scrapy模拟登录值携带cookie

Posted 2021-02-20 gouq

 

 

 

 登录人人网的一个小例子：

 1 # -*- coding: utf-8 -*-
 2 import scrapy
 3 import re
 4 
 5 class RenrenSpider(scrapy.Spider):
 6     name = ‘renren‘
 7     allowed_domains = [‘renren.com‘]
 8     start_urls = [‘http://www.renren.com/469175544/profile‘]
 9 
10     #重写 start_requests函数
11     def start_requests(self):
12         cookies = "anonymid=k9qu49f8-u2i9f6; depovince=GW; _r01_=1; JSESSIONID=abcyifRVJlHZa8oZrZzhx; ick_login=0e0c11f7-bf9d-459c-a90e-58cd4c4080d1; taihe_bi_sdk_uid=1484c0da41eccfff893c567343c25dfc; taihe_bi_sdk_session=5593c355d7a1c951d83c0bea940cee01; _de=DFB3AA5FF07DCEC55398183FA2F16FA6; ick=82f1abf5-42ab-4a45-bf6e-5b62ffa52a32; __utma=151146938.214793330.1588497096.1588497096.1588497096.1; __utmc=151146938; __utmz=151146938.1588497096.1.1.utmcsr=renren.com|utmccn=(referral)|utmcmd=referral|utmcct=/; __utmb=151146938.4.10.1588497096; jebecookies=01c2365d-44a6-4092-9350-7d4aee6560f7|||||; p=d3581425a61f49a0d4299705fff295624; first_login_flag=1; ln_uact=18398915957; ln_hurl=http://head.xiaonei.com/photos/0/0/men_main.gif; t=d939d694f6359a2d8bf5ed0f056569e24; societyguester=d939d694f6359a2d8bf5ed0f056569e24; id=469175544; xnsid=2630ca7c; ver=7.0; loginfrom=null; jebe_key=25bfd9a1-c482-4cb9-a0a2-dee18f5d7f00%7Ca4a12ab29ed67d86d0e62a032248ff26%7C1588497169902%7C1%7C1588497169522; jebe_key=25bfd9a1-c482-4cb9-a0a2-dee18f5d7f00%7Ca4a12ab29ed67d86d0e62a032248ff26%7C1588497169902%7C1%7C1588497169526; XNESSESSIONID=d39262cd4fdb; wp_fold=0; wp=0"
13         cookies = {i.split(‘=‘)[0]: i.split(‘=‘)[1] for i in cookies.split(‘;‘)}
14         yield scrapy.Request(
15         self.start_urls[0],
16         callback = self.parse,
17         cookies = cookies
18         )
19 
20     def parse(self, response):
21         print(re.findall(‘落雨‘, response.body.decode()))
22         yield scrapy.Request(
23             ‘http://www.renren.com/469175544/profile?v=info_timeline‘,
24             callback = self.parse_detail
25         )
26 
27     def parse_detail(self,response):
28         print(re.findall(‘落雨‘, response.body.decode()))