Scrapy基础(十四)————Scrapy实现知乎模拟登陆

模拟登陆大体思路见此博文，本篇文章只是将登陆在scrapy中实现而已

之前介绍过通过requests的session 会话模拟登陆；必须是session,涉及到验证码和xsrf的
写入cookie验证的问题；在scrapy中不需担心此问题，因为Request会保证这是一个会话，并且自动传递cookies
原理想通，因为验证码识别的问题，这里先使用cookie模拟登陆

 # -*- coding: utf-8 -*- 

 import scrapy
 import json
 import re

 class ZhihuSpider(scrapy.Spider):

     name = "zhihu"
     allowed_domains = ["zhihu.com"]
     start_urls = ['http://www.zhihu.com/']
     #头部
     headers = {
     "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
     "Host":"www.zhihu.com",
     "Referer":"https://www.zhihu.com/",
 }
     #从已经登陆的浏览在中copy下来的
     cookies = {
     "d_c0":"",
     "l_cap_id":"",
     "r_cap_id":"",
     "cap_id":"",
     "_zap":"",
     "__utmc":"",
     "__utmb":"",
     "__utmv":"",
     "__utma":"",
     "__utmz":"",
     "q_c1":"",
     }
     #最开始请求的reqeust函数，自动调用,将首次获取的response返回给登陆函数（里面有xsrf）
     def start_requests(self):
         #必须带上cookie；return返回，不用生成器，只需爬取登陆页面一次，而且必须返回一个可迭代对象,所以是列表
         return [scrapy.Request(url="https://www.zhihu.com/#signin",cookies=self.cookies,headers=self.headers,callback=self.login)]

     #知乎登录
     def login(self,response):
         #正则匹配出xsrf
         response_text = response.text
         match_obj = re.match('.*name="_xsrf" value="(.*?)"', response_text, re.DOTALL)
         if match_obj:
             xsrf = (match_obj.group(1))

         url = "https://www.zhihu.com/login/phone_num"
         data={
             "_xsrf":xsrf,
             'remember_me': 'true',
             "password":"",
             "phone_num":""
         }

         #将获取到的xsrf加载到cookie中
         self.cookies["_xsrf"] = xsrf
         #通过FormRequest提交表单,这里的request对象和之前的session一样,还是处于刚刚的对话中；回调给检查登陆的函数
         return [scrapy.FormRequest(url=url,headers=self.headers,formdata=data,callback=self.check_login)]

     #查看登录状态；登陆成功则默认回调parse函数进行解析网页
     def check_login(self,response):
         text_json = json.load(response.text)
         if "msg" in text_json and text_json["msg"]=="\u767b\u5f55\u6210\u529f":
             for urls in self.start_urls:
                yield scrapy.Request(url=urls,dont_filter=True,headers=self.headers)

     def parse(self, response):
         pass