"li\")\n", - " all_commits.extend(commits)\n", - "\n", - " print(f\"Page {page + 1}: Found {len(commits)} commits\")\n", - "\n", - " await crawler.crawler_strategy.kill_session(session_id)\n", - " print(f\"Successfully crawled {len(all_commits)} commits across 3 pages\")\n", - "\n", - "await crawl_typescript_commits()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "EJRnYsp6yZQN" - }, - "source": [ - "### Using JsonCssExtractionStrategy for Fast Structured Output" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "1ZMqIzB_8SYp" - }, - "source": [ - "The JsonCssExtractionStrategy is a powerful feature of Crawl4AI that allows for precise, structured data extraction from web pages. Here's how it works:\n", - "\n", - "1. You define a schema that describes the pattern of data you're interested in extracting.\n", - "2. The schema includes a base selector that identifies repeating elements on the page.\n", - "3. Within the schema, you define fields, each with its own selector and type.\n", - "4. These field selectors are applied within the context of each base selector element.\n", - "5. The strategy supports nested structures, lists within lists, and various data types.\n", - "6. You can even include computed fields for more complex data manipulation.\n", - "\n", - "This approach allows for highly flexible and precise data extraction, transforming semi-structured web content into clean, structured JSON data. It's particularly useful for extracting consistent data patterns from pages like product listings, news articles, or search results.\n", - "\n", - "For more details and advanced usage, check out the full documentation on the Crawl4AI website." - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "trCMR2T9yZQN", - "outputId": "718d36f4-cccf-40f4-8d8c-c3ba73524d16" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[LOG] 🌤️ Warming up the AsyncWebCrawler\n", - "[LOG] 🌞 AsyncWebCrawler is ready to crawl\n", - "[LOG] 🕸️ Crawling https://www.nbcnews.com/business using AsyncPlaywrightCrawlerStrategy...\n", - "[LOG] ✅ Crawled https://www.nbcnews.com/business successfully!\n", - "[LOG] 🚀 Crawling done for https://www.nbcnews.com/business, success: True, time taken: 7.00 seconds\n", - "[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.32 seconds\n", - "[LOG] 🔥 Extracting semantic blocks for https://www.nbcnews.com/business, Strategy: AsyncWebCrawler\n", - "[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.48 seconds.\n", - "Successfully extracted 11 news teasers\n", - "{\n", - " \"category\": \"Business News\",\n", - " \"headline\": \"NBC ripped up its Olympics playbook for 2024 \\u2014 so far, the new strategy paid off\",\n", - " \"summary\": \"The Olympics have long been key to NBCUniversal. Paris marked the 18th Olympic Games broadcast by NBC in the U.S.\",\n", - " \"time\": \"13h ago\",\n", - " \"image\": {\n", - " \"src\": \"https://media-cldnry.s-nbcnews.com/image/upload/t_focal-200x100,f_auto,q_auto:best/rockcms/2024-09/240903-nbc-olympics-ch-1344-c7a486.jpg\",\n", - " \"alt\": \"Mike Tirico.\"\n", - " },\n", - " \"link\": \"https://www.nbcnews.com/business\"\n", - "}\n" - ] - } - ], - "source": [ - "async def extract_news_teasers():\n", - " schema = {\n", - " \"name\": \"News Teaser Extractor\",\n", - " \"baseSelector\": \".wide-tease-item__wrapper\",\n", - " \"fields\": [\n", - " {\n", - " \"name\": \"category\",\n", - " \"selector\": \".unibrow span[data-testid='unibrow-text']\",\n", - " \"type\": \"text\",\n", - " },\n", - " {\n", - " \"name\": \"headline\",\n", - " \"selector\": \".wide-tease-item__headline\",\n", - " \"type\": \"text\",\n", - " },\n", - " {\n", - " \"name\": \"summary\",\n", - " \"selector\": \".wide-tease-item__description\",\n", - " \"type\": \"text\",\n", - " },\n", - " {\n", - " \"name\": \"time\",\n", - " \"selector\": \"[data-testid='wide-tease-date']\",\n", - " \"type\": \"text\",\n", - " },\n", - " {\n", - " \"name\": \"image\",\n", - " \"type\": \"nested\",\n", - " \"selector\": \"picture.teasePicture img\",\n", - " \"fields\": [\n", - " {\"name\": \"src\", \"type\": \"attribute\", \"attribute\": \"src\"},\n", - " {\"name\": \"alt\", \"type\": \"attribute\", \"attribute\": \"alt\"},\n", - " ],\n", - " },\n", - " {\n", - " \"name\": \"link\",\n", - " \"selector\": \"a[href]\",\n", - " \"type\": \"attribute\",\n", - " \"attribute\": \"href\",\n", - " },\n", - " ],\n", - " }\n", - "\n", - " extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)\n", - "\n", - " async with AsyncWebCrawler(verbose=True) as crawler:\n", - " result = await crawler.arun(\n", - " url=\"https://www.nbcnews.com/business\",\n", - " extraction_strategy=extraction_strategy,\n", - " bypass_cache=True,\n", - " )\n", - "\n", - " assert result.success, \"Failed to crawl the page\"\n", - "\n", - " news_teasers = json.loads(result.extracted_content)\n", - " print(f\"Successfully extracted {len(news_teasers)} news teasers\")\n", - " print(json.dumps(news_teasers[0], indent=2))\n", - "\n", - "await extract_news_teasers()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "FnyVhJaByZQN" - }, - "source": [ - "## Speed Comparison\n", - "\n", - "Let's compare the speed of Crawl4AI with Firecrawl, a paid service. Note that we can't run Firecrawl in this Colab environment, so we'll simulate its performance based on previously recorded data." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "agDD186f3wig" - }, - "source": [ - "💡 **Note on Speed Comparison:**\n", - "\n", - "The speed test conducted here is running on Google Colab, where the internet speed and performance can vary and may not reflect optimal conditions. When we call Firecrawl's API, we're seeing its best performance, while Crawl4AI's performance is limited by Colab's network speed.\n", - "\n", - "For a more accurate comparison, it's recommended to run these tests on your own servers or computers with a stable and fast internet connection. Despite these limitations, Crawl4AI still demonstrates faster performance in this environment.\n", - "\n", - "If you run these tests locally, you may observe an even more significant speed advantage for Crawl4AI compared to other services." