Python学习之抓去微信文章地址

#!/usr/bin/python3
# -*- coding: UTF-8 -*-
import time
import json
import requests
import re
import random

with open('cookies.txt', 'r') as f:
    cookie = f.read()
cookies = json.loads(cookie)
query = 'python'
url = 
response = requests.get(url=url, cookies=cookies)
print(response.url)
token = re.findall(r'token=(\d+)', str(response.url))[0]
print(token)

headers = {
    'Host': 
    'Connection': 'keep-alive',
    'Accept': 'application/json, text/javascript, */*; q=0.01',
    'Origin': 
    'X-Requested-With': 'XMLHttpRequest',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36',
    'Referer':  % token,
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.8',
}

data = {
    'token': token,
    'lang': 'zh_CN',
    'f': 'json',
    'ajax': '1',
    'random': random.random(),
    'url': query,
    'begin': '0',
    'count': '3',
}

search_url = 

search_response = requests.post(search_url, cookies=cookies, data=data, headers=headers)

content = search_response.json().get('list')
max_num = search_response.json().get('total')

num = int(int(max_num / 3))
begin = 0
while num + 1 > 0:
    data = {
        'token': token,
        'lang': 'zh_CN',
        'f': 'json',
        'ajax': '1',
        'random': random.random(),
        'url': query,
        'begin': begin,
        'count': '3',
    }
    search_response = requests.post(search_url, cookies=cookies, data=data, headers=headers)
    content = search_response.json().get('list')
    for item in content:
        print(item.get('title'))
        print(item.get('url'))
    num -= 1
    begin = int(begin)
    begin += 3
    time.sleep(5)

'''

POST /cgi-bin/operate_appmsg?sub=check_appmsg_copyright_stat HTTP/1.1
Host: 
Connection: keep-alive
Content-Length: 93
Accept: application/json, text/javascript, */*; q=0.01
Origin: 
X-Requested-With: XMLHttpRequest
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36
Content-Type:  charset=UTF-8
Referer: 
Accept-Encoding: gzip, deflate, br
Accept-Language: zh-CN,zh;q=0.8
Cookie: uuid=cd825042331d7df020ed99923ea197e0; ticket=b16a87ff3386c63c8bfdfa41f29b9370c3c3f8b0; ticket_id=gh_43eac31c7156; cert=oOCdsQpP0CmVtcd5UJeZPLWF0aCi8DaW; noticeLoginFlag=1;  data_bizuin=3211400906; data_ticket=CzLCzqc9dlajT9jS38LpewTKWCssHIqjFBlrt6RZdDUcAtwSJ12UePry8oDAWY2U; xid=169de70f29b0774e3f0f06078d7bd08e; openid2ticket_oyhZqv-FCu9B0qdiZACeB1V3iUQY=m4sfFODJcBQvk3GL4htNrVV5QVkpdRZUOJw0ty1Gizc=; ua_id=QvEoIaaEyUAyqoBVAAAAABRDD5s0BFYfMLaye0agITg=; slave_user=gh_43eac31c7156; slave_sid=b3ZwMWJDU1M3S0RJalFkeUN5N1ZJNl9QYVpmRWNZT2dNbk9KbFVkV2lwQlRlWXZYVEN2YWk0VFpOVjEzd0RrWFZqSVRJeHJIX1BEcDFjSVRwbGZxZ3B3MHFiTnNOR3RPM3FSRjlxY2V0NlJ0OU9YeDBxcWFBRmE3N0d5OGxWQzdFck1mazZnaVpuQUp1S3BC; bizuin=3277315949



token:228900066
lang:zh_CN
f:json
ajax:1
random:0.8357587121245356
url:python
begin:0
count:3

token:228900066
lang:zh_CN
f:json
ajax:1
random:0.7160792781038223
url:python
begin:3
count:3

'''