import scrapy
import re
 
class Login1Spider(scrapy.Spider):
  name = 'login1'
  allowed_domains = ['github.com']
  start_urls = ['https://github.com/NoobPythoner'] # 这是一个需要登陆以后才能访问的页面
 
  def start_requests(self): # 重构start_requests方法
    # 这个cookies_str是抓包获取的
    cookies_str = '...' # 抓包获取
    # 将cookies_str转换为cookies_dict
    cookies_dict = {i.split('=')[0]:i.split('=')[1] for i in cookies_str.split('; ')}
    yield scrapy.Request(
      self.start_urls[0],
      callback=self.parse,
      cookies=cookies_dict
    )
 
  def parse(self, response): # 通过正则表达式匹配用户名来验证是否登陆成功
    result_list = re.findall(r'noobpythoner|NoobPythoner', response.body.decode())
    print(result_list)
    pass

 yield scrapy.FormRequest(
       "https://github.com/session",
       formdata={
         "authenticity_token":authenticity_token,
         "utf8":utf8,
         "commit":commit,
         "login":"****",
         "password":"****"
       },
       callback=self.parse_login
     )

import scrapy
import re
 
class Login3Spider(scrapy.Spider):
  name = 'login3'
  allowed_domains = ['github.com']
  start_urls = ['https://github.com/login']
 
  def parse(self, response):
    yield scrapy.FormRequest.from_response(
      response, # 传入response对象,自动解析
      # 可以通过xpath来定位form表单,当前页只有一个form表单时,将会自动定位
      formxpath='//*[@id="login"]/form', 
      formdata={'login': '****', 'password': '***'},
      callback=self.parse_login
    )
 
  def parse_login(self,response):
    ret = re.findall(r"noobpythoner|NoobPythoner", response.text)
    print(ret)