QQ空间爬虫--获取好友信息

QQ空间网页版：https://user.qzone.qq.com/

登陆后，进入设置，有一个权限设置，设置“谁能看我的空间”为好友可见，然后构造爬虫。

（1）获取Cookie

两种方式：

第一种：通过chrome F12慢慢找获取

第二种：selenium模拟登陆获取

from selenium import webdriver
from time import sleep
import json

QQ_num = ''
QQ_s = ''
driver = webdriver.Firefox()
driver.get('https://user.qzone.qq.com/' + QQ_num + '/main')
driver.switch_to.frame('login_frame')
#找到账号密码登陆的地方
driver.find_element_by_id('switcher_plogin').click()
driver.find_element_by_id('u').send_keys(QQ_num)
driver.find_element_by_id('p').send_keys(QQ_s)
driver.find_element_by_id('login_button').click()
#保存本地的cookie
sleep(1)
cookies = driver.get_cookies()
cookie_dic = {}
for cookie in cookies:
    if 'name' in cookie and 'value' in cookie:
        cookie_dic[cookie['name']] = cookie['value']
    with open('cookie_dict.txt', 'w') as f:
        json.dump(cookie_dic, f)

（2）构造链接

这个从知乎上看别人的思路，主要是g_tk的构造

（3）获取所有好友信息（主要是昵称和QQ号）

import urllib
import requests
import csv
import json
import re

class Qzone:

    #算出来gtk
    def get_gtk(self):
        p_skey = cookie['p_skey']
        h = 5381
        for i in p_skey:
            h += (h << 5) + ord(i)
        g_tk = h & 2147483647
        return g_tk

    #得到uin
    def get_uin(self):
        uin = cookie['ptui_loginuin']
        return uin

        # 得到好友qq
    def get_qq(self):
        qq_list = []
        friend_list = self.get_friend()

        csvfile = open('friends.csv', 'w', newline='')
        csv_write = csv.writer(csvfile, dialect='excel')

        for friend in friend_list:
            csv_write.writerow(friend)
            qq_list.append(friend[1])
        csvfile.close()
        return qq_list

        # 找出好友列表
    def get_friend(self):
        url_friend = 'https://user.qzone.qq.com/proxy/domain/r.qzone.qq.com/cgi-bin/tfriend/friend_ship_manager.cgi?'
        g_tk = self.get_gtk()
        uin = self.get_uin()
        data = {
            'uin': uin,
             'do': 1,
            'g_tk': g_tk
        }
        data_encode = urllib.parse.urlencode(data)
        url_friend += data_encode
        res = requests.get(url_friend, headers=header, cookies=cookie)
        friend_json = re.findall('((.*))', res.text, re.S)[0]
        friend_dict = json.loads(friend_json)
        friend_result_list = []
         # 循环将好友的姓名qq号存入字典中
        for friend in friend_dict['data']['items_list']:
            friend_result_list.append([friend['name'], friend['uin']])
        # 得到的好友字典是{name: qqNum}格式的
        return friend_result_list
        
if __name__ == '__main__':
    qzone = Qzone()

    #将关系设置为全局变量以供方便调用
    relationships = []
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:61.0) Gecko/20100101 Firefox/61.0",
        "Accepted-Language": "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
    }
    with open('cookie_dict.txt','r') as f:
        cookie = json.load(f)
    #得到qq列表，
    qq_list = qzone.get_qq()