1 # -*- coding: utf-8 -*- 
 2 
 3 import scrapy
 4 import json
 5 import re
 6 
 7 
 8 
 9 
10 
11 class ZhihuSpider(scrapy.Spider):
12 
13     name = "zhihu"
14     allowed_domains = ["zhihu.com"]
15     start_urls = [‘http://www.zhihu.com/‘]
16     #头部
17     headers = {
18     "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",
19     "Host":"www.zhihu.com",
20     "Referer":"https://www.zhihu.com/",
21 }
22     #从已经登陆的浏览在中copy下来的
23     cookies = {
24     "d_c0":"",
25     "l_cap_id":"",
26     "r_cap_id":"",
27     "cap_id":"",
28     "_zap":"",
29     "__utmc":"",
30     "__utmb":"",
31     "__utmv":"",
32     "__utma":"",
33     "__utmz":"5",
34     "q_c1":"",
35     }
36     #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）
37     def start_requests(self):
38         #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
39         return [scrapy.Request(url="https://www.zhihu.com/#signin",cookies=self.cookies,headers=self.headers,callback=self.login)]
40 
41 
42     #知乎登录
43     def login(self,response):
44         #正则匹配出xsrf
45         response_text = response.text
46         match_obj = re.match(‘.*name="_xsrf" value="(.*?)"‘, response_text, re.DOTALL)
47         if match_obj:
48             xsrf = (match_obj.group(1))
49 
50         url = "https://www.zhihu.com/login/phone_num"
51         data={
52             "_xsrf":xsrf,
53             ‘remember_me‘: ‘true‘,
54             "password":"",
55             "phone_num":""
56         }
57 
58         #将获取到的xsrf加载到cookie中
59         self.cookies["_xsrf"] = xsrf
60         #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
61         return [scrapy.FormRequest(url=url,headers=self.headers,formdata=data,callback=self.check_login)]
62 
63     #查看登录状态；登陆成功则默认回调parse函数进行解析网页
64     def check_login(self,response):
65         text_json = json.load(response.text)
66         if "msg" in text_json and text_json["msg"]=="\u767b\u5f55\u6210\u529f":
67             for urls in self.start_urls:
68                yield scrapy.Request(url=urls,dont_filter=True,headers=self.headers)
69 
70 
71 
72 
73     def parse(self, response):
74         pass