DecryptLogin

github

import scrapy
import re

class GithubSpider(scrapy.Spider):
    name = 'github'
    allowed_domains = ['github.com']
    start_urls = ['https://github.com/login']

    def parse(self, response):
        authenticity_token = response.xpath("//input[@name='authenticity_token']/@value").extract_first()
        utf8 = response.xpath("//input[@name='utf8']/@value").extract_first()
        commit = response.xpath("//input[@name='commit']/@value").extract_first()
        # print(authenticity_token)
        # print(utf8)
        # print(commit)
        post_data = dict(
            login="*************",
            password="**********",
            authenticity_token=authenticity_token,
            utf8='✓',
            commit='Sign in',
        )
        yield scrapy.FormRequest(
            url='https://github.com/session',
            formdata=post_data,
            callback=self.after_login
        )
    def after_login(self,response):
        print(re.findall("oookkkssss",response.body.decode()))
        # print(response.body.decode())

 

 

 

 

 

 

 

参考：https://blog.csdn.net/kingx3/article/details/108396493

import scrapy
from ps import k_login,k_password

class GloginSpider(scrapy.Spider):
    name = 'github1'
    allowed_domains = ['github.com']
    start_urls = ['https://github.com/login']
    url = 'https://github.com/session'
    # def start_requests(self):
    def parse(self, response):
        commit = 'Sign in'
        authenticity_token = response.xpath('//input[@name="authenticity_token"]/@value').extract_first()
        # .extract_first是在选择器列表中返回第一个列表值
        # 等同于.extract()[0],也可以是[0].extract()
        # 测试中发现ga_id在登录前为空,尝试不添加这一项
        # ga_id = response.xpath('//meta[@name="octolytics-dimension-ga_id"]/@content').extract()
        login = k_login
        password = k_password
        timestamp = response.xpath('//input[contains(@name,"timestamp")]/@value')[0].extract()
        timestamp_secret = response.xpath('//input[contains(@name,"timestamp")]/@value')[1].extract()
        # print(authenticity_token)
        # print(ga_id)
        # print(timestamp,timestamp_secret)

        # 定义一个字典提交数据
        form_data = {
            'commit': commit,
            'authenticity_token': authenticity_token,
            # 'ga_id': ga_id,
            'login': login,
            'password': password,
            'webauthn-support': 'supported',
            'webauthn-iuvpaa-support': 'unsupported',
            'timestamp': timestamp,
            'timestamp_secret': timestamp_secret,
        }

        # scrapy.Request只支持get请求
        # post请求可以使用.FormRequest,默认为POST
        yield scrapy.FormRequest(
            url=self.url,
            formdata=form_data,
            callback=self.after_login
        )

    def after_login(self,response):

        # print(response.body.decode('utf-8'))
        with open('./github.html','w',encoding='utf-8') as f:

            f.write(response.body.decode('utf-8'))