微信公众号爬虫

96
繁著
2017.10.19 18:26* 字数 175

微信团队于2017-06-06发布更新:

“ 对所有公众号开放,在图文消息正文中插入自己帐号和其他公众号已群发文章链接的能力。”

那么,利用这个接口,我们就可以爬取指定公众号的文章链接了

文章参考:静觅

准备工具:一个订阅号,安装selenium

爬取步骤:




  1. get_cookie.py用selenium登陆,获取cookie,其中你需要勾选“记住”选项,还需要微信扫描二维码,确定顺利登陆
# -*- coding:utf-8 -*-
from selenium import webdriver
import io
import time
import json
from pprint import pprint

post = {}

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36")
driver = webdriver.Chrome('/Users/weiweiwang/code/financialNews/chromedriver',chrome_options=chrome_options)
driver.get('https://mp.weixin.qq.com/')
time.sleep(2)
driver.find_element_by_xpath("./*//input[@name='account']").clear()
driver.find_element_by_xpath("./*//input[@name='account']").send_keys('你的账号')
driver.find_element_by_xpath("./*//input[@name='password']").clear()
driver.find_element_by_xpath("./*//input[@name='password']").send_keys('你的密码')
# 在自动输完密码之后记得点一下记住我
time.sleep(5)
driver.find_element_by_xpath("./*//a[@class='btn_login']").click()
# 拿手机扫二维码!
time.sleep(15)
driver.get('https://mp.weixin.qq.com/')
cookie_items = driver.get_cookies()
for cookie_item in cookie_items:
    post[cookie_item['name']] = cookie_item['value']
cookie_str = json.dumps(post)
with io.open('cookie.txt', 'w+') as f:
    f.write(cookie_str.decode('utf-8'))
  1. get_url.py获取你需要的公众号的历史文章链接
# -*- coding:utf-8 -*-
import requests
import io
import redis
import json
import re
import random
import time

gzlist = ['yq_Butler']


url = 'https://mp.weixin.qq.com'
header = {
    "HOST": "mp.weixin.qq.com",
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36"
    }

with io.open('cookie.txt', 'r') as f:
    cookie = f.read()
cookies = json.loads(cookie)
response = requests.get(url=url, cookies=cookies)
token = re.findall(r'token=(\d+)', str(response.url))[0]
for query in gzlist:
    query_id = {
        'action': 'search_biz',
        'token' : token,
        'lang': 'zh_CN',
        'f': 'json',
        'ajax': '1',
        'random': random.random(),
        'query': query,
        'begin': '0',
        'count': '5',
    }
    search_url = 'https://mp.weixin.qq.com/cgi-bin/searchbiz?'
    search_response = requests.get(search_url, cookies=cookies, headers=header, params=query_id)
    lists = search_response.json().get('list')[0]
    fakeid = lists.get('fakeid')
    query_id_data = {
        'token': token,
        'lang': 'zh_CN',
        'f': 'json',
        'ajax': '1',
        'random': random.random(),
        'action': 'list_ex',
        'begin': '0',
        'count': '5',
        'query': '',
        'fakeid': fakeid,
        'type': '9'
    }
    appmsg_url = 'https://mp.weixin.qq.com/cgi-bin/appmsg?'
    appmsg_response = requests.get(appmsg_url, cookies=cookies, headers=header, params=query_id_data)
    max_num = appmsg_response.json().get('app_msg_cnt')
    num = int(int(max_num) / 5)
    begin = 0
    while num + 1 > 0 :
        query_id_data = {
            'token': token,
            'lang': 'zh_CN',
            'f': 'json',
            'ajax': '1',
            'random': random.random(),
            'action': 'list_ex',
            'begin': '{}'.format(str(begin)),
            'count': '5',
            'query': '',
            'fakeid': fakeid,
            'type': '9'
        }
        print('翻页###################',begin)
        query_fakeid_response = requests.get(appmsg_url, cookies=cookies, headers=header, params=query_id_data)
        fakeid_list = query_fakeid_response.json().get('app_msg_list')
        for item in fakeid_list:
            print(item.get('link'))
        num -= 1
        begin = int(begin)
        begin+=5
        time.sleep(2)

所有代码见github

人生苦短我用python