FormRequest和FormRequest.from_response的区别

 1 class FormrequestSpider(CrawlSpider):
 2         name=‘github‘
 3         allowed_domains=[‘github.com‘]
 4         start_urls=[‘https://github.com/login‘]
 5 
 6         def parse(self, response):
 7             authenticity_token=response.xpath("//input[@name=‘authenticity_token‘]/@value").extract_first()
 8             utf8=response.xpath("//input[@name=‘utf8‘]/@value").extract_first()
 9             commit=response.xpath("//input[@name=‘commit‘]/@value").extract_first()
10             post_data=dict(
11                 login="***********",
12                 password="**********",
13                 authenticity_token=authenticity_token,
14                 utf8=utf8,
15                 commit=commit,
16             )
17             # 表单请求
18             yield scrapy.FormRequest(
19                 "https://github.com/session",
20                 formdata=post_data,
21                 callback=self.after_login
22             )
23 
24         def after_login(self, response):
25             # with open("a.html","w",encoding="utf-8") as f:
26             #     f.write(response.body.decode())
27             print(re.findall("********", response.body.decode()))

 1 class GithubSpider(CrawlSpider):
 2     name=‘github2‘
 3     allowed_domains=[‘github.com‘]
 4     start_urls=[‘https://github.com/login‘]
 5 
 6     def parse(self, response):
 7         yield scrapy.FormRequest.from_response(
 8             response,  # 自动的从response中寻找from表单
 9             # formdata只需要传入字典型登录名和密码，字典的健是input标签中的name属性
10             formdata={"login": "***********", "password": "**********"},
11             callback=self.after_login
12         )
13 
14     def after_login(self, response):
15         print(response.text)