scrapy实现github登录

效果展示

1.  
   import scrapy
2.  
    
3.  
    
4.  
   class LoginSpider(scrapy.Spider):
5.  
   name = 'login'
6.  
   allowed_domains = ['github.com']
7.  
   start_urls = ['http://github.com/login']#首先访问登录页面
8.  
   P= "15175857475a"
9.  
   def parse(self, response):
10.  
    authenticity_token=response.xpath('//input[@name="authenticity_token"]/@value').extract()[0]
11.  
    timestamp=response.xpath('//input[@name="timestamp"]/@value').extract()[0]
12.  
    timestamp_secret=response.xpath('//input[@name="timestamp_secret"]/@value').extract()[0]
13.  
    required_field=response.xpath('//input[@type="text"]/@name').extract()[1]
14.  
    form_data={
15.  
    "commit": "Sign in",
16.  
    "authenticity_token":authenticity_token ,
17.  
    "login": "用户名",
18.  
    "trusted_device": "",
19.  
    "password": "密码",
20.  
    "webauthn-support": "supported",
21.  
    "webauthn-iuvpaa-support": "unsupported",
22.  
    "return_to": "https://github.com/login",
23.  
    "allow_signup": "",
24.  
    "client_id": "",
25.  
    "integration": "",
26.  
    required_field: "",
27.  
    "timestamp": timestamp,
28.  
    "timestamp_secret":timestamp_secret,
29.  
    }
30.  
    yield scrapy.FormRequest(url="http://github.com/session",callback=self.verify_login,formdata=form_data)
31.  
    def verify_login(self,response):
32.  
    if "Fengxiaobing00" in response.text:
33.  
    print("登录成功")
34.  
    else:
35.  
    print("不成功")
36.  
    #登录github
37.  
    #请求流程 向 https://github.com/session 提交post 用户名密码等数据 获取登录页面
38.  
    #1.访问 https://github.com/login获取https://github.com/session 需要的参数
39.  
     
40.  
    """commit: Sign in 忽略
41.  
    需要购造
42.  
    authenticity_token: qx0N300eRt thwVSihcr93xQOhYLRGsdEEBXf0twTZXS8lCV9e58/neVLLBY0/v1A7zAhASGyIeuJdSR28oBRA==
43.  
    login: 2418917657@qq.com 用户名
44.  
    password: 15175857475a1 密码
45.  
    trusted_device:
46.  
    webauthn-support: supported 忽略
47.  
    webauthn-iuvpaa-support: unsupported 忽略
48.  
    return_to: https://github.com/login
49.  
    allow_signup:
50.  
    client_id:
51.  
    integration:
52.  
    required_field_f9a9: 不太一样，但是没有数据
53.  
    timestamp: 1641002690912 时间戳 需要枸造
54.  
     
55.  
    需要枸造
56.  
    timestamp_secret: b539cdfd359669612d24768a002e4f3ccca2f52ccba8217aefc4eb6485ccf9f5"""
57.  
     
58.  
    """
59.  
    参数获取的方式：
60.  
    1.之前请求的页面中获取
61.  
    2.js代码动态生成
62.  
    """

这篇好文章是转载于：学新通技术网