Add quickstart example set
This commit is contained in:
UncleCode
562
docs/examples/quickstart.py
Normal file
562
docs/examples/quickstart.py
Normal file
@@ -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())
|
||||
404
docs/examples/quickstart_examples.py
Normal file
404
docs/examples/quickstart_examples.py
Normal file
@@ -0,0 +1,404 @@
|
||||
import asyncio
|
||||
import os
|
||||
import json
|
||||
import base64
|
||||
from pathlib import Path
|
||||
from typing import List
|
||||
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode, CrawlResult
|
||||
from crawl4ai.configs import ProxyConfig
|
||||
from crawl4ai import RoundRobinProxyStrategy
|
||||
from crawl4ai import JsonCssExtractionStrategy, LLMExtractionStrategy
|
||||
from crawl4ai import LLMConfig
|
||||
from crawl4ai import PruningContentFilter
|
||||
from crawl4ai import DefaultMarkdownGenerator
|
||||
from crawl4ai import BFSDeepCrawlStrategy, DomainFilter, FilterChain
|
||||
from crawl4ai import BrowserConfig
|
||||
|
||||
__cur_dir__ = Path(__file__).parent
|
||||
|
||||
async def demo_basic_crawl():
|
||||
"""Basic web crawling with markdown generation"""
|
||||
print("\n=== 1. Basic Web Crawling ===")
|
||||
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
results: List[CrawlResult] = await crawler.arun(
|
||||
url="https://news.ycombinator.com/",
|
||||
)
|
||||
|
||||
for i, result in enumerate(results):
|
||||
print(f"Result {i + 1}:")
|
||||
print(f"Success: {result.success}")
|
||||
if result.success:
|
||||
print(f"Markdown length: {len(result.markdown.raw_markdown)} chars")
|
||||
print(f"First 100 chars: {result.markdown.raw_markdown[:100]}...")
|
||||
else:
|
||||
print("Failed to crawl the URL")
|
||||
|
||||
|
||||
async def demo_parallel_crawl():
|
||||
"""Crawl multiple URLs in parallel"""
|
||||
print("\n=== 2. Parallel Crawling ===")
|
||||
|
||||
urls = [
|
||||
"https://news.ycombinator.com/",
|
||||
"https://example.com/",
|
||||
"https://httpbin.org/html",
|
||||
]
|
||||
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
results: List[CrawlResult] = await crawler.arun_many(
|
||||
urls=urls,
|
||||
)
|
||||
|
||||
print(f"Crawled {len(results)} URLs in parallel:")
|
||||
for i, result in enumerate(results):
|
||||
print(
|
||||
f" {i + 1}. {result.url} - {'Success' if result.success else 'Failed'}"
|
||||
)
|
||||
|
||||
|
||||
async def demo_fit_markdown():
|
||||
"""Generate focused markdown with LLM content filter"""
|
||||
print("\n=== 3. Fit Markdown with LLM Content Filter ===")
|
||||
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
result = await crawler.arun(
|
||||
"https://en.wikipedia.org/wiki/Python_(programming_language)",
|
||||
config=CrawlerRunConfig(
|
||||
markdown_generator=DefaultMarkdownGenerator(
|
||||
content_filter=PruningContentFilter()
|
||||
)
|
||||
),
|
||||
)
|
||||
|
||||
# Print stats and save the fit markdown
|
||||
print(f"Raw: {len(result.markdown.raw_markdown)} chars")
|
||||
print(f"Fit: {len(result.markdown.fit_markdown)} chars")
|
||||
|
||||
|
||||
async def demo_llm_structured_extraction_no_schema():
|
||||
# Create a simple LLM extraction strategy (no schema required)
|
||||
extraction_strategy = LLMExtractionStrategy(
|
||||
llm_config=LLMConfig(
|
||||
provider="groq/qwen-2.5-32b",
|
||||
api_token="env:GROQ_API_KEY",
|
||||
),
|
||||
instruction="This is news.ycombinator.com, extract all news for each. title, source url, number of comments.",
|
||||
extract_type="schema",
