Scrapy学习-9-FromRequest

用FromRequest模拟登陆知乎网站

实例

　　默认登陆成功以后的请求都会带上cookie

# -*- coding: utf-8 -*-
import re
import json
import datetime

try:
    import urlparse as parse
except:
    from urllib import parse

import scrapy

class ZhihuSpider(scrapy.Spider):
    
    name = "zhihu"
    allowed_domains = ["www.zhihu.com"]
    start_urls = ['https://www.zhihu.com/']
    headers = {
        "HOST": "www.zhihu.com",
        "Referer": "https://www.zhizhu.com",
        'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0"
    }

    def parse(self, response):
        pass

    def start_requests(self):
        return [scrapy.Request('https://www.zhihu.com/#signin', headers=self.headers, callback=self.login)]

    def login(self, response):
        response_text = response.text
        match_obj = re.match('.*name="_xsrf" value="(.*?)"', response_text, re.DOTALL)
        xsrf = ''
        if match_obj:
            xsrf = (match_obj.group(1))

        if xsrf:
            post_url = "https://www.zhihu.com/login/phone_num"
            post_data = {
                "_xsrf": xsrf,
                "phone_num": "18782902568",
                "password": "admin123"
            }

            return [scrapy.FormRequest(
                url = post_url,
                formdata = post_data,
                headers=self.headers,
                callback=self.check_login
            )]

    def check_login(self, response):
        #验证服务器的返回数据判断是否成功
        text_json = json.loads(response.text)
        if "msg" in text_json and text_json["msg"] == "登录成功":
            for url in self.start_urls:
                yield scrapy.Request(url, dont_filter=True, headers=self.headers)