模擬登陸時，必須保證settings.py里的 COOKIES_ENABLED (Cookies中間件) 處于開啟狀態(tài)哀托，COOKIES_ENABLED = True 或 # COOKIES_ENABLED = False惦辛，使用Scrapy模擬登陸簡單易懂，可以說能處理大部分的登錄操作仓手。
一胖齐、策略一：直接POST數據
只要是需要提供post數據的，就可以用這種方法

# -*- coding: utf-8 -*-
import scrapy
class Renren1Spider(scrapy.Spider):
    name = "renren"
    allowed_domains = ["renren.com"]

    def start_requests(self):
        url = 'http://www.renren.com/PLogin.do'
        # FormRequest 是Scrapy發(fā)送POST請求的方法
        yield scrapy.FormRequest(
                url = url,
                formdata = {"email" : "xxx@163.com", "password" : "xxx"},
                callback = self.parse_page)

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

二嗽冒、策略二：正規(guī)的模擬登陸步驟

① 首先發(fā)送登錄頁面的get請求呀伙，獲取到頁面里的登錄必須的參數（比如說zhihu登陸界面的 _xsrf）
② 然后和賬戶密碼一起post到服務器，登錄成功

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

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

    # 處理start_urls里的登錄url的響應內容添坊，提取登陸需要的參數（如果需要的話)
    def parse(self, response):
        # 提取登陸需要的參數
        #_xsrf = response.xpath("http://_xsrf").extract()[0]
        # 發(fā)送請求參數剿另，并調用指定回調函數處理
        yield scrapy.FormRequest.from_response(
                response,
                formdata = {"email" : "xxx@163.com", "password" : "xxx"}, "_xsrf" = _xsrf},
                callback = self.parse_page
            )

    # 獲取登錄成功狀態(tài)，訪問需要登錄后才能訪問的頁面
    def parse_page(self, response):
        url = "http://www.renren.com/422167102/profile"
        yield scrapy.Request(url, callback = self.parse_newpage)

    # 處理響應內容
    def parse_newpage(self, response):
        with open("renren.html", "w") as filename:
            filename.write(response.body)

三贬蛙、策略三：使用保存登陸狀態(tài)的Cookie模擬登陸

這種方法模擬登錄成功率100%

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

class RenrenSpider(scrapy.Spider):
    name = "renren"
    allowed_domains = ["renren.com"]
    start_urls = (
        'http://www.renren.com/hahaha',
        'http://www.renren.com/meinv',
        'http://www.renren.com/shuaige',
    )

    cookies = {
    "anonymid" : "ixrna3fysufnwv",
    "_r01_" : "1",
    "ap" : "327550029",
    "JSESSIONID" : "abciwg61A_RvtaRS3GjOv",
    "depovince" : "GW",
    "springskin" : "set",
    "jebe_key" : "f6fb270b-d06d-42e6-8b53-e67c3156aa7e%7Cc13c37f53bca9e1e7132d4b58ce00fa3%7C1484060607478%7C1%7C1486198628950",
    "t" : "691808127750a83d33704a565d8340ae9",
    "societyguester" : "691808127750a83d33704a565d8340ae9",
    "id" : "327550029",
    "xnsid" : "f42b25cf",
    "loginfrom" : "syshome"
    }

    # 可以重寫Spider類的start_requests方法雨女，附帶Cookie值，發(fā)送POST請求
    def start_requests(self):
        for url in self.start_urls:
            yield scrapy.FormRequest(url, cookies = self.cookies, callback = self.parse_page)

    # 處理響應內容
    def parse_page(self, response):
        with open("deng.html", "w") as filename:
            filename.write(response.body)