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "F7KwHv8G1LbY" - }, - "outputs": [], - "source": [ - "!pip install firecrawl" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "91813zILyZQN", - "outputId": "663223db-ab89-4976-b233-05ceca62b19b" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Firecrawl (simulated):\n", - "Time taken: 4.38 seconds\n", - "Content length: 41967 characters\n", - "Images found: 49\n", - "\n", - "Crawl4AI (simple crawl):\n", - "Time taken: 4.22 seconds\n", - "Content length: 18221 characters\n", - "Images found: 49\n", - "\n", - "Crawl4AI (with JavaScript execution):\n", - "Time taken: 9.13 seconds\n", - "Content length: 34243 characters\n", - "Images found: 89\n" - ] - } - ], - "source": [ - "import os\n", - "from google.colab import userdata\n", - "os.environ['FIRECRAWL_API_KEY'] = userdata.get('FIRECRAWL_API_KEY')\n", - "import time\n", - "from firecrawl import FirecrawlApp\n", - "\n", - "async def speed_comparison():\n", - " # Simulated Firecrawl performance\n", - " app = FirecrawlApp(api_key=os.environ['FIRECRAWL_API_KEY'])\n", - " start = time.time()\n", - " scrape_status = app.scrape_url(\n", - " 'https://www.nbcnews.com/business',\n", - " params={'formats': ['markdown', 'html']}\n", - " )\n", - " end = time.time()\n", - " print(\"Firecrawl (simulated):\")\n", - " print(f\"Time taken: {end - start:.2f} seconds\")\n", - " print(f\"Content length: {len(scrape_status['markdown'])} characters\")\n", - " print(f\"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}\")\n", - " print()\n", - "\n", - " async with AsyncWebCrawler() as crawler:\n", - " # Crawl4AI simple crawl\n", - " start = time.time()\n", - " result = await crawler.arun(\n", - " url=\"https://www.nbcnews.com/business\",\n", - " word_count_threshold=0,\n", - " bypass_cache=True,\n", - " verbose=False\n", - " )\n", - " end = time.time()\n", - " print(\"Crawl4AI (simple crawl):\")\n", - " print(f\"Time taken: {end - start:.2f} seconds\")\n", - " print(f\"Content length: {len(result.markdown)} characters\")\n", - " print(f\"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}\")\n", - " print()\n", - "\n", - " # Crawl4AI with JavaScript execution\n", - " start = time.time()\n", - " result = await crawler.arun(\n", - " url=\"https://www.nbcnews.com/business\",\n", - " js_code=[\"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();\"],\n", - " word_count_threshold=0,\n", - " bypass_cache=True,\n", - " verbose=False\n", - " )\n", - " end = time.time()\n", - " print(\"Crawl4AI (with JavaScript execution):\")\n", - " print(f\"Time taken: {end - start:.2f} seconds\")\n", - " print(f\"Content length: {len(result.markdown)} characters\")\n", - " print(f\"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}\")\n", - "\n", - "await speed_comparison()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "OBFFYVJIyZQN" - }, - "source": [ - "If you run on a local machine with a proper internet speed:\n", - "- Simple crawl: Crawl4AI is typically over 3-4 times faster than Firecrawl.\n", - "- With JavaScript execution: Even when executing JavaScript to load more content (potentially doubling the number of images found), Crawl4AI is still faster than Firecrawl's simple crawl.\n", - "\n", - "Please note that actual performance may vary depending on network conditions and the specific content being crawled." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "A6_1RK1_yZQO" - }, - "source": [ - "## Conclusion\n", - "\n", - "In this notebook, we've explored the powerful features of Crawl4AI, including:\n", - "\n", - "1. Basic crawling\n", - "2. JavaScript execution and CSS selector usage\n", - "3. Proxy support\n", - "4. Structured data extraction with OpenAI\n", - "5. Advanced multi-page crawling with JavaScript execution\n", - "6. Fast structured output using JsonCssExtractionStrategy\n", - "7. Speed comparison with other services\n", - "\n", - "Crawl4AI offers a fast, flexible, and powerful solution for web crawling and data extraction tasks. Its asynchronous architecture and advanced features make it suitable for a wide range of applications, from simple web scraping to complex, multi-page data extraction scenarios.\n", - "\n", - "For more information and advanced usage, please visit the [Crawl4AI documentation](https://docs.crawl4ai.com/).\n", - "\n", - "Happy crawling!" - ] - } - ], - "metadata": { - "colab": { - "provenance": [] - }, - "kernelspec": { - "display_name": "venv", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.10.13" - } - }, - "nbformat": 4, - "nbformat_minor": 0 -} diff --git a/docs/md_v2/advanced/network-console-capture.md b/docs/md_v2/advanced/network-console-capture.md new file mode 100644 index 00000000..4305a25f --- /dev/null +++ b/docs/md_v2/advanced/network-console-capture.md @@ -0,0 +1,205 @@ +# Network Requests & Console Message Capturing + +Crawl4AI can capture all network requests and browser console messages during a crawl, which is invaluable for debugging, security analysis, or understanding page behavior. + +## Configuration + +To enable network and console capturing, use these configuration options: + +```python +from crawl4ai import AsyncWebCrawler, CrawlerRunConfig + +# Enable both network request capture and console message capture +config = CrawlerRunConfig( + capture_network_requests=True, # Capture all network requests and responses + capture_console_messages=True # Capture all browser console output +) +``` + +## Example Usage + +```python +import asyncio +import json +from crawl4ai import AsyncWebCrawler, CrawlerRunConfig + +async def main(): + # Enable both network request capture and console message capture + config = CrawlerRunConfig( + capture_network_requests=True, + capture_console_messages=True + ) + + async with AsyncWebCrawler() as crawler: + result = await crawler.arun( + url="https://example.com", + config=config + ) + + if result.success: + # Analyze network requests + if result.network_requests: + print(f"Captured {len(result.network_requests)} network events") + + # Count request types + request_count = len([r for r in result.network_requests if r.get("event_type") == "request"]) + response_count = len([r for r in result.network_requests if r.get("event_type") == "response"]) + failed_count = len([r for r in result.network_requests if r.get("event_type") == "request_failed"]) + + print(f"Requests: {request_count}, Responses: {response_count}, Failed: {failed_count}") + + # Find API calls + api_calls = [r for r in result.network_requests + if r.get("event_type") == "request" and "api" in r.get("url", "")] + if