|
||||
schema="{title: string, url: string, comments: int}",
|
||||
extra_args={
|
||||
"temperature": 0.0,
|
||||
"max_tokens": 4096,
|
||||
},
|
||||
verbose=True,
|
||||
)
|
||||
|
||||
config = CrawlerRunConfig(extraction_strategy=extraction_strategy)
|
||||
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
results: List[CrawlResult] = await crawler.arun(
|
||||
"https://news.ycombinator.com/", config=config
|
||||
)
|
||||
|
||||
for result in results:
|
||||
print(f"URL: {result.url}")
|
||||
print(f"Success: {result.success}")
|
||||
if result.success:
|
||||
data = json.loads(result.extracted_content)
|
||||
print(json.dumps(data, indent=2))
|
||||
else:
|
||||
print("Failed to extract structured data")
|
||||
|
||||
|
||||
async def demo_css_structured_extraction_no_schema():
|
||||
"""Extract structured data using CSS selectors"""
|
||||
print("\n=== 5. CSS-Based Structured Extraction ===")
|
||||
# Sample HTML for schema generation (one-time cost)
|
||||
sample_html = """
|
||||
<div class="body-post clear">
|
||||
<a class="story-link" href="https://thehackernews.com/2025/04/malicious-python-packages-on-pypi.html">
|
||||
<div class="clear home-post-box cf">
|
||||
<div class="home-img clear">
|
||||
<div class="img-ratio">
|
||||
<img alt="..." src="...">
|
||||
</div>
|
||||
</div>
|
||||
<div class="clear home-right">
|
||||
<h2 class="home-title">Malicious Python Packages on PyPI Downloaded 39,000+ Times, Steal Sensitive Data</h2>
|
||||
<div class="item-label">
|
||||
<span class="h-datetime"><i class="icon-font icon-calendar"></i>Apr 05, 2025</span>
|
||||
<span class="h-tags">Malware / Supply Chain Attack</span>
|
||||
</div>
|
||||
<div class="home-desc"> Cybersecurity researchers have uncovered malicious libraries in the Python Package Index (PyPI) repository that are designed to steal sensitive information. Two of the packages, bitcoinlibdbfix and bitcoinlib-dev, masquerade as fixes for recent issues detected in a legitimate Python module called bitcoinlib, according to ReversingLabs . A third package discovered by Socket, disgrasya, contained a fully automated carding script targeting WooCommerce stores. The packages attracted hundreds of downloads before being taken down, according to statistics from pepy.tech - bitcoinlibdbfix - 1,101 downloads bitcoinlib-dev - 735 downloads disgrasya - 37,217 downloads "The malicious libraries both attempt a similar attack, overwriting the legitimate 'clw cli' command with malicious code that attempts to exfiltrate sensitive database files," ReversingLabs said. In an interesting twist, the authors of the counterfeit libraries are said to have joined a GitHub issue...</div>
|
||||
</div>
|
||||
</div>
|
||||
</a>
|
||||
</div>
|
||||
"""
|
||||
|
||||
# Generate schema using LLM (one-time setup)
|
||||
schema = JsonCssExtractionStrategy.generate_schema(
|
||||
html=sample_html,
|
||||
llm_config=LLMConfig(
|
||||
provider="groq/qwen-2.5-32b",
|
||||
api_token="env:GROQ_API_KEY",
|
||||
),
|
||||
query="From https://thehackernews.com/, I have shares a sample of one news div with a title, date, and description. Please generate a schema for this news div.",
|
||||
)
|
||||
|
||||
print(f"Generated schema: {json.dumps(schema, indent=2)}")
|
||||
# Save the schema to a file , and use it for future extractions, in result for such extraction you will call LLM once
|
||||
# with open("schema.json", "w") as f:
|
||||
# json.dump(schema, f, indent=2)
|
||||
|
||||
