How to run crawler in infinite loop?

[marisancans]

How can I run the crawler on an infinite loop while it wait for requests to come in from time to time

[vdusek]

You can run crawler.run() repeatedly in an infinite loop.

import asyncio

from crawlee.beautifulsoup_crawler import BeautifulSoupCrawler, BeautifulSoupCrawlingContext


async def main() -> None:
    crawler = BeautifulSoupCrawler()

    @crawler.router.default_handler
    async def request_handler(context: BeautifulSoupCrawlingContext) -> None:
        context.log.info(f'Processing {context.request.url} ...')

        data = {
            'url': context.request.url,
            'title': context.soup.title.string if context.soup.title else None,
            'h1s': [h1.text for h1 in context.soup.find_all('h1')],
            'h2s': [h2.text for h2 in context.soup.find_all('h2')],
            'h3s': [h3.text for h3 in context.soup.find_all('h3')],
        }

        await context.push_data(data)

    while True:
        # get your URLs here
        urls = ['https://crawlee.dev']
        await crawler.run(urls)
        await asyncio.sleep(10)

if __name__ == '__main__':
    asyncio.run(main())

Converting this to discussion.