api_calls: + print(f"Detected {len(api_calls)} API calls:") + for call in api_calls[:3]: # Show first 3 + print(f" - {call.get('method')} {call.get('url')}") + + # Analyze console messages + if result.console_messages: + print(f"Captured {len(result.console_messages)} console messages") + + # Group by type + message_types = {} + for msg in result.console_messages: + msg_type = msg.get("type", "unknown") + message_types[msg_type] = message_types.get(msg_type, 0) + 1 + + print("Message types:", message_types) + + # Show errors (often the most important) + errors = [msg for msg in result.console_messages if msg.get("type") == "error"] + if errors: + print(f"Found {len(errors)} console errors:") + for err in errors[:2]: # Show first 2 + print(f" - {err.get('text', '')[:100]}") + + # Export all captured data to a file for detailed analysis + with open("network_capture.json", "w") as f: + json.dump({ + "url": result.url, + "network_requests": result.network_requests or [], + "console_messages": result.console_messages or [] + }, f, indent=2) + + print("Exported detailed capture data to network_capture.json") + +if __name__ == "__main__": + asyncio.run(main()) +``` + +## Captured Data Structure + +### Network Requests + +The `result.network_requests` contains a list of dictionaries, each representing a network event with these common fields: + +| Field | Description | +|-------|-------------| +| `event_type` | Type of event: `"request"`, `"response"`, or `"request_failed"` | +| `url` | The URL of the request | +| `timestamp` | Unix timestamp when the event was captured | + +#### Request Event Fields + +```json +{ + "event_type": "request", + "url": "https://example.com/api/data.json", + "method": "GET", + "headers": {"User-Agent": "...", "Accept": "..."}, + "post_data": "key=value&otherkey=value", + "resource_type": "fetch", + "is_navigation_request": false, + "timestamp": 1633456789.123 +} +``` + +#### Response Event Fields + +```json +{ + "event_type": "response", + "url": "https://example.com/api/data.json", + "status": 200, + "status_text": "OK", + "headers": {"Content-Type": "application/json", "Cache-Control": "..."}, + "from_service_worker": false, + "request_timing": {"requestTime": 1234.56, "receiveHeadersEnd": 1234.78}, + "timestamp": 1633456789.456 +} +``` + +#### Failed Request Event Fields + +```json +{ + "event_type": "request_failed", + "url": "https://example.com/missing.png", + "method": "GET", + "resource_type": "image", + "failure_text": "net::ERR_ABORTED 404", + "timestamp": 1633456789.789 +} +``` + +### Console Messages + +The `result.console_messages` contains a list of dictionaries, each representing a console message with these common fields: + +| Field | Description | +|-------|-------------| +| `type` | Message type: `"log"`, `"error"`, `"warning"`, `"info"`, etc. | +| `text` | The message text | +| `timestamp` | Unix timestamp when the message was captured | + +#### Console Message Example + +```json +{ + "type": "error", + "text": "Uncaught TypeError: Cannot read property 'length' of undefined", + "location": "https://example.com/script.js:123:45", + "timestamp": 1633456790.123 +} +``` + +## Key Benefits + +- **Full Request Visibility**: Capture all network activity including: + - Requests (URLs, methods, headers, post data) + - Responses (status codes, headers, timing) + - Failed requests (with error messages) + +- **Console Message Access**: View all JavaScript console output: + - Log messages + - Warnings + - Errors with stack traces + - Developer debugging information + +- **Debugging Power**: Identify issues such as: + - Failed API calls or resource loading + - JavaScript errors affecting page functionality + - CORS or other security issues + - Hidden API endpoints and data flows + +- **Security Analysis**: Detect: + - Unexpected third-party requests + - Data leakage in request payloads + - Suspicious script behavior + +- **Performance Insights**: Analyze: + - Request timing data + - Resource loading patterns + - Potential bottlenecks + +## Use Cases + +1. **API Discovery**: Identify hidden endpoints and data flows in single-page applications +2. **Debugging**: Track down JavaScript errors affecting page functionality +3. **Security Auditing**: Detect unwanted third-party requests or data leakage +4. **Performance Analysis**: Identify slow-loading resources +5. **Ad/Tracker Analysis**: Detect and catalog advertising or tracking calls + +This capability is especially valuable for complex sites with heavy JavaScript, single-page applications, or when you need to understand the exact communication happening between a browser and servers. \ No newline at end of file diff --git a/docs/md_v2/api/crawl-result.md b/docs/md_v2/api/crawl-result.md index 4c42009b..52cf6ace 100644 --- a/docs/md_v2/api/crawl-result.md +++ b/docs/md_v2/api/crawl-result.md @@ -15,6 +15,7 @@ class CrawlResult(BaseModel): downloaded_files: Optional[List[str]] = None screenshot: Optional[str] = None pdf : Optional[bytes] = None + mhtml: Optional[str] = None markdown: Optional[Union[str, MarkdownGenerationResult]] = None extracted_content: Optional[str] = None metadata: Optional[dict] = None @@ -236,7 +237,16 @@ if result.pdf: f.write(result.pdf) ``` -### 5.5 **`metadata`** *(Optional[dict])* +### 5.5 **`mhtml`** *(Optional[str])* +**What**: MHTML snapshot of the page if `capture_mhtml=True` in `CrawlerRunConfig`. MHTML (MIME HTML) format preserves the entire web page with all its resources (CSS, images, scripts, etc.) in a single file. +**Usage**: +```python +if result.mhtml: + with open("page.mhtml", "w", encoding="utf-8") as f: + f.write(result.mhtml) +``` + +### 5.6 **`metadata`** *(Optional[dict])* **What**: Page-level metadata if discovered (title, description, OG data, etc.). **Usage**: ```python @@ -271,7 +281,69 @@ for result in results: --- -## 7. Example: Accessing Everything +## 7. Network Requests & Console Messages + +When you enable network and console message capturing in `CrawlerRunConfig` using `capture_network_requests=True` and `capture_console_messages=True`, the `CrawlResult` will include these fields: + +### 7.1 **`network_requests`** *(Optional[List[Dict[str, Any]]])* +**What**: A list of dictionaries containing information about all network requests, responses, and failures captured during the crawl. +**Structure**: +- Each item has