python公众号文章_python采集微信公众号文章

本文实例为大家分享了python采集微信公众号文章的具体代码，供大家参考，具体内容如下

在python一个子目录里存2个文件，分别是：采集公众号文章.py和config.py。 代码如下：

1.采集公众号文章.py

from urllib.parse import urlencode

import pymongo

import requests

from lxml.etree import XMLSyntaxError

from requests.exceptions import ConnectionError

from pyquery import PyQuery as pq

from config import *

#配置MongoDB

client = pymongo.MongoClient(MONGO_URI)

db = client[MONGO_DB]

base_url = 'http://weixin.sogou.com/weixin?'

#添加头文件

headers = {

'Cookie': 'usid=S-pkM6vW_ac4ktr1; SUV=00A75E9078EFD9F75A6573ECAD0EC883; wuid=AAGCxerSHQAAAAqRGn4SoAgAAAA=; IPLOC=CN4414; SUID=767BEAB73220910A000000005AA9E2AA; pgv_pvi=159197184; pgv_si=s8252565504; ABTEST=0|1521083055|v1; weixinIndexVisited=1; sct=1; JSESSIONID=aaalXqKRP6JjS8ac4Hwhw; ppinf=5|1521083238|1522292838|dHJ1c3Q6MToxfGNsaWVudGlkOjQ6MjAxN3x1bmlxbmFtZTo2OiUzQSUyOXxjcnQ6MTA6MTUyMTA4MzIzOHxyZWZuaWNrOjY6JTNBJTI5fHVzZXJpZDo0NDpvOXQybHVOaExNcS1vLW1zbjMxMmNMSkp4OGpZQHdlaXhpbi5zb2h1LmNvbXw; pprdig=tbVf7qLZdDMjpCn4jTf3dg8C8NeRX-YgDi8KUcezn0rteWuhkgU4xMNaxZbakVQuswboIGl