Scrapy模拟表单登录

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u014595375/article/details/77018402

Link

import scrapy

class LoginSpider(scrapy.Spider):
    name = 'example.com'
    start_urls = ['http://www.example.com/users/login.php']

    def parse(self, response):
        return scrapy.FormRequest.from_response(
            response,
            formdata={'username': 'john', 'password': 'secret'},
            callback=self.after_login
        )

    def after_login(self, response):
        # check login succeed before going on
        # 在Python3中下面的字符串需要改写为b"authentication failed"
        if "authentication failed" in response.body:
            self.logger.error("Login failed")
            return

        # continue scraping with authenticated session...