2 replies

How to handle TimeoutErrors

Hey,

We've just started using Crawlee 0.1.2 for some basic web scraping tasks, and I'm unsure from the docs how to handle cases where the HTTP request times out.

Below is a simple script that scrapes a webpage and outputs the number of anchor tags on the page. This particular site blocks the request (in that it never responds) and the script hangs indefinitely.

How can I handle this case so that the script doesn't hang indefinitely?

Thanks in advance :perfecto:

from datetime import timedelta
from crawlee.beautifulsoup_crawler import (
    BeautifulSoupCrawler,
    BeautifulSoupCrawlingContext,
)
import asyncio

async def task():
    crawler = BeautifulSoupCrawler(
        request_handler_timeout=timedelta(seconds=10),
        max_request_retries=0,
    )

    @crawler.router.default_handler
    async def _request_handler(context: BeautifulSoupCrawlingContext):
        url = context.request.url
        links = context.soup.find_all("a")
        print(f"Found {len(links)} links")

    await crawler.run(["https://www.unicreditgroup.eu/"])


if __name__ == "__main__":
    asyncio.run(task())

from datetime import timedelta
from crawlee.beautifulsoup_crawler import (
    BeautifulSoupCrawler,
    BeautifulSoupCrawlingContext,
)
import asyncio

async def task():
    crawler = BeautifulSoupCrawler(
        request_handler_timeout=timedelta(seconds=10),
        max_request_retries=0,
    )

    @crawler.router.default_handler
    async def _request_handler(context: BeautifulSoupCrawlingContext):
        url = context.request.url
        links = context.soup.find_all("a")
        print(f"Found {len(links)} links")

    await crawler.run(["https://www.unicreditgroup.eu/"])


if __name__ == "__main__":
    asyncio.run(task())

from datetime import timedelta
from crawlee.beautifulsoup_crawler import (
    BeautifulSoupCrawler,
    BeautifulSoupCrawlingContext,
)
import asyncio

async def task():
    crawler = BeautifulSoupCrawler(
        request_handler_timeout=timedelta(seconds=10),
        max_request_retries=0,
    )

    @crawler.router.default_handler
    async def _request_handler(context: BeautifulSoupCrawlingContext):
        url = context.request.url
        links = context.soup.find_all("a")
        print(f"Found {len(links)} links")

    await crawler.run(["https://www.unicreditgroup.eu/"])


if __name__ == "__main__":
    asyncio.run(task())

from datetime import timedelta
from crawlee.beautifulsoup_crawler import (
    BeautifulSoupCrawler,
    BeautifulSoupCrawlingContext,
)
import asyncio

async def task():
    crawler = BeautifulSoupCrawler(
        request_handler_timeout=timedelta(seconds=10),
        max_request_retries=0,
    )

    @crawler.router.default_handler
    async def _request_handler(context: BeautifulSoupCrawlingContext):
        url = context.request.url
        links = context.soup.find_all("a")
        print(f"Found {len(links)} links")

    await crawler.run(["https://www.unicreditgroup.eu/"])


if __name__ == "__main__":
    asyncio.run(task())

logs.txt7.95KB

How to handle TimeoutErrors

Similar Threads

Similar Threads

Similar Threads