一、策略一：直接POST資料

# -*- 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傳送POST請求的方法
        yield scrapy.FormRequest(
                url = url,
                formdata = {"email"
 
 : "[email protected]", "password" : "xxx"},
                callback = self.parse_page)

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

二、策略二：正規的模擬登陸步驟

# -*- 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裡的登入url的響應內容，提取登陸需要的引數（如果需要的話)
    def parse(self, response):
        # 提取登陸需要的引數
        #_xsrf = response.xpath("//_xsrf").extract()[0]
 

        # 傳送請求引數，並呼叫指定回撥函式處理
        yield scrapy.FormRequest.from_response(
                response,
                formdata = {"email" : "[email protected]", "password" : "xxx"}, "_xsrf" = _xsrf},
                callback = self.parse_page
            )

    # 獲取登入成功狀態，訪問需要登入後才能訪問的頁面
    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、策略三：使用儲存登陸狀態的Cookie模擬登陸

這種方法模擬登入成功率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，附帶Cookie值，傳送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)

本文歸屬：博行天下 連結：https://www.jianshu.com/p/7b4486ba942f