single_crawler.py 文件源码

def load_crawler(self, crawler, url, ignore_regex):
        """
        Loads the given crawler with the given url.

        :param class crawler: class of the crawler to load
        :param str url: url to start the crawler with
        :param regex ignore_regex: to be able to ignore urls that match this
                                   regex code
        """
        self.process = CrawlerProcess(self.cfg.get_scrapy_options())
        self.process.crawl(
            crawler,
            self.helper,
            url=url,
            config=self.cfg,
            ignore_regex=ignore_regex)