Python模拟登录的几种方式

Python模拟登录的几种方式

1、使用cookie模拟登陆

# -*- coding: utf-8 -*-
import scrapy
# 实在没办法了，可以用这种方法模拟登录，麻烦一点，成功率100%

class RenrenSpider(scrapy.Spider):
    name = "renren"
    allowed_domains = ["renren.com"]
    start_urls = (
        'http://www.renren.com/xxxxx',
        'http://www.renren.com/11111',
        'http://www.renren.com/xx',
    )

    cookies = {
  		#cookie内容
    }

    def start_requests(self):
        for url in self.start_urls:
        #yield scrapy.Request(url, callback = self.parse)
            #url = "http://www.renren.com/410043129/profile"
            yield scrapy.FormRequest(url, cookies = self.cookies, callback = self.parse_page)

    def parse_page(self, response):
        print "===========" + response.url
        with open("deng.html", "w") as filename:
            filename.write(response.body)

2、只要是需要提供post数据的

# -*- coding: utf-8 -*-
import scrapy

# 只要是需要提供post数据的，就可以用这种方法，
# 下面示例：post数据是账户密码
class Renren1Spider(scrapy.Spider):
    name = "renren1"
    allowed_domains = ["renren.com"]

    def start_requests(self):
        url = 'http://www.renren.com/PLogin.do'
        yield scrapy.FormRequest(
                url = url,
                formdata = {"email" : "xxx", "password" : "xxx"},
                callback = self.parse_page)

    def parse_page(self, response):
        with open("mao2.html", "w") as filename:
            filename.write(response.body)

3、 首先发送登录页面的get请求，获取到页面里的登录必须的参数，比如说zhihu的 _xsrf，然后和账户密码一起post到服务器，登录成功

# -*- coding: utf-8 -*-
import scrapy

# 正统模拟登录方法：
# 首先发送登录页面的get请求，获取到页面里的登录必须的参数，比如说zhihu的 _xsrf
# 然后和账户密码一起post到服务器，登录成功

class Renren2Spider(scrapy.Spider):
    name = "renren2"
    allowed_domains = ["renren.com"]
    start_urls = (
        "http://www.renren.com/PLogin.do",
    )

    def parse(self, response):
        #_xsrf = response.xpath("//_xsrf").extract()[0]
        yield scrapy.FormRequest.from_response(
                response,
                formdata = {"email" : "xxx", "password" : "xxx"},#, "_xsrf" = _xsrf},
                callback = self.parse_page
            )

    def parse_page(self, response):
        print "=========1===" + response.url
        #with open("mao.html", "w") as filename:
        #    filename.write(response.body)
        url = "http://www.renren.com/422167102/profile"
        yield scrapy.Request(url, callback = self.parse_newpage)

    def parse_newpage(self, response):
        print "===========2====" + response.url
        with open("xiao.html", "w") as filename:
            filename.write(response.body)