python 爬虫网页登陆的简单实现

 #! -*- encoding:utf-8 -*-
  import requests
  import random
  import requests.adapters

  # 要访问的目标页面
  targetUrlList = [
    "https://httpbin.org/ip",
    "https://httpbin.org/headers",
    "https://httpbin.org/user-agent",
  ]

  # 代理服务器
  proxyHost = "t.16yun.cn"
  proxyPort = "31111"

  # 代理隧道验证信息
  proxyUser = "username"
  proxyPass = "password"

  proxyMeta = "http://%(user)s:%(pass)s@%(host)s:%(port)s" % {
    "host": proxyHost,
    "port": proxyPort,
    "user": proxyUser,
    "pass": proxyPass,
  }

  # 设置 http和https访问都是用HTTP代理
  proxies = {
    "http": proxyMeta,
    "https": proxyMeta,
  }

  # 访问三次网站，使用相同的Session(keep-alive)，均能够保持相同的外网IP
  s = requests.session()

  # 设置cookie
  cookie_dict = {"JSESSION":"123456789"}
  cookies = requests.utils.cookiejar_from_dict(cookie_dict, cookiejar=None, overwrite=True)
  s.cookies = cookies

  for i in range(3):
    for url in targetUrlList:
      r = s.get(url, proxies=proxies)
      print r.text
若存在验证码，此时采用resp**e = requests_session.post(url=url_login, data=data)是不行的，做法应该如下：

resp**e_captcha = requests_session.get(url=url_login, cookies=cookies)
resp**e1 = requests.get(url_login) # 未登陆
resp**e2 = requests_session.get(url_login) # 已登陆，因为之前拿到了Resp**e Cookie！
resp**e3 = requests_session.get(url_results) # 已登陆，因为之前拿到了Resp**e Cookie！