Python爬虫-爬取伯乐在线美女邮箱

爬取伯乐在线美女邮箱

1.登录界面的进入,设置url，cookie，data，headers

2.进入主页，点击邮箱链接，需要重新设置url，cookie(读取重新保存的cookie)，data，headers

  1 '''
  2 爬取伯乐在线的美女联系方式
  3 需要：
  4 1. 登录
  5 2. 在登录和相应声望值的前提下，提取对方的邮箱
  6 '''
  7 
  8 from urllib import request, error, parse
  9 from http import cookiejar
 10 import json
 11 
 12 def login():
 13     '''
 14     输入用户名称和密码
 15     获取相应的登录cookie
 16     cookie 写文件
 17     :return:
 18     '''
 19 
 20     # 1. 需要找到登录入口
 21     url = "http://date.jobbole.com/wp-login.php"
 22 
 23     # 2. 准备登录数据
 24     data = {
 25         "log": "augsnano",
 26         "pwd": "123456789",
 27         # 登陆后重定向地址
 28         "redirect_to": "http://date.jobbole.com/4965/",
 29         "rememberme": "on"
 30     }
 31 
 32     data = parse.urlencode(data).encode()
 33 
 34 
 35     # 3. 准备存放cookie文件
 36     # r表示不转义
 37     f = r'jobbole_cookie.txt'
 38 
 39     # 4. 准备请求头信息
 40     headers = {
 41         "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.119 Safari/537.36",
 42         "Connection": "keep-alive"
 43 
 44     }
 45 
 46     # 5. 准备cookie hanlder
 47     cookie_handler = cookiejar.MozillaCookieJar(f)
 48 
 49     # 6. 准备http请求handler
 50     http_handler = request.HTTPCookieProcessor(cookie_handler)
 51 
 52 
 53     # 7. 构建opener
 54     opener = request.build_opener(http_handler)
 55 
 56     # 8. 构建请求对象
 57     req = request.Request(url, data=data, headers=headers)
 58 
 59     # 9. 发送请求
 60     try:
 61         rsp = opener.open(req)
 62 
 63         cookie_handler.save(f, ignore_discard=True, ignore_expires=True)
 64 
 65         html = rsp.read().decode()
 66         print(html)
 67     except error.URLError as e:
 68         print(e)
 69 
 70 
 71 def getInfo():
 72     # 1. 确定url
 73     url = "http://date.jobbole.com/wp-admin/admin-ajax.php"
 74 
 75     # 2. 读取已经保存的cookie
 76     f = r'jobbole_cookie.txt'
 77     cookie = cookiejar.MozillaCookieJar()
 78     cookie.load(f, ignore_expires=True, ignore_discard=True)
 79 
 80     # 3. 构建http_handler
 81     http_handler = request.HTTPCookieProcessor(cookie)
 82 
 83     # 4. 构建opener
 84     opener = request.build_opener(http_handler)
 85 
 86     # 以下是准备请求对象的过程
 87 
 88     # 5. 构建data
 89     data = {
 90         "action": "get_date_contact",
 91         "postId": "4965"
 92     }
 93 
 94     data = parse.urlencode(data).encode()
 95 
 96     # 6. 构建请求头
 97     headers = {
 98         "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.119 Safari/537.36",
 99         "Connection": "keep-alive"
100     }
101 
102     # 7. 构建请求实体
103     req = request.Request(url, data=data, headers=headers)
104 
105     # 8. 用opener打开
106     try:
107         rsp = opener.open(req)
108         html = rsp.read().decode()
109 
110         html = json.loads(html)
111         print(html)
112 
113         f = "rsp.html"
114         with open(f, 'w') as f:
115             f.write(html)
116 
117     except Exception as e:
118         print(e)
119 
120 
121 
122 
123 
124 
125 if __name__ == '__main__':
126     getInfo()