自动登录并点赞

用到的知识点

1、cookie

 　　a. from scrapy.http.cookies import CookieJar #用这个包获取第一次访问时的cookie

　　 b、cookie_odj = CookieJar() #实例化对象

　　　　cookie_odj.extract_cookies(response,response.request)

　　　　cookie_dict = cookie_odj._cookies #获取cookie  
2、Request 传参
　　

yield scrapy.Request(
    url="https://dig.chouti.com/login", #地址
    method="POST",　　　　　　　　　　　　　　#请求方式
    body="phone=8619923803579&password=140709ben&oneMonth=1", #请求体
    headers={"Content-Type":"application/x-www-form-urlencoded; charset=UTF-8"},#请求头
    cookies=cookies_dict,　　#cookie
    callback=self.check_log, #回调函数
)

示例：

# -*- coding: utf-8 -*-
import scrapy
from scrapy.http.cookies import CookieJar  # 用这个包获取第一次访问时的cookie


class CtiSpider(scrapy.Spider):
    name = 'cti'
    allowed_domains = ['dig.chouti.com']
    start_urls = ['http://dig.chouti.com/']
    cookies_dict = None  # 保存好的cookie方便其它方法调用

    def parse(self, response):
        cookie_odj = CookieJar()  # 实例化对象
        cookie_odj.extract_cookies(response, response.request)
        self.cookies_dict = cookie_odj._cookies

        yield scrapy.Request(
            url="https://dig.chouti.com/login",
            method="POST",
            body="phone=8619923803579&password=0709ben&oneMonth=1",
            headers={"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8"},
            cookies=self.cookies_dict,
            callback=self.check_log,
        )

    def check_log(self, response):

        yield scrapy.Request(url="https://dig.chouti.com/", callback=self.good)

    def good(self, response):
        url_list = response.xpath("//div[@share-linkid]/@share-linkid").extract()
        for i in url_list:
            good_url = "https://dig.chouti.com/link/vote?linksId=%s" % i

            yield scrapy.Request(
                url=good_url,
                method="POST",
                cookies=self.cookies_dict,
                callback=self.check_good
            )

        pages_list = response.xpath("//div[@id='page-area']//a/@href").extract()
        for a in pages_list:
            page_url = "https://dig.chouti.com%s" % a

            yield scrapy.Request(url=page_url, callback=self.good)

    def check_good(self, response):
        print(response.text)