import urllib import urllib2 import os import requests import re import json sns_url = 'http://sns.video.qq.com/fcgi-bin/video_comment_id?otype=json&op=3&vid=' url = 'http://v.qq.com/cover/q/qviv9yyjn83eyfu.html?vid=n0016ibg4eb' head = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.71 Safari/537.36'} QQTV = 'http://coral.qq.com/article/%s/comment?commentid=0&reqnum=10' def find_html(): response = urllib2.urlopen(url) html = response.read(); return html def find_vid(): response = find_html() #vid = re.search('vid:"(.*?)",',response.body,re.S).group(1) vid = re.search('vid:"(.*?)",',str(response),re.S).group(1) vid_url = sns_url + str(vid) return vid_url def find_fin(): qq_url = find_vid() response = urllib2.urlopen(qq_url) html = response.read() comment = re.search('"comment_id":"(.*?)",',str(html),re.S).group(1) # print(comment) fin_html = QQTV % comment return fin_html def get_message(): comment_url = find_fin() print(comment_url) json_comment = requests.get(comment_url,headers = head).content json_Dict = json.loads(json_comment) json_Data = json_Dict['data'] json_comment = json_Data['commentid'] for each in json_comment: print(each['content']) if __name__ == '__main__': get_message()