an `event_type` field that can be `"request"`, `"response"`, or `"request_failed"`. +- Request events include `url`, `method`, `headers`, `post_data`, `resource_type`, and `is_navigation_request`. +- Response events include `url`, `status`, `status_text`, `headers`, and `request_timing`. +- Failed request events include `url`, `method`, `resource_type`, and `failure_text`. +- All events include a `timestamp` field. + +**Usage**: +```python +if result.network_requests: + # Count different types of events + requests = [r for r in result.network_requests if r.get("event_type") == "request"] + responses = [r for r in result.network_requests if r.get("event_type") == "response"] + failures = [r for r in result.network_requests if r.get("event_type") == "request_failed"] + + print(f"Captured {len(requests)} requests, {len(responses)} responses, and {len(failures)} failures") + + # Analyze API calls + api_calls = [r for r in requests if "api" in r.get("url", "")] + + # Identify failed resources + for failure in failures: + print(f"Failed to load: {failure.get('url')} - {failure.get('failure_text')}") +``` + +### 7.2 **`console_messages`** *(Optional[List[Dict[str, Any]]])* +**What**: A list of dictionaries containing all browser console messages captured during the crawl. +**Structure**: +- Each item has a `type` field indicating the message type (e.g., `"log"`, `"error"`, `"warning"`, etc.). +- The `text` field contains the actual message text. +- Some messages include `location` information (URL, line, column). +- All messages include a `timestamp` field. + +**Usage**: +```python +if result.console_messages: + # Count messages by type + message_types = {} + for msg in result.console_messages: + msg_type = msg.get("type", "unknown") + message_types[msg_type] = message_types.get(msg_type, 0) + 1 + + print(f"Message type counts: {message_types}") + + # Display errors (which are usually most important) + for msg in result.console_messages: + if msg.get("type") == "error": + print(f"Error: {msg.get('text')}") +``` + +These fields provide deep visibility into the page's network activity and browser console, which is invaluable for debugging, security analysis, and understanding complex web applications. + +For more details on network and console capturing, see the [Network & Console Capture documentation](../advanced/network-console-capture.md). + +--- + +## 8. Example: Accessing Everything ```python async def handle_result(result: CrawlResult): @@ -304,16 +376,36 @@ async def handle_result(result: CrawlResult): if result.extracted_content: print("Structured data:", result.extracted_content) - # Screenshot/PDF + # Screenshot/PDF/MHTML if result.screenshot: print("Screenshot length:", len(result.screenshot)) if result.pdf: print("PDF bytes length:", len(result.pdf)) + if result.mhtml: + print("MHTML length:", len(result.mhtml)) + + # Network and console capturing + if result.network_requests: + print(f"Network requests captured: {len(result.network_requests)}") + # Analyze request types + req_types = {} + for req in result.network_requests: + if "resource_type" in req: + req_types[req["resource_type"]] = req_types.get(req["resource_type"], 0) + 1 + print(f"Resource types: {req_types}") + + if result.console_messages: + print(f"Console messages captured: {len(result.console_messages)}") + # Count by message type + msg_types = {} + for msg in result.console_messages: + msg_types[msg.get("type", "unknown")] = msg_types.get(msg.get("type", "unknown"), 0) + 1 + print(f"Message types: {msg_types}") ``` --- -## 8. Key Points & Future +## 9. Key Points & Future 1. **Deprecated legacy properties of CrawlResult** - `markdown_v2` - Deprecated in v0.5. Just use `markdown`. It holds the `MarkdownGenerationResult` now! diff --git a/docs/md_v2/api/parameters.md b/docs/md_v2/api/parameters.md index 7e615a8c..494378a4 100644 --- a/docs/md_v2/api/parameters.md +++ b/docs/md_v2/api/parameters.md @@ -141,6 +141,7 @@ If your page is a single-page app with repeated JS updates, set `js_only=True` i | **`screenshot_wait_for`** | `float or None` | Extra wait time before the screenshot. | | **`screenshot_height_threshold`** | `int` (~20000) | If the page is taller than this, alternate screenshot strategies are used. | | **`pdf`** | `bool` (False) | If `True`, returns a PDF in `result.pdf`. | +| **`capture_mhtml`** | `bool` (False) | If `True`, captures an MHTML snapshot of the page in `result.mhtml`. MHTML includes all page resources (CSS, images, etc.) in a single file. | | **`image_description_min_word_threshold`** | `int` (~50) | Minimum words for an image’s alt text or description to be considered valid. | | **`image_score_threshold`** | `int` (~3) | Filter out low-scoring images. The crawler scores images by relevance (size, context, etc.). | | **`exclude_external_images`** | `bool` (False) | Exclude images from other domains. | diff --git a/docs/md_v2/core/browser-crawler-config.md b/docs/md_v2/core/browser-crawler-config.md index a080fca3..a031acf7 100644 --- a/docs/md_v2/core/browser-crawler-config.md +++ b/docs/md_v2/core/browser-crawler-config.md @@ -136,6 +136,12 @@ class CrawlerRunConfig: wait_for=None, screenshot=False, pdf=False, + capture_mhtml=False, + enable_rate_limiting=False, + rate_limit_config=None, + memory_threshold_percent=70.0, + check_interval=1.0, + max_session_permit=20, display_mode=None, verbose=True, stream=False, # Enable streaming for arun_many() @@ -170,10 +176,9 @@ class CrawlerRunConfig: - A CSS or JS expression to wait for before extracting content. - Common usage: `wait_for="css:.main-loaded"` or `wait_for="js:() => window.loaded === true"`. -7. **`screenshot`** & **`pdf`**: - - If `True`, captures a screenshot or PDF after the page is fully loaded. - - The results go to `result.screenshot` (base64) or `result.pdf` (bytes). - +7. **`screenshot`**, **`pdf`**, & **`capture_mhtml`**: + - If `True`, captures a screenshot, PDF, or MHTML snapshot after the page is fully loaded. + - The results go to `result.screenshot` (base64), `result.pdf` (bytes), or `result.mhtml` (string). 