用cookie登录慕课网络教学中心刷评论

声明：本文仅供学习参考

我们学校和的网络教学平台是在慕课网上的，需要登录到慕课网的教学平台以后，拿到cookie

注意：没次提交后需要休眠，否则刷评论过快会被系统发现

如果请求太快，很容易被系统发现（输入验证码）所以没用多线程

对于cookie的获取采取手动方式，也可以尝试从浏览器获取cookie，cookie需要转化为字典形式

chrome浏览器cookie的位置在：“C:\Users\Garbos\AppData\Local\Google\Chrome\User Data\Default\Cookies”，需要修改路径中的系统用户名

 # coding   :utf-8
 # @Time    : 2017/7/30 16:42
 # @Author  : Jingxiao Fu
 # @File    : headers_cookies.py
 import random
 import os
 import subprocess
 import sqlite3
 import win32crypt
 import sys

 header_str = '''Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50
 Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)
 Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)'''

 def get_headers():
     header = header_str.split('\n')
     header_length = len(header)
     headers = {
         'Connection': 'keep-alive',
         'user-agent': header[random.randint(0, header_length - 1)],
         'Content-Type': 'application/x-www-form-urlencoded',
         'Accept-Language': 'zh-CN,zh;q=0.8'
     }
     return headers

 def get_cookie_use_hand():
     '''手动复制cookie'''
     cookie = ""

     cookie = cookie.replace('Cookie:', '')
     cookie = cookie.replace(' ', '')
     cookies = cookie.split(';')
     for i in range(len(cookies)):
         cookies[i] = cookies[i].replace('=', ':', 1)
     cookies_dict = {}
     for header in cookies:
         L = header.split(':', 1)
         cookies_dict[L[0]] = L[1]
     return cookies_dict

 '''从chrome浏览器获取cookie'''

 def get_cookie_from_chrome():
     host_url = 'mooc1.xynu.edu.cn'
     cookie_file_path = r"C:\Users\Garbos\AppData\Local\Google\Chrome\User Data\Default\Cookies"

     sql_query = "select host_key, name, encrypted_value ,value from cookies WHERE host_key='%s'" % host_url
     with sqlite3.connect(cookie_file_path) as con:
         cu = con.cursor()
         cu.execute(sql_query)
         cookies_sql = {name: win32crypt.CryptUnprotectData(encrypted_value)[1].decode() for
                        host_key, name, encrypted_value, value in cu.execute(sql_query).fetchall()}

     return cookies_sql

手动模拟几遍，发现关键的步骤，就可以实现

 # coding   :utf-8
 # @Time    : 2017/8/7 9:19
 # @Author  : Yong-life
 # @File    : CrawlingNetStudyRoom.py

 import re
 import time
 import requests
 from headers_cookies import get_headers
 from headers_cookies import get_cookie_from_chrome

 def get_response(url):
     '''封装http请求'''
     cookie = get_cookie_from_chrome()
     response = requests.get(url, headers=get_headers(), cookies=cookie)
     return response.text

 def crawling_classid(html):
     '''爬取课程列表，因为可能有些可能放在了文件夹中，需要递归遍历'''
     classid_list = []
     pattern_classid = 'httpsClass" >[\s]*<a[\s]*href=\'(.*?)\'  target="_blank"   >'
     classid_list.extend(re.findall(pattern_classid, html))
     file_list = []
     pattern_file = r'class="Mcon1img">[\s]*<input type="hidden" value="(.*?)" />'
     file_list.extend(re.findall(pattern_file, html))
     for file_id in file_list:
         file_url = 'http://mooc1.xynu.edu.cn/visit/courses/study?isAjax=true&fileId=' + file_id
         classid_list.extend(crawling_classid(get_response(file_url)))
     return classid_list

 def send_msg(course_id, clazz_id, count):
     '''发送请求，刷评论，可以修改data中的str(i)'''
     url = 'http://mooc1.xynu.edu.cn/bbscircle/grouptopic/publish'
     cookie = get_cookie_from_chrome()
     for i in range(1, count+1):
         data = (
         'courseId=' + course_id + '&clazzid=' + clazz_id + '&title=' + str(i) + '&content=&type=4&files=').encode(
             'utf-8')
         print('send: ' + course_id + ' ' + str(i))
         response = requests.post(url, data, cookies=cookie, headers=get_headers())
         time.sleep(3)

 def manager_crawling():
     url = 'http://mooc1.xynu.edu.cn/visit/courses?template=1&s=7c6b45e1ac1448adf0ff862c75c8ab3f'
     html = get_response(url)
     print('已进入学习空间...')
     MAX_COUNT = 10
     class_url_list = crawling_classid(html)
     print('爬取学习空间课程列表...')
     print('开始发送数据...')
     for i, url in zip(range(len(class_url_list)), class_url_list):
         pattern_class = r'courseId=(.*?)&clazzid=(.*?)&enc'
         regx = re.search(pattern_class, url)
         course_id, clazz_id = regx.group(1), regx.group(2)
         send_msg(course_id, clazz_id, MAX_COUNT)

     print('执行完毕!')

 if __name__ == '__main__':
     manager_crawling()

效果：

 少年，还在为学校规定的评论数发愁吗？