知乎的登录破解：   

  1 import requests  2 #适合python2和python3版本的导包  3 try:  4     import cookielib  5 except:  6     import http.cookiejar as cookielib  7 import re  8 from urllib import parse, request  9  10 #使用会话机制向url发送request,提高效率，不必每次都发请求(类比浏览器直接在本标签页操作，不需重新产生新的标签页) 11 session = requests.session() 12 #将会话产生的cookies保存在本地 13 session.cookies = cookielib.LWPCookieJar(filename="cookies.txt") 14  15 #浏览器版本信息，目的是伪装成一个浏览器，让服务器认为我们的代码是一个浏览器请求而不是爬虫，避免被拒绝 16 headers = { 17     "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:53.0) Gecko/20100101 Firefox/53.0", 18     "Host":"www.zhihu.com", 19     "Referer":"https://www.zhihu.com/", 20 } 21  22 #获取登录xsrf 23 def get_xsrf(): 24  25     url = "https://www.zhihu.com/#signin" 26  27     try: 28         #带上cookie,避免产生验证码识别 29         req = session.get(url=url,cookies=cookies,headers=headers) 30         #通过正则表达式解析出 xsrf 类比csrf机制 31         xsrf = re.findall(‘<input type="hidden" name="_xsrf" value="http://www.mamicode.com/(.*?)"/>‘,req.text) 32         if xsrf: 33             xsrf = xsrf[0] 34             print(xsrf) 35             return xsrf 36         else: 37             return xsrf 38     except Exception as e: 39         print(e) 40         print("failed download") 41  42  43  44 #知乎登录 45 def zhihu_login(account,password): 46  47     #首先获取xsrf 48     xsrf = get_xsrf() 49     #判断是手机号：以手机号登录，提交表单和提交URL不同，构造不同的URL和表单 50     if re.match("\d{10}",account): 51  52         url = "https://www.zhihu.com/login/phone_num" 53         data=http://www.mamicode.com/{ 54             "_xsrf":xsrf, 55             ‘remember_me‘: ‘true‘, 56             "password":password, 57             "phone_num":account 58         } 59     if ‘@‘ in account: 60         url = "https://www.zhihu.com/login/email" 61         data=http://www.mamicode.com/{ 62             "_xsrf":xsrf, 63             ‘remember_me‘: ‘true‘, 64             "password":password, 65             "email":account 66         } 67     #将获取到的xsrf加载到cookie中 68     cookies["_xsrf"] = xsrf 69     #带上表单，头信息，cookies申请登录 70     r = session.post(url=url,data=http://www.mamicode.com/data,headers=headers,cookies=cookies) 71     print(r.text) 72     #登录成功将cookies保存到本地 73     session.cookies.save() 74  75  76 #获取首页;登录后可直接获取，因为session中已经(带了)加载了cookie 77 def get_index(): 78     response = session.get("https://www.zhihu.com/",headers=headers) 79     print(response.status_code) 80     #将首页写入本地文件 81     with open("index_page.html","wb") as f: 82         f.write(response.text.encode("utf-8")) 83     print("write ok") 84  85 #查看登录状态;向一个只有登录的页面get,若登录会返回200；否则304，会重定向到登录页(重定向后会返回200) 86 def is_login(): 87     url = "https://www.zhihu.com/inbox" 88     #allow_redirects  禁止重定向 89     response  = session.get(url=url,headers=headers,allow_redirects=False) 90     #判断是否登录 91     if response.status_code != 200: 92         return False 93     else: 94         return True 95  96  97 #先尝试本地cookie登录，不成功使用浏览器copy下来的cookies重新登录,生成本地cookies 98 try: 99     #先尝试加载之前保存在本地的cookies100     session.cookies.load(ignore_discard=True)101     print("cookies 已记载")102 except:103     #没加载就重新登录104     print("cookie 未加载")105     #这个cookie是从firebug中复制来的106     cookies = {107     "d_c0":"",108     "l_cap_id":"",109     "r_cap_id":"",110     "cap_id":"",111     "_zap":"",112     "__utmc":"",113     "__utmb":"",114     "__utmv":"",115     "__utma":"",116     "__utmz":"",117     "q_c1":""118 119 }120     #调用登录函数,成功后会更新cookie到本地121     zhihu_login("342200377@qq.com","19971013zf")122     #更新成功后重新加载cookies123     session.cookies.load(ignore_discard=True)124 125 126 print(is_login())