正统模拟登录方法

 # coding:utf-8
  2 
  3 import scrapy
  4 
  5 # 正统模拟登录方法，首先用get请求获取到页面里登录必须的参数，例如知乎的_zsrf
  6 # 然后和账号密码一起post到服务器，登录成功
  7 class RenrenSpider(scrapy.Spider):
  8     name = "ren"
  9     allowed_domains = ["renren.com"]
 10     start_urls = ["http://www.renren.com/PLogin.do"]
 11 
 12     def parse(self,response):
 13         yield scrapy.FormRequest.from_response(
 14                 response,
 15                 formdata = {"email": "1316","password": "131"},
 16                 callback = self.parse_page
 17             )
 18 
 19     def parse_page(self,response):
 20         print("---------------------------1-----------" + response.url)
 21         url = "http://www.renren.com/310446841/profile"
 22         yield scrapy.Request(url, callback = self.parse_newpage)
 23 
 24     def parse_newpage(self,response):
 25         print("---------------------2-----------" + response.url)
 26         with open("chen.html","w") as f:
 27             f.write(response.body)
~