spider.py文件编写
import scrapy
import re
class LoginGithubSpider(scrapy.Spider):
name = 'login_reren'
allowed_domains = ['gihub.com']
start_urls = ['https://github.com/login']
def parse(self, response):
yield scrapy.FormRequest.from_response(
response,
formdata={"user":"zhao-ji", "password":"******"},
callback=self.after_login_verify
)
def after_login_verify(self, response):
print(re.findall(r"zhao-ji", response.body.decode()))