8. **`verbose`**: - Logs additional runtime details. - Overlaps with the browser’s verbosity if also set to `True` in `BrowserConfig`. diff --git a/docs/md_v2/core/crawler-result.md b/docs/md_v2/core/crawler-result.md index 961b38f6..d7648ecb 100644 --- a/docs/md_v2/core/crawler-result.md +++ b/docs/md_v2/core/crawler-result.md @@ -26,6 +26,7 @@ class CrawlResult(BaseModel): downloaded_files: Optional[List[str]] = None screenshot: Optional[str] = None pdf : Optional[bytes] = None + mhtml: Optional[str] = None markdown: Optional[Union[str, MarkdownGenerationResult]] = None extracted_content: Optional[str] = None metadata: Optional[dict] = None @@ -51,6 +52,7 @@ class CrawlResult(BaseModel): | **downloaded_files (`Optional[List[str]]`)** | If `accept_downloads=True` in `BrowserConfig`, this lists the filepaths of saved downloads. | | **screenshot (`Optional[str]`)** | Screenshot of the page (base64-encoded) if `screenshot=True`. | | **pdf (`Optional[bytes]`)** | PDF of the page if `pdf=True`. | +| **mhtml (`Optional[str]`)** | MHTML snapshot of the page if `capture_mhtml=True`. Contains the full page with all resources. | | **markdown (`Optional[str or MarkdownGenerationResult]`)** | It holds a `MarkdownGenerationResult`. Over time, this will be consolidated into `markdown`. The generator can provide raw markdown, citations, references, and optionally `fit_markdown`. | | **extracted_content (`Optional[str]`)** | The output of a structured extraction (CSS/LLM-based) stored as JSON string or other text. | | **metadata (`Optional[dict]`)** | Additional info about the crawl or extracted data. | @@ -190,18 +192,27 @@ for img in images: print("Image URL:", img["src"], "Alt:", img.get("alt")) ``` -### 5.3 `screenshot` and `pdf` +### 5.3 `screenshot`, `pdf`, and `mhtml` -If you set `screenshot=True` or `pdf=True` in **`CrawlerRunConfig`**, then: +If you set `screenshot=True`, `pdf=True`, or `capture_mhtml=True` in **`CrawlerRunConfig`**, then: -- `result.screenshot` contains a base64-encoded PNG string. +- `result.screenshot` contains a base64-encoded PNG string. - `result.pdf` contains raw PDF bytes (you can write them to a file). +- `result.mhtml` contains the MHTML snapshot of the page as a string (you can write it to a .mhtml file). ```python +# Save the PDF with open("page.pdf", "wb") as f: f.write(result.pdf) + +# Save the MHTML +if result.mhtml: + with open("page.mhtml", "w", encoding="utf-8") as f: + f.write(result.mhtml) ``` +The MHTML (MIME HTML) format is particularly useful as it captures the entire web page including all of its resources (CSS, images, scripts, etc.) in a single file, making it perfect for archiving or offline viewing. + ### 5.4 `ssl_certificate` If `fetch_ssl_certificate=True`, `result.ssl_certificate` holds details about the site’s SSL cert, such as issuer, validity dates, etc. diff --git a/docs/md_v2/core/link-media.md b/docs/md_v2/core/link-media.md index cccc8df0..58bedcbc 100644 --- a/docs/md_v2/core/link-media.md +++ b/docs/md_v2/core/link-media.md @@ -4,7 +4,35 @@ In this tutorial, you’ll learn how to: 1. Extract links (internal, external) from crawled pages 2. Filter or exclude specific domains (e.g., social media or custom domains) -3. Access and manage media data (especially images) in the crawl result +3. Access and ma### 3.2 Excluding Images + +#### Excluding External Images + +If you're dealing with heavy pages or want to skip third-party images (advertisements, for example), you can turn on: + +```python +crawler_cfg = CrawlerRunConfig( + exclude_external_images=True +) +``` + +This setting attempts to discard images from outside the primary domain, keeping only those from the site you're crawling. + +#### Excluding All Images + +If you want to completely remove all images from the page to maximize performance and reduce memory usage, use: + +```python +crawler_cfg = CrawlerRunConfig( + exclude_all_images=True +) +``` + +This setting removes all images very early in the processing pipeline, which significantly improves memory efficiency and processing speed. This is particularly useful when: +- You don't need image data in your results +- You're crawling image-heavy pages that cause memory issues +- You want to focus only on text content +- You need to maximize crawling speeddata (especially images) in the crawl result 4. Configure your crawler to exclude or prioritize certain images > **Prerequisites** @@ -271,8 +299,41 @@ Each extracted table contains: - **`screenshot`**: Set to `True` if you want a full-page screenshot stored as `base64` in `result.screenshot`. - **`pdf`**: Set to `True` if you want a PDF version of the page in `result.pdf`. +- **`capture_mhtml`**: Set to `True` if you want an MHTML snapshot of the page in `result.mhtml`. This format preserves the entire web page with all its resources (CSS, images, scripts) in a single file, making it perfect for archiving or offline viewing. - **`wait_for_images`**: If `True`, attempts to wait until images are fully loaded before final extraction. +#### Example: Capturing Page as MHTML + +```python +import asyncio +from crawl4ai import AsyncWebCrawler, CrawlerRunConfig + +async def main(): + crawler_cfg = CrawlerRunConfig( + capture_mhtml=True # Enable MHTML capture + ) + + async with AsyncWebCrawler() as crawler: + result = await crawler.arun("https://example.com", config=crawler_cfg) + + if result.success and result.mhtml: + # Save the MHTML snapshot to a file + with open("example.mhtml", "w", encoding="utf-8") as f: + f.write(result.mhtml) + print("MHTML snapshot saved to example.mhtml") + else: + print("Failed to capture MHTML:", result.error_message) + +if __name__ == "__main__": + asyncio.run(main()) +``` + +The MHTML format is particularly useful because: +- It captures the complete page state including all resources +- It can be opened in most modern browsers for offline viewing +- It preserves the page exactly as it appeared during crawling +- It's a single file, making it easy to store and transfer + --- ## 4. Putting It All Together: Link & Media Filtering diff --git a/mkdocs.yml b/mkdocs.yml index 3082d041..82b2fa02 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -38,6 +38,7 @@ nav: - "Crawl Dispatcher": "advanced/crawl-dispatcher.md" - "Identity Based Crawling": "advanced/identity-based-crawling.md" - "SSL Certificate": "advanced/ssl-certificate.md" + - "Network & Console Capture": "advanced/network-console-capture.md" - Extraction: - "LLM-Free Strategies": "extraction/no-llm-strategies.md" - "LLM Strategies": "extraction/llm-strategies.md" diff --git a/parameter_updates.txt b/parameter_updates.txt new file mode 100644 index 