def oninit(self, url):
url = self.url_suf + url
res = self.downloader.download(url)
if not res: return
cont = res.content
uid = re.search("CONFIG\['oid'\]='(.*?)'", cont).group(1)
nick = re.search("CONFIG\['onick'\]='(.*?)'",
cont).group(1).decode('utf-8')
# ajax 请求微博时要用
page_id = re.search("CONFIG\['page_id'\]='(.*?)'", cont).group(1)
domain = re.search("CONFIG\['domain'\]='(.*?)'", cont).group(1)
location = re.search("CONFIG\['location'\]='(.*?)'", cont).group(1)
nums = Parser.parse_index(cont)
if not nums: return
follow_num, fans_num, wb_num = nums
# 验证该用户关注粉丝微博数是否变化
# 如变化更新信息，微博变化则需要爬取更新的微博
# 该方法返回需要爬取的微博数
crawl_info, wb_num = self.validater.validate_nums(page_id, nums)
self.crawl_info = crawl_info
return {
'uid': uid,
'page_id': page_id,
'nick': nick,
'domain': domain,
'location': location,
'follow_num': int(follow_num),
'fans_num': int(fans_num),
'wb_num': int(wb_num)
}
