Scrapy实现模拟登录的示例代码

# -*- coding: utf-8 -*-
import scrapy
import re
 
class TmallLoginSpider(scrapy.Spider):
  name = 'github_login3'
  allowed_domains = ['github.com']
  start_urls = ['https://github.com/']
 
  def start_requests(self): # 请求时携带Cookies
    cookies = '_ga=GA1.2.363045452.1554860671; tz=Asia%2FShanghai; _octo=GH1.1.1405577398.1554860677; _device_id=ee3ff12512668a1f9dc6fb33e388ea20; ignored_unsupported_browser_notice=false; has_recent_activity=1; user_session=5oxrsfsZCor1iJFCgRXXyeAXd8hcmzEUGh70-xHWLjQkT62Q; __Host-user_session_same_site=5oxrsfsZCor1iJFCgRXXyeAXd8hcmzEUGh70-xHWLjQkT62Q; logged_in=yes; dotcom_user=pengjunlee; _gat=1'
    cookies = {i.split('=')[0]: i.split('=')[1] for i in cookies.split('; ')}
    yield scrapy.Request(self.start_urls[0], cookies=cookies)
    
  def parse(self, response): # 验证是否请求成功
    print(re.findall('Learn Git and GitHub without any code!',response.body.decode()))

# -*- coding: utf-8 -*-
import scrapy
import re
 
class GithubLoginSpider(scrapy.Spider):
  name = 'github_login'
  allowed_domains = ['github.com']
  start_urls = ['https://github.com/login']
 
  def parse(self, response): # 发送Post请求获取Cookies
    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()
    form_data = {
      'login': 'pengjunlee@163.com',
      'password': '123456',
      'webauthn-support': 'supported',
      'authenticity_token': authenticity_token,
      'utf8': utf8,
      'commit': commit}
    yield scrapy.FormRequest("https://github.com/session", formdata=form_data, callback=self.after_login)
 
  def after_login(self, response): # 验证是否请求成功
    print(re.findall('Learn Git and GitHub without any code!', response.body.decode()))

# -*- coding: utf-8 -*-
import scrapy
import re
 
class GithubLogin2Spider(scrapy.Spider):
  name = 'github_login2'
  allowed_domains = ['github.com']
  start_urls = ['https://github.com/login']
 
  def parse(self, response): # 发送Post请求获取Cookies
    form_data = {
      'login': 'pengjunlee@163.com',
      'password': '123456'
    }
    yield scrapy.FormRequest.from_response(response,formdata=form_data,callback=self.after_login)
 
  def after_login(self,response): # 验证是否请求成功
    print(re.findall('Learn Git and GitHub without any code!',response.body.decode()))

'''
response (Response object) – 包含表单HTML的响应，将用来对表单的字段进行预填充
formname (string) – 如果设置了该值，name 等于该值的表单将被使用
formid (string) – 如果设置了该值，id 等于该值的表单将被使用
formxpath (string) – 如果设置了该值，匹配该 xpath 的第一个表单将被使用
formcss (string) – 如果设置了该值，匹配该 css选择器的第一个表单将被使用
formnumber (integer) – 索引值等于该值的表单将被使用，默认第一个（索引值为 0 ）
formdata (dict) – 传入的表单数据，将覆盖form 元素中已经存在的值
clickdata (dict) – 用于查找可点击控件的属性值
dont_click (boolean) – 如果设置为 True，将不点击任何元素，直接提交表单数据
'''