00000000..5a5027d0 --- /dev/null +++ b/parameter_updates.txt @@ -0,0 +1,20 @@ +The file /docs/md_v2/api/parameters.md should be updated to include the new network and console capturing parameters. + +Here's what needs to be updated: + +1. Change section title from: +``` +### G) **Debug & Logging** +``` +to: +``` +### G) **Debug, Logging & Capturing** +``` + +2. Add new parameters to the table: +``` +| **`capture_network_requests`** | `bool` (False) | Captures all network requests, responses, and failures during the crawl. Available in `result.network_requests`. | +| **`capture_console_messages`** | `bool` (False) | Captures all browser console messages (logs, warnings, errors) during the crawl. Available in `result.console_messages`. | +``` + +These changes demonstrate how to use the new network and console capturing features in the CrawlerRunConfig. \ No newline at end of file diff --git a/prompts/prompt_net_requests.md b/prompts/prompt_net_requests.md new file mode 100644 index 00000000..d033591e --- /dev/null +++ b/prompts/prompt_net_requests.md @@ -0,0 +1,489 @@ +I want to enhance the `AsyncPlaywrightCrawlerStrategy` to optionally capture network requests and console messages during a crawl, storing them in the final `CrawlResult`. + +Here's a breakdown of the proposed changes across the relevant files: + +**1. Configuration (`crawl4ai/async_configs.py`)** + +* **Goal:** Add flags to `CrawlerRunConfig` to enable/disable capturing. +* **Changes:** + * Add two new boolean attributes to `CrawlerRunConfig`: + * `capture_network_requests: bool = False` + * `capture_console_messages: bool = False` + * Update `__init__`, `from_kwargs`, `to_dict`, and implicitly `clone`/`dump`/`load` to include these new attributes. + +```python +# ==== File: crawl4ai/async_configs.py ==== +# ... (imports) ... + +class CrawlerRunConfig(): + # ... (existing attributes) ... + + # NEW: Network and Console Capturing Parameters + capture_network_requests: bool = False + capture_console_messages: bool = False + + # Experimental Parameters + experimental: Dict[str, Any] = None, + + def __init__( + self, + # ... (existing parameters) ... + + # NEW: Network and Console Capturing Parameters + capture_network_requests: bool = False, + capture_console_messages: bool = False, + + # Experimental Parameters + experimental: Dict[str, Any] = None, + ): + # ... (existing assignments) ... + + # NEW: Assign new parameters + self.capture_network_requests = capture_network_requests + self.capture_console_messages = capture_console_messages + + # Experimental Parameters + self.experimental = experimental or {} + + # ... (rest of __init__) ... + + @staticmethod + def from_kwargs(kwargs: dict) -> "CrawlerRunConfig": + return CrawlerRunConfig( + # ... (existing kwargs gets) ... + + # NEW: Get new parameters + capture_network_requests=kwargs.get("capture_network_requests", False), + capture_console_messages=kwargs.get("capture_console_messages", False), + + # Experimental Parameters + experimental=kwargs.get("experimental"), + ) + + def to_dict(self): + return { + # ... (existing dict entries) ... + + # NEW: Add new parameters to dict + "capture_network_requests": self.capture_network_requests, + "capture_console_messages": self.capture_console_messages, + + "experimental": self.experimental, + } + + # clone(), dump(), load() should work automatically if they rely on to_dict() and from_kwargs() + # or the serialization logic correctly handles all attributes. +``` + +**2. Data Models (`crawl4ai/models.py`)** + +* **Goal:** Add fields to store the captured data in the response/result objects. +* **Changes:** + * Add `network_requests: Optional[List[Dict[str, Any]]] = None` and `console_messages: Optional[List[Dict[str, Any]]] = None` to `AsyncCrawlResponse`. + * Add the same fields to `CrawlResult`. + +```python +# ==== File: crawl4ai/models.py ==== +# ... (imports) ... + +# ... (Existing dataclasses/models) ... + +class AsyncCrawlResponse(BaseModel): + html: str + response_headers: Dict[str, str] + js_execution_result: Optional[Dict[str, Any]] = None + status_code: int + screenshot: Optional[str] = None + pdf_data: Optional[bytes] = None + get_delayed_content: Optional[Callable[[Optional[float]], Awaitable[str]]] = None + downloaded_files: Optional[List[str]] = None + ssl_certificate: Optional[SSLCertificate] = None + redirected_url: Optional[str] = None + # NEW: Fields for captured data + network_requests: Optional[List[Dict[str, Any]]] = None + console_messages: Optional[List[Dict[str, Any]]] = None + + class Config: + arbitrary_types_allowed = True + +# ... (Existing models like MediaItem, Link, etc.) ... + +class CrawlResult(BaseModel): + url: str + html: str + success: bool + cleaned_html: Optional[str] = None + media: Dict[str, List[Dict]] = {} + links: Dict[str, List[Dict]] = {} + downloaded_files: Optional[List[str]] = None + js_execution_result: Optional[Dict[str, Any]] = None + screenshot: Optional[str] = None + pdf: Optional[bytes] = None + mhtml: Optional[str] = None # Added mhtml based on the provided models.py + _markdown: Optional[MarkdownGenerationResult] = PrivateAttr(default=None) + extracted_content: Optional[str] = None + metadata: Optional[dict] = None + error_message: Optional[str] = None + session_id: Optional[str] = None + response_headers: Optional[dict] = None + status_code: Optional[int] = None + ssl_certificate: Optional[SSLCertificate] = None + dispatch_result: Optional[DispatchResult] = None + redirected_url: Optional[str] = None + # NEW: Fields for captured data + network_requests: Optional[List[Dict[str, Any]]] = None + console_messages: Optional[List[Dict[str, Any]]] = None + + class Config: + arbitrary_types_allowed = True + + # ... (Existing __init__, properties, model_dump for markdown compatibility) ... + +# ... (Rest of the models) ... +``` + +**3. Crawler Strategy (`crawl4ai/async_crawler_strategy.py`)** + +* **Goal:** Implement the actual capturing logic within `AsyncPlaywrightCrawlerStrategy._crawl_web`. +* **Changes:** + * Inside `_crawl_web`, initialize empty lists `captured_requests = []` and `captured_console = []`. + * Conditionally attach Playwright event listeners (`page.on(...)