spider.py 文件源码

def parse_user_0(self, response):
        """ ??????-???????????????? """
        user_item = UserItem()
        selector = Selector(response)
        text0 = selector.xpath('body/div[@class="u"]/div[@class="tip2"]').extract_first()
        if text0:
            num_tweets = re.findall(u'\u5fae\u535a\[(\d+)\]', text0)  # ???
            num_follows = re.findall(u'\u5173\u6ce8\[(\d+)\]', text0)  # ???
            num_fans = re.findall(u'\u7c89\u4e1d\[(\d+)\]', text0)  # ???
            if num_tweets:
                user_item["ctweets"] = int(num_tweets[0])
            if num_follows:
                user_item["cfollows"] = int(num_follows[0])
            if num_fans:
                user_item["cfans"] = int(num_fans[0])
            user_item["_id"] = response.meta["user_id"]
            url_information1 = "http://weibo.cn/%s/info" % response.meta["user_id"]
            yield Request(url=url_information1, meta={"item": user_item}, callback=self.parse_user_1)