docs/examples/hello_world.py

Rama main · réplica de lectura del repositorio original.

import asyncio
from crawl4ai import (
    AsyncWebCrawler,
    BrowserConfig,
    CrawlerRunConfig,
    DefaultMarkdownGenerator,
    PruningContentFilterLXML,
    CrawlResult
)


async def main():
    browser_config = BrowserConfig(
        headless=False,
        verbose=True,
    )
    async with AsyncWebCrawler(config=browser_config) as crawler:
        crawler_config = CrawlerRunConfig(
            markdown_generator=DefaultMarkdownGenerator(
                content_filter=PruningContentFilterLXML()
            ),
        )
        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())