# Create no-LLM extraction strategy with the generated schema
|
||||
extraction_strategy = JsonCssExtractionStrategy(schema)
|
||||
config = CrawlerRunConfig(extraction_strategy=extraction_strategy)
|
||||
|
||||
# Use the fast CSS extraction (no LLM calls during extraction)
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
results: List[CrawlResult] = await crawler.arun(
|
||||
"https://thehackernews.com", config=config
|
||||
)
|
||||
|
||||
for result in results:
|
||||
print(f"URL: {result.url}")
|
||||
print(f"Success: {result.success}")
|
||||
if result.success:
|
||||
data = json.loads(result.extracted_content)
|
||||
print(json.dumps(data, indent=2))
|
||||
else:
|
||||
print("Failed to extract structured data")
|
||||
|
||||
|
||||
async def demo_deep_crawl():
|
||||
"""Deep crawling with BFS strategy"""
|
||||
print("\n=== 6. Deep Crawling ===")
|
||||
|
||||
filter_chain = FilterChain([DomainFilter(allowed_domains=["crawl4ai.com"])])
|
||||
|
||||
deep_crawl_strategy = BFSDeepCrawlStrategy(
|
||||
max_depth=1, max_pages=5, filter_chain=filter_chain
|
||||
)
|
||||
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
results: List[CrawlResult] = await crawler.arun(
|
||||
url="https://docs.crawl4ai.com",
|
||||
config=CrawlerRunConfig(deep_crawl_strategy=deep_crawl_strategy),
|
||||
)
|
||||
|
||||
print(f"Deep crawl returned {len(results)} pages:")
|
||||
for i, result in enumerate(results):
|
||||
depth = result.metadata.get("depth", "unknown")
|
||||
print(f" {i + 1}. {result.url} (Depth: {depth})")
|
||||
|
||||
|
||||
async def demo_js_interaction():
|
||||
"""Execute JavaScript to load more content"""
|
||||
print("\n=== 7. JavaScript Interaction ===")
|
||||
|
||||
# A simple page that needs JS to reveal content
|
||||
async with AsyncWebCrawler(config=BrowserConfig(headless=False)) as crawler:
|
||||
# Initial load
|
||||
|
||||
news_schema = {
|
||||
"name": "news",
|
||||
"baseSelector": "tr.athing",
|
||||
"fields": [
|
||||
{
|
||||
"name": "title",
|
||||
"selector": "span.titleline",
|
||||
"type": "text",
|
||||
}
|
||||
],
|
||||
}
|
||||
results: List[CrawlResult] = await crawler.arun(
|
||||
url="https://news.ycombinator.com",
|
||||
config=CrawlerRunConfig(
|
||||
session_id="hn_session", # Keep session
|
||||
extraction_strategy=JsonCssExtractionStrategy(schema=news_schema),
|
||||
),
|
||||
)
|
||||
|
||||
news = []
|
||||
for result in results:
|
||||
if result.success:
|
||||
data = json.loads(result.extracted_content)
|
||||
news.extend(data)
|
||||
print(json.dumps(data, indent=2))
|
||||
else:
|
||||
print("Failed to extract structured data")
|
||||
|
||||
print(f"Initial items: {len(news)}")
|
||||
|
||||
# Click "More" link
|
||||
more_config = CrawlerRunConfig(
|
||||
js_code="document.querySelector('a.morelink').click();",
|
||||
js_only=True, # Continue in same page
|
||||
session_id="hn_session", # Keep session
|
||||
extraction_strategy=JsonCssExtractionStrategy(
|
||||
schema=news_schema,
|
||||
),
|
||||
)
|
||||
|
||||
result: List[CrawlResult] = await crawler.arun(
|
||||
url="https://news.ycombinator.com", config=more_config
|
||||
)
|
||||
|
||||
# Extract new items
|
||||
for result in results:
|
||||
if result.success:
|
||||
data = json.loads(result.extracted_content)
|
||||
news.extend(data)
|
||||
print(json.dumps(data, indent=2))
|
||||
else:
|
||||
print("Failed to extract structured data")
|
||||
print(f"Total items: {len(news)}")
|
||||
|
||||
|
||||
|
||||
