parsers.py 文件源码

def crawl_feed(self, feed_url: str=None) -> List[str]:

        urls = []

        if not feed_url:
            feed_url = constants.rss_url
        feed = feedparser.parse(
            feed_url,
            handlers=ProxyHandler,
            request_headers=self.settings.requests_headers
        )

        for item in feed['items']:
            if any([item['title'].startswith(category) for category in self.own_settings.accepted_rss_categories]):
                urls.append(item['link'])
        return urls