1 # -*- coding:utf-8 -*- 
 2 
 3 # Author: benjaminYang
 4 from slenium import webdriver
 5 
 6 import time
 7 
 8 import json
 9 
10 driver=webdriver.Chrome() #需要一个谷歌驱动
11 
12 driver.get(“http://mp.weixin.qq.com”) #所要驱动操作的页面url
13 
14  
15 
16 driver.find_element_by_xpath(‘//*[@id="header"]/div[2]/div/div/form/div[1]/div[1]/div/span/input‘).clear()        #获取用户名输入框的xpath并清空
17 driver.find_element_by_xpath(‘//*[@id="header"]/div[2]/div/div/form/div[1]/div[1]/div/span/input‘).send_keys(‘你自己的公众号用户名‘) #自动填写用户名
18 time.sleep(2)
19 
20 
21 
22 driver.find_element_by_xpath(‘//*[@id="header"]/div[2]/div/div/form/div[1]/div[2]/div/span/input‘).clear()   #获取密码输入框的xpath并清空
23 
24 driver.find_element_by_xpath(‘//*[@id="header"]/div[2]/div/div/form/div[1]/div[2]/div/span/input‘).send_keys(‘你的密码‘)   #自动输入密码
25 
26 time.sleep(2)
27 
28 driver.find_element_by_xpath(‘//*[@id="header"]/div[2]/div/div/form/div[3]/label‘).click()  #获取记住账号label的xpath并勾选
29 
30 time.sleep(2)            driver.find_element_by_xpath(‘//*[@id="header"]/div[2]/div/div/form/div[4]/a‘).click()
31 #获取登录div的xpath 并点击
32 
33 time.sleep(15)           
34  
35 cookies=driver.get_cookies() #获取登录之后的cookies
36  
37 cookie={} 
38 from items in cookies:
39      cookie[items.get(‘name’)]=items.get(‘value’) #将获取到的cookies 存入到cookie字典里
40 with open(‘cookies.txt’,’w’) as file:
41      file.wrie(json.dumps(cookie)  #dict转化成str 存入txt文件中
42 driver.close()

#!/usr/bin/env python

# -*- coding:utf-8 -*- 

# Author: benjaminYang
Import  request

Import  json

Import  re

Import  random

Import  time

 

def main(query):

         with open(‘cookies.txt’) as file:

                  cookie=file.read()          #读取cookies文件内容

    url=‘https://mp.weixin.qq.com/‘
headers={‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36‘

,‘Referer‘:‘https://mp.weixin.qq.com/cgi-bin/appmsg?t=media/appmsg_edit_v2&action=edit&isNew=1&share=1&type=10&lang=zh_CN&token=1988933146‘

,‘Host‘:‘mp.weixin.qq.com‘,

         }              #设置请求头部 User-Agent, Referer, Host
cookies=json.loads(cookie) #str转成dict
response=requests.get(url,cookies=cookies)
token=re.findall(‘token=(\d+)’,str(response,url))[0] #获取url中的token
 
data={
‘token‘:token,

‘lang‘:‘zh_CN‘,        

‘f‘: ‘json‘,            

‘ajax‘:‘1‘,                #使用ajax异步

‘random‘:random.random(),  #生成随机数

‘url‘:query,               #搜索的文章类型

‘begin‘:‘0‘,              #从第一个文章开始

‘count‘:‘3‘,            #每页文章数目 
}
search_url=‘https://mp.weixin.qq.com/cgi-bin/operate_appmsg?sub=check_appmsg_copyright_sta‘
search_response=requests.post(search_url,cookies=cookies,data=data,headers=headers)
max_num=search_reponse.json().get(‘total’)# 获取所有文章的条数
num=int(int(max_num/3) #文章的总页数，一页3篇除最后一页
 
begin=0
while num+1>0;
     data={
‘token‘: token,

‘lang‘: ‘zh_CN‘,

‘f‘: ‘json‘,

‘ajax‘: ‘1‘,

‘random‘: random.random(),

‘url‘: query,

‘begin‘: ‘{}‘.format(str(begin)),

‘count‘: ‘3‘,
}
search_response = requests.post(search_url, cookies=cookies, data=data, headers=headers)

content=search_response.json().get(‘list‘)
 
for items in content:

    print (items.get(‘title‘))#标题

    print (items.get(‘url‘))  #文章的url

    print (items.get(‘nickname‘))

    num -=1      #每循环一次总页数减一

    begin=int(begin)    

    begin+=3       #每循环一次文章数加3
 
    time.sleep(5)
if __name__==’__main__’:
query=input(‘请输入你要搜索的文章：’)
main(query)