python--爬虫--利用cookie登录网络教学中心刷评论

声明：本文仅供学习参考

这个功能终于实现了，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

 # coding   :utf-8
 # @Time    : 2017/8/7 8:00
 # @Author  : Yong-life
 # @File    : translateCookies.py

 def translatestr(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

手动模拟了几遍，发现关键的几部，就可以完成了

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

 import re
 import time
 import requests
 from translateCookies import translatestr
 def gethtml(url):
     cookie = '__dxca=75091f84-4096-4d77-ba79-47356cc19b1e; 2334userinfo=bd47f4dce1b38171d15866435d79f7a9d807a544f7930b6abeaaa6286f1f1754e7876672f860a859c0433867ead52763adde0d57e85b541e; 2334UID=27561080; 2334enc=2DC5074C7374D67F2ACD4C1F5A7E7F56; _uid=27561080; uf=0d7d2f765ae428714a3fffffed66c4445f985d480e6f2f069b0594e13f4b452f9f4fcd6f19e32a2edcaf7a1eebd6007c0d8a4c92b12beb4be5b05dc70bcb18cfc05a9b956030332946da21146a924e23; _d=1502066525521; UID=27561080; vc=2DC5074C7374D67F2ACD4C1F5A7E7F56; vc2=AD5E945ED353A9AE790FA793E860A279; DSSTASH_LOG=C_38-UN_968-US_27561080-T_1502066525521; k8s=ba998ae2451b05102dd62f59c4aae09e27424974; route=7aaebcbdcf7cf94856c7fb5f82d77b4b; fanyamoocs=5CED1B5320BFFBA211401F839C536D9E; fid=2334; isfyportal=1; JSESSIONID=42822D4D414525EFAF03F092E432FCEA'
     cookie = translatestr(cookie)
     header = {
         'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36',
         'Content-Type': 'text/html;charset=UTF-8'#
     }
     response = requests.get(url, headers=header, cookies=cookie)
     return response.text
 def crawlingClassid(html):
     classidList = []
     pattern_classid = 'class="Mcon1img httpsClass" >[\s]*<a[\s]*href=\'(.*?)\'  target="_blank"   >'
     classidList.extend(re.findall(pattern_classid, html))
     fileList = []
     pattern_file = r'class="Mcon1img">[\s]*<input type="hidden" value="(.*?)" />'
     fileList.extend(re.findall(pattern_file, html))
     for file_id in fileList:
         file_url = 'http://mooc1.xynu.edu.cn/visit/courses/study?isAjax=true&fileId=' + file_id
         classidList.extend(crawlingClassid(gethtml(file_url)))
     return classidList
 def sendMsg(courseId, clazzid, count):
     url = 'http://mooc1.xynu.edu.cn/bbscircle/grouptopic/publish'
     cookie = '__dxca=75091f84-4096-4d77-ba79-47356cc19b1e; 2334userinfo=bd47f4dce1b38171d15866435d79f7a9d807a544f7930b6abeaaa6286f1f1754e7876672f860a859c0433867ead52763adde0d57e85b541e; 2334UID=27561080; 2334enc=2DC5074C7374D67F2ACD4C1F5A7E7F56; _uid=27561080; uf=0d7d2f765ae428714a3fffffed66c4445f985d480e6f2f069b0594e13f4b452f9f4fcd6f19e32a2edcaf7a1eebd6007c0d8a4c92b12beb4be5b05dc70bcb18cfc05a9b956030332946da21146a924e23; _d=1502066525521; UID=27561080; vc=2DC5074C7374D67F2ACD4C1F5A7E7F56; vc2=AD5E945ED353A9AE790FA793E860A279; DSSTASH_LOG=C_38-UN_968-US_27561080-T_1502066525521; k8s=ba998ae2451b05102dd62f59c4aae09e27424974; route=7aaebcbdcf7cf94856c7fb5f82d77b4b; fanyamoocs=5CED1B5320BFFBA211401F839C536D9E; fid=2334; isfyportal=1; JSESSIONID=42822D4D414525EFAF03F092E432FCEA'

     cookie = translatestr(cookie)
     header = {
         'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36',
         'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'  #
     }
     for i in range(1, count):
         data = ('courseId='+ courseId +'&clazzid='+ clazzid +'&title='+ str(i) +'&content=&type=4&files=').encode('utf-8')
         print('send: ' + courseId +' '+ str(i))
         response = requests.post(url, data, cookies=cookie, headers=header)
         time.sleep(3)
 def managerCrawling():
     url = 'http://mooc1.xynu.edu.cn/visit/courses?template=1&s=7c6b45e1ac1448adf0ff862c75c8ab3f'
     html = gethtml(url)
     MAX_COUNT = 3
     class_url_list = crawlingClassid(html)
     threads = []
     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)
         courseId, clazzid = regx.group(1), regx.group(2)
         sendMsg(courseId, clazzid, MAX_COUNT)
 if __name__=='__main__':
     managerCrawling()

效果：