python 爬取微信文章（搜狗为入口）

本人想搞个采集微信文章的网站，无奈实在从微信本生无法找到入口链接，网上翻看了大量的资料，发现大家的做法总体来说大同小异，都是以搜狗为入口。下文是笔者整理的一份python爬取微信文章的代码，有兴趣的欢迎阅读，本人小站：www.quzhuanpan.com喜欢的话可以去首页加官方微信或者qq。
#coding:utf-8
author = \’haoning\’
**#!/usr/bin/env python
import time
import datetime
import requests**
import json
import sys
reload(sys)
sys.setdefaultencoding( \”utf-8\” )
import re
import xml.etree.ElementTree as ET
import os
#OPENID = \’oIWsFtyel13ZMva1qltQ3pfejlwU\’
OPENID = \’oIWsFtw_-W2DaHwRz1oGWzL-wF9M&ext\’
XML_LIST = []
# get current time in milliseconds
current_milli_time = lambda: int(round(time.time() * 1000))
def get_json(pageIndex):

global OPENID
the_headers = {
\'User-Agent\': \'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36\',
\'Referer\': \'http://weixin.sogou.com/gzh?openid={0}\'.format(OPENID),
\'Host\': \'weixin.sogou.com\'
}

url = \'http://weixin.sogou.com/gzhjs?cb=sogou.weixin.gzhcb&openid={0}&page={1}&t={2}\'.format(OPENID, pageIndex, current_milli_time()) #url
print(url)

response = requests.get(url, headers = the_headers)
# TO-DO; check if match the reg
response_text = response.text
print response_text
json_start = response_text.index(\'sogou.weixin.gzhcb(\') + 19
json_end = response_text.index(\')\') - 2
json_str = response_text[json_start : json_end] #get json
#print(json_str)
# convert json_str to json object
json_obj = json.loads(json_str) #get json obj
# print json_obj[\'totalPages\']
return json_obj

def add_xml(jsonObj):

global XML_LIST
xmls = jsonObj[\'items\'] #get item
#print type(xmls)
XML_LIST.extend(xmls) #用新列表扩展原来的列表
**[#www.oksousou.com][2]**

# ———— Main —————-
print \’play it