async def demo_media_and_links():
|
||||
"""Extract media and links from a page"""
|
||||
print("\n=== 8. Media and Links Extraction ===")
|
||||
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
result: List[CrawlResult] = await crawler.arun("https://en.wikipedia.org/wiki/Main_Page")
|
||||
|
||||
for i, result in enumerate(result):
|
||||
# Extract and save all images
|
||||
images = result.media.get("images", [])
|
||||
print(f"Found {len(images)} images")
|
||||
|
||||
# Extract and save all links (internal and external)
|
||||
internal_links = result.links.get("internal", [])
|
||||
external_links = result.links.get("external", [])
|
||||
print(f"Found {len(internal_links)} internal links")
|
||||
print(f"Found {len(external_links)} external links")
|
||||
|
||||
# Save everything to files
|
||||
with open("images.json", "w") as f:
|
||||
json.dump(images, f, indent=2)
|
||||
|
||||
with open("links.json", "w") as f:
|
||||
json.dump(
|
||||
{"internal": internal_links, "external": external_links},
|
||||
f,
|
||||
indent=2,
|
||||
)
|
||||
|
||||
|
||||
async def demo_screenshot_and_pdf():
|
||||
"""Capture screenshot and PDF of a page"""
|
||||
print("\n=== 9. Screenshot and PDF Capture ===")
|
||||
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
result: List[CrawlResult] = await crawler.arun(
|
||||
# url="https://example.com",
|
||||
url="https://en.wikipedia.org/wiki/Giant_anteater",
|
||||
config=CrawlerRunConfig(screenshot=True, pdf=True),
|
||||
)
|
||||
|
||||
for i, result in enumerate(result):
|
||||
if result.screenshot:
|
||||
# Save screenshot
|
||||
screenshot_path = f"{__cur_dir__}/tmp/example_screenshot.png"
|
||||
with open(screenshot_path, "wb") as f:
|
||||
f.write(base64.b64decode(result.screenshot))
|
||||
print(f"Screenshot saved to {screenshot_path}")
|
||||
|
||||
if result.pdf:
|
||||
# Save PDF
|
||||
pdf_path = f"{__cur_dir__}/tmp/example.pdf"
|
||||
with open(pdf_path, "wb") as f:
|
||||
f.write(result.pdf)
|
||||
print(f"PDF saved to {pdf_path}")
|
||||
|
||||
|
||||
async def demo_proxy_rotation():
|
||||
"""Proxy rotation for multiple requests"""
|
||||
print("\n=== 10. Proxy Rotation ===")
|
||||
|
||||
# Example proxies (replace with real ones)
|
||||
proxies = [
|
||||
ProxyConfig(server="http://proxy1.example.com:8080"),
|
||||
ProxyConfig(server="http://proxy2.example.com:8080"),
|
||||
]
|
||||
|
||||
proxy_strategy = RoundRobinProxyStrategy(proxies)
|
||||
|
||||
print(f"Using {len(proxies)} proxies in rotation")
|
||||
print(
|
||||
"Note: This example uses placeholder proxies - replace with real ones to test"
|
||||
)
|
||||
|
||||
async with AsyncWebCrawler() as crawler:
|
||||
config = CrawlerRunConfig(
|
||||
proxy_rotation_strategy=proxy_strategy, cache_mode=CacheMode.BYPASS
|
||||
)
|
||||
|
||||
# In a real scenario, these would be run and the proxies would rotate
|
||||
print("In a real scenario, requests would rotate through the available proxies")
|
||||
|
||||
|
||||
async def demo_raw_html_and_file():
|
||||
"""Process raw HTML and local files"""
|
||||
print("\n=== 11. Raw HTML and Local Files ===")
|
||||
|
||||
raw_html = """
|
||||
<html><body>
|
||||
<h1>Sample Article</h1>
|
||||
<p>This is sample content for testing Crawl4AI's raw HTML processing.</p>
|
||||
</body></html>
|
||||
"""
|
||||
|
||||
# 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())
|
||||
@@ -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
|
||||
}
|
||||
Reference in New Issue
Block a user