docs/md_v2/marketplace/frontend/app-detail.html
Get started with this integration in just a few steps.
bashCopy
pip install crawl4ai
pythonCopy
from crawl4ai import AsyncWebCrawler
async def main():
async with AsyncWebCrawler() as crawler:
result = await crawler.arun(
url="https://example.com",
# Your configuration here
)
print(result.markdown)
if __name__ == " __main__":
import asyncio
asyncio.run(main())
Customize the crawler with these advanced options:
Optimize crawling speed with parallel processing and caching strategies.
Handle login forms, cookies, and session management automatically.
Use CSS selectors, XPath, or AI-powered content extraction.
Rotate proxies and bypass rate limiting with built-in proxy management.
pythonCopy
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode
from crawl4ai import LLMConfig
from crawl4ai.extraction_strategy import LLMExtractionStrategy
async def extract_with_llm():
async with AsyncWebCrawler() as crawler:
result = await crawler.arun(
url="https://example.com",
config=CrawlerRunConfig(
extraction_strategy=LLMExtractionStrategy(
llm_config=LLMConfig(
provider="openai/gpt-4o",
api_token="your-api-key",
),
instruction="Extract product information"
),
cache_mode=CacheMode.BYPASS
)
)
return result.extracted_content
# Run the extraction
data = await extract_with_llm()
print(data)
Use cache_mode=CacheMode.BYPASS for a fresh crawl, or CacheMode.WRITE_ONLY to avoid refetching.
Complete documentation and API reference.
Real-world examples and use cases.
Found a bug? Report it on GitHub Issues.
Join our Discord for help and discussions.