rss_spider.py 文件源码

def topics_id_rss(self):
        logging.debug('fetch rss feeds')
        topic_ids=list()
        for v2ex_rss_url in self.v2ex_rss_url_list:
            feed=feedparser.parse(v2ex_rss_url)
            logging.debug('fetch rss feed: %s' % v2ex_rss_url)
            items=feed["items"]
            for item in items:
                author=item["author"]
                title=item["title"]
                link=item["link"]
                published=item[ "date" ] 
                summary=item["summary"]
                topic_id=int(re.findall(r't\/(\d+)#?', link)[0])
                topic_ids.append(topic_id)
        topic_ids=set(topic_ids)
        return topic_ids