Scrapy, a fast high-level web crawling & scraping framework for Python.
import asyncio
from twisted.internet import asyncioreactor
import scrapy
from scrapy.crawler import AsyncCrawlerProcess
# Twisted doesn't make a loop passed to it the current event loop.
asyncioreactor.install(asyncio.SelectorEventLoop())
class NoRequestsSpider(scrapy.Spider):
name = "no_request"
async def start(self):
return
yield
process = AsyncCrawlerProcess()
process.crawl(NoRequestsSpider)
process.start()