问在多个请求或刮过的项目后暂停刮取

EN

import scrapy
from scrapy import signals
import time

class SampleSpider(scrapy.Spider):
    name = 'sample'
    start_urls = ['http://quotes.toscrape.com/page/1/']
    item_count = 0

    @classmethod
    def from_crawler(cls, crawler, *args, **kwargs):
        spider = super(SampleSpider, cls).from_crawler(crawler, *args, **kwargs)
        crawler.signals.connect(spider.item_scraped, signal=signals.item_scraped)
        spider.crawler = crawler
        return spider

    def item_scraped(self, item):
        # increase item count and then check if the item count is 5 from the previous pause
        self.item_count += 1
        if self.item_count % 5 == 0:
            self.logger.info(f"Pausing scrape job...item count = {self.item_count}")
            self.crawler.engine.pause()
            time.sleep(10)
            self.crawler.engine.unpause()
            self.logger.info(f"Resuming crawl...")

    def parse(self, response):
        for quote in response.css('div.quote'):
            yield {
                'text': quote.css('span.text::text').get(),
                'author': quote.css('small.author::text').get(),
                'tags': quote.css('div.tags a.tag::text').getall(),
            }