Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

608 B
Raw Blame
import scrapy
from scrapy.crawler import AsyncCrawlerProcess


class CachingHostnameResolverSpider(scrapy.Spider):
    """
    Finishes without a scrapy.exceptions.CannotResolveHostError exception
    """

    name = "caching_hostname_resolver_spider"

    async def start(self):
        yield scrapy.Request("http://[::1]")


if __name__ == "__main__":
    process = AsyncCrawlerProcess(
        settings={
            "RETRY_ENABLED": False,
            "TWISTED_DNS_RESOLVER": "scrapy.resolver.CachingHostnameResolver",
        }
    )
    process.crawl(CachingHostnameResolverSpider)
    process.start()