Scrapy-Reactor无法重新启动[重复]

您不能重新启动反应堆，但是应该可以通过分叉一个单独的过程来使其运行更多次：

import scrapyimport scrapy.crawler as crawlerfrom multiprocessing import Process, Queuefrom twisted.internet import reactor# your spiderclass QuotesSpider(scrapy.Spider):    name = "quotes"    start_urls = ['http://quotes.toscrape.com/tag/humor/']    def parse(self, response):        for quote in response.css('div.quote'): print(quote.css('span.text::text').extract_first())# the wrapper to make it run more timesdef run_spider(spider):    def f(q):        try: runner = crawler.CrawlerRunner() deferred = runner.crawl(spider) deferred.addBoth(lambda _: reactor.stop()) reactor.run() q.put(None)        except Exception as e: q.put(e)    q = Queue()    p = Process(target=f, args=(q,))    p.start()    result = q.get()    p.join()    if result is not None:        raise result

运行两次：

print('first run:')run_spider(QuotesSpider)print('nsecond run:')run_spider(QuotesSpider)

结果：

first run:“The person, be it gentleman or lady, who has not pleasure in a good novel, must be intolerably stupid.”“A day without sunshine is like, you know, night.”...second run:“The person, be it gentleman or lady, who has not pleasure in a good novel, must be intolerably stupid.”“A day without sunshine is like, you know, night.”...