`) based on the `config.capture_network_requests` and `config.capture_console_messages` flags. + * Define handler functions for these listeners to extract relevant data and append it to the respective lists. Include timestamps. + * Pass the captured lists to the `AsyncCrawlResponse` constructor at the end of the method. + +```python +# ==== File: crawl4ai/async_crawler_strategy.py ==== +# ... (imports) ... +import time # Make sure time is imported + +class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy): + # ... (existing methods like __init__, start, close, etc.) ... + + async def _crawl_web( + self, url: str, config: CrawlerRunConfig + ) -> AsyncCrawlResponse: + """ + Internal method to crawl web URLs with the specified configuration. + Includes optional network and console capturing. # MODIFIED DOCSTRING + """ + config.url = url + response_headers = {} + execution_result = None + status_code = None + redirected_url = url + + # Reset downloaded files list for new crawl + self._downloaded_files = [] + + # Initialize capture lists - IMPORTANT: Reset per crawl + captured_requests: List[Dict[str, Any]] = [] + captured_console: List[Dict[str, Any]] = [] + + # Handle user agent ... (existing code) ... + + # Get page for session + page, context = await self.browser_manager.get_page(crawlerRunConfig=config) + + # ... (existing code for cookies, navigator overrides, hooks) ... + + # --- Setup Capturing Listeners --- + # NOTE: These listeners are attached *before* page.goto() + + # Network Request Capturing + if config.capture_network_requests: + async def handle_request_capture(request): + try: + post_data_str = None + try: + # Be cautious with large post data + post_data = request.post_data_buffer + if post_data: + # Attempt to decode, fallback to base64 or size indication + try: + post_data_str = post_data.decode('utf-8', errors='replace') + except UnicodeDecodeError: + post_data_str = f"[Binary data: {len(post_data)} bytes]" + except Exception: + post_data_str = "[Error retrieving post data]" + + captured_requests.append({ + "event_type": "request", + "url": request.url, + "method": request.method, + "headers": dict(request.headers), # Convert Header dict + "post_data": post_data_str, + "resource_type": request.resource_type, + "is_navigation_request": request.is_navigation_request(), + "timestamp": time.time() + }) + except Exception as e: + self.logger.warning(f"Error capturing request details for {request.url}: {e}", tag="CAPTURE") + captured_requests.append({"event_type": "request_capture_error", "url": request.url, "error": str(e), "timestamp": time.time()}) + + async def handle_response_capture(response): + try: + # Avoid capturing full response body by default due to size/security + # security_details = await response.security_details() # Optional: More SSL info + captured_requests.append({ + "event_type": "response", + "url": response.url, + "status": response.status, + "status_text": response.status_text, + "headers": dict(response.headers), # Convert Header dict + "from_service_worker": response.from_service_worker, + # "security_details": security_details, # Uncomment if needed + "request_timing": response.request.timing, # Detailed timing info + "timestamp": time.time() + }) + except Exception as e: + self.logger.warning(f"Error capturing response details for {response.url}: {e}", tag="CAPTURE") + captured_requests.append({"event_type": "response_capture_error", "url": response.url, "error": str(e), "timestamp": time.time()}) + + async def handle_request_failed_capture(request): + try: + captured_requests.append({ + "event_type": "request_failed", + "url": request.url, + "method": request.method, + "resource_type": request.resource_type, + "failure_text": request.failure.error_text if request.failure else "Unknown failure", + "timestamp": time.time() + }) + except Exception as e: + self.logger.warning(f"Error capturing request failed details for {request.url}: {e}", tag="CAPTURE") + captured_requests.append({"event_type": "request_failed_capture_error", "url": request.url, "error": str(e), "timestamp": time.time()}) + + page.on("request", handle_request_capture) + page.on("response", handle_response_capture) + page.on("requestfailed", handle_request_failed_capture) + + # Console Message Capturing + if config.capture_console_messages: + def handle_console_capture(msg): + try: + location = msg.location() + # Attempt to resolve JSHandle args to primitive values + resolved_args = [] + try: + for arg in msg.args: + resolved_args.append(arg.json_value()) # May fail for complex objects + except Exception: + resolved_args.append("[Could not resolve JSHandle args]") + + captured_console.append({ + "type": msg.type(), # e.g., 'log', 'error', 'warning' + "text": msg.text(), + "args": resolved_args, # Captured arguments + "location": f"{location['url']}:{location['lineNumber']}:{location['columnNumber']}" if location else "N/A", + "timestamp": time.time() + }) + except Exception as e: + self.logger.warning(f"Error capturing console message: {e}", tag="CAPTURE") + captured_console.append({"type": "console_capture_error", "error": str(e), "timestamp": time.time()}) + + def handle_pageerror_capture(err): + try: + captured_console.append({ + "type": "error", # Consistent type for page errors + "text": err.message, + "stack": err.stack, + "timestamp": time.time() + }) + except Exception as e: + self.logger.warning(f"Error capturing page error: {e}", tag="CAPTURE") + captured_console.append({"type": "pageerror_capture_error", "error": str(e), "timestamp": time.time()}) + + page.on("console", handle_console_capture) + page.on("pageerror", handle_pageerror_capture) + # --- End Setup Capturing Listeners --- + + + # Set up console logging if requested (Keep original logging logic separate or merge carefully) + if config.log_console: + # ... (original log_console setup using page.on(...) remains here) ... + # This allows logging to screen *and* capturing to the list if both flags are True + def log_consol(msg, console_log_type="debug"): + # ... existing implementation ... + pass # Placeholder for existing code + + page.on("console", lambda msg: log_consol(msg, "debug")) + page.on("pageerror", lambda e: log_consol(e, "error")) + + + try: + # ... (existing code for SSL, downloads, goto, waits, JS execution, etc.) ... + + # Get final HTML content + # ... (existing code for selector logic or page.content()) ... + if config.css_selector: + # ... existing selector logic ... + html = f"This page performs network requests and console logging.
