9b5ccac76e
Add new RegexExtractionStrategy for fast, zero-LLM extraction of common data types: - Built-in patterns for emails, URLs, phones, dates, and more - Support for custom regex patterns - LLM-assisted pattern generation utility - Optimized HTML preprocessing with fit_html field - Enhanced network response body capture Breaking changes: None
28 lines
758 B
Python
28 lines
758 B
Python
import asyncio
|
|
from crawl4ai import (
|
|
AsyncWebCrawler,
|
|
BrowserConfig,
|
|
CrawlerRunConfig,
|
|
DefaultMarkdownGenerator,
|
|
PruningContentFilter,
|
|
CrawlResult
|
|
)
|
|
|
|
|
|
|
|
async def main():
|
|
browser_config = BrowserConfig(headless=True, verbose=True)
|
|
async with AsyncWebCrawler(config=browser_config) as crawler:
|
|
crawler_config = CrawlerRunConfig(
|
|
markdown_generator=DefaultMarkdownGenerator(
|
|
content_filter=PruningContentFilter()
|
|
),
|
|
)
|
|
result : CrawlResult = await crawler.arun(
|
|
url="https://www.helloworld.org", config=crawler_config
|
|
)
|
|
print(result.markdown.raw_markdown[:500])
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|