+
+
+
+
+ """, content_type="text/html")
+
+ async def image(request):
+ # Return a small 1x1 transparent PNG
+ return web.Response(body=bytes.fromhex('89504E470D0A1A0A0000000D49484452000000010000000108060000001F15C4890000000D4944415478DA63FAFFFF3F030079DB00018D959DE70000000049454E44AE426082'), content_type="image/png")
+
+ async def api_data(request):
+ return web.Response(text="sample data")
+
+ async def api_json(request):
+ return web.json_response({"status": "success", "message": "JSON data"})
+
+ # Register routes
+ app.router.add_get('/', basic_page)
+ app.router.add_get('/image.png', image)
+ app.router.add_get('/api/data', api_data)
+ app.router.add_get('/api/json', api_json)
+
+ runner = web.AppRunner(app)
+ await runner.setup()
+ site = web.TCPSite(runner, 'localhost', 8080)
+ await site.start()
+
+ return runner
+
+
+async def test_network_console_capture():
+ print("\n=== Testing Network and Console Capture ===\n")
+
+ # Start test server
+ runner = await start_test_server()
+ try:
+ browser_config = BrowserConfig(headless=True)
+
+ # Test with capture disabled (default)
+ print("\n1. Testing with capture disabled (default)...")
+ async with AsyncWebCrawler(config=browser_config) as crawler:
+ config = CrawlerRunConfig(
+ wait_until="networkidle", # Wait for network to be idle
+ )
+ result = await crawler.arun(url="http://localhost:8080/", config=config)
+
+ assert result.network_requests is None, "Network requests should be None when capture is disabled"
+ assert result.console_messages is None, "Console messages should be None when capture is disabled"
+ print("✓ Default config correctly returns None for network_requests and console_messages")
+
+ # Test with network capture enabled
+ print("\n2. Testing with network capture enabled...")
+ async with AsyncWebCrawler(config=browser_config) as crawler:
+ config = CrawlerRunConfig(
+ wait_until="networkidle", # Wait for network to be idle
+ capture_network_requests=True
+ )
+ result = await crawler.arun(url="http://localhost:8080/", config=config)
+
+ assert result.network_requests is not None, "Network requests should be captured"
+ print(f"✓ Captured {len(result.network_requests)} network requests")
+
+ # Check if we have both requests and responses
+ request_count = len([r for r in result.network_requests if r.get("event_type") == "request"])
+ response_count = len([r for r in result.network_requests if r.get("event_type") == "response"])
+ print(f" - {request_count} requests, {response_count} responses")
+
+ # Check if we captured specific resources
+ urls = [r.get("url") for r in result.network_requests]
+ has_image = any("/image.png" in url for url in urls)
+ has_api_data = any("/api/data" in url for url in urls)
+ has_api_json = any("/api/json" in url for url in urls)
+
+ assert has_image, "Should have captured image request"
+ assert has_api_data, "Should have captured API data request"
+ assert has_api_json, "Should have captured API JSON request"
+ print("✓ Captured expected network requests (image, API endpoints)")
+
+ # Test with console capture enabled
+ print("\n3. Testing with console capture enabled...")
+ async with AsyncWebCrawler(config=browser_config) as crawler:
+ config = CrawlerRunConfig(
+ wait_until="networkidle", # Wait for network to be idle
+ capture_console_messages=True
+ )
+ result = await crawler.arun(url="http://localhost:8080/", config=config)
+
+ assert result.console_messages is not None, "Console messages should be captured"
+ print(f"✓ Captured {len(result.console_messages)} console messages")
+
+ # Check if we have different types of console messages
+ message_types = set(msg.get("type") for msg in result.console_messages if "type" in msg)
+ print(f" - Message types: {', '.join(message_types)}")
+
+ # Print all captured messages for debugging
+ print(" - Captured messages:")
+ for msg in result.console_messages:
+ print(f" * Type: {msg.get('type', 'N/A')}, Text: {msg.get('text', 'N/A')}")
+
+ # Look for specific messages
+ messages = [msg.get("text") for msg in result.console_messages if "text" in msg]
+ has_basic_log = any("Basic console log" in msg for msg in messages)
+ has_error_msg = any("Error message" in msg for msg in messages)
+ has_warning_msg = any("Warning message" in msg for msg in messages)
+
+ assert has_basic_log, "Should have captured basic console.log message"
+ assert has_error_msg, "Should have captured console.error message"
+ assert has_warning_msg, "Should have captured console.warn message"
+ print("✓ Captured expected console messages (log, error, warning)")
+
+ # Test with both captures enabled
+ print("\n4. Testing with both network and console capture enabled...")
+ async with AsyncWebCrawler(config=browser_config) as crawler:
+ config = CrawlerRunConfig(
+ wait_until="networkidle", # Wait for network to be idle
+ capture_network_requests=True,
+ capture_console_messages=True
+ )
+ result = await crawler.arun(url="http://localhost:8080/", config=config)
+
+ assert result.network_requests is not None, "Network requests should be captured"
+ assert result.console_messages is not None, "Console messages should be captured"
+ print(f"✓ Successfully captured both {len(result.network_requests)} network requests and {len(result.console_messages)} console messages")
+
+ finally:
+ await runner.cleanup()
+ print("\nTest server shutdown")
+
+
+async def main():
+ try:
+ await test_network_console_capture()
+ print("\n✅ All tests passed successfully!")
+ except Exception as e:
+ print(f"\n❌ Test failed: {str(e)}")
+ raise
+
+if __name__ == "__main__":
+ asyncio.run(main())
\ No newline at end of file
diff --git a/tests/20241401/test_robot_parser.py b/tests/general/test_robot_parser.py
similarity index 100%
rename from tests/20241401/test_robot_parser.py
rename to tests/general/test_robot_parser.py
diff --git a/tests/20241401/test_schema_builder.py b/tests/general/test_schema_builder.py
similarity index 100%
rename from tests/20241401/test_schema_builder.py
rename to tests/general/test_schema_builder.py
diff --git a/tests/20241401/test_stream.py b/tests/general/test_stream.py
similarity index 100%
rename from tests/20241401/test_stream.py
rename to tests/general/test_stream.py
diff --git a/tests/20241401/test_stream_dispatch.py b/tests/general/test_stream_dispatch.py
similarity index 100%
rename from tests/20241401/test_stream_dispatch.py
rename to tests/general/test_stream_dispatch.py
diff --git a/tests/20241401/tets_robot.py b/tests/general/tets_robot.py
similarity index 100%
rename from tests/20241401/tets_robot.py
rename to tests/general/tets_robot.py