python爬取加密qq空间_python3.7 爬取QQ空间好友

1 from urllib importparse2 from selenium importwebdriver3 importrequests4 importjson5 from json importloads6 importtime7 importpymssql8 importdatetime9

10 def get_key_values(body,key,end =';'):11 """提取body中不包括的key，分片操作12

13 :param body: 父字符串14 :param key: 子字符串15 :param end: 结束字符串，默认为;16 :return: 不包括子字符串的字符串17 """

18 return body[body.find(key) + len(key): body.find(';', body.find(key))]19

20 defget_key(cookies):21 """获取cookie中的相关键的值22 解密23

24 :param cookies: 缓存25 :return: 相关键的值26 """

27 key = get_key_values(cookies,'p_skey=')28 h = 5381

29 for i inkey:30 h += (h << 5) +ord(i)31 return h & 2147483647

33 defweb_login_cookie():34 """url = 'https://user.qzone.qq.com/QQ号相关的缓存35 实现自动化登录36

37 :return: 浏览器的缓存38 """

39 driver =webdriver.Chrome()40 qq_account = '1612893772'

41 qq_password = '13974162858x'

42 login(driver,qq_account,qq_password)43 time.sleep(10)44 driver.get('https://user.qzone.qq.com/{}'.format(qq_account))45 cookie = ''

46 for elem in driver.get_cookies(): #记录相关的Cookie

47 #elem 为 dict类型

48 cookie += elem["name"] + "=" + elem["value"] + ";"

49 #cookies = cookie

50 returncookie51

52 deflogin(driver,qq_account,qq_password):53 """登录54

55 :param driver: 浏览器对象56 :param qq_account: QQ账号57 :param qq_password: QQ密码58 :return:59 """

60 driver.maximize_window()61 driver.get('http://user.qzone.qq.com')62 driver.switch_to.frame('login_frame')63 time.sleep(1)64 driver.find_element_by_id("switcher_plogin").click()65 driver.find_element_by_id("u").send_keys(qq_account)66 time.sleep(2)67 driver.find_element_by_id("p").send_keys(qq_password)68 time.sleep(2)69 driver.find_element_by_id("login_button").click()70

71 def send_requests(req,headers,url,params=None):72 """url_friend = 'https://user.qzone.qq.com/proxy/domain/r.qzone.qq.com/cgi-bin/tfriend/friend_ship_manager.cgi?'73 url_friend携带以下参数：uin（QQ号）、do（没有它，返回空，默认值为：1）74 rd，g_t，qzonetoken（每次登录都发生变化，从Cookiezz中获取）75 fupdate，clean（默认值为：1）76

77 :param req: 请求（Request）,该请求为会话78 :param headers: 请求头79 :param params: 请求参数80 :return: JSONP数据81 """

82 if None !=params:83 url = url +parse.urlencode(params)84 #url = url+'&offset='+str(0)

85 page = req.get(url=url, headers=headers)86 returnpage.text87

88 defget_each_str(req,uin,headers):89 each_url = 'https://user.qzone.qq.com/{}'.format(uin)90 page = req.get(url=each_url, headers=headers)91

92 def friend_db(dicts,name=''):93 """操作DB94

95 :param dicts: 数据字典信息96 :param name: 备注名97 :return: void98 """

99 if len(str(dicts['birthyear'])) < 4:100 dicts['birthyear'] = '1900'

101 if dicts['birthday'][1:2] == '0':102 dicts['birthday'] = '01-01'

103 if len(dicts['signature']) > 70:104 dicts['signature'] = ''

105 friend_db_dict ={106 'friendInfo': [107 dicts['uin'], name, dicts['age'], '男' if dicts['sex'] == 1 else '女'

108 , datetime.datetime.strptime(str(dicts['birthyear']) + '-' + str(dicts['birthday']), '%Y-%m-%d')],109 'friendPlace': [110 dicts['uin'], dicts['company'],dicts['career'], dicts['hco'] + dicts['hp'] + dicts['hc'],111 dicts['country'] + dicts['province'] + dicts['city'],dicts['cco'] + dicts['cp'] + dicts['cc'], dicts['cb']],112 'friendNet': [113 dicts['uin'], dicts['nickname'], dicts['spacename'], dicts['desc'], dicts['signature']]114 }115 conn = pymssql.connect(host='localhost', user='sa', password='123456', database='friendDB',116 charset='utf8')117 cur =conn.cursor()118 sql = "begin tran insertData insert into friendInfo values({},'{}',{},'{}','{}');"\119 "insert into friendPlace values({},'{}','{}','{}','{}','{}','{}');"\120 "insert into friendNet values({},'{}','{}','{}','{}');"\121 "commit tran insertData".\122 format(friend_db_dict['friendInfo'][0],friend_db_dict['friendInfo'][1],friend_db_dict['friendInfo'][2]123 ,friend_db_dict['friendInfo'][3],friend_db_dict['friendInfo'][4],friend_db_dict['friendPlace'][0],124 friend_db_dict['friendPlace'][1],friend_db_dict['friendPlace'][2],friend_db_dict['friendPlace'][3],125 friend_db_dict['friendPlace'][4],friend_db_dict['friendPlace'][5],friend_db_dict['friendPlace'][6],126 friend_db_dict['friendNet'][0],friend_db_dict['friendNet'][1],friend_db_dict['friendNet'][2],127 friend_db_dict['friendNet'][3],friend_db_dict['friendNet'][4])128 print('sql:',sql)129 cur.execute(sql)130 conn.commit()131 cur.close()132 conn.close()133

134 defmain():135 """主要操作136

137 :return: void138 """

139 req =requests.session()140 headers={'host': 'h5.qzone.qq.com',141 'accept-encoding':'gzip, deflate, br',142 'accept-language':'zh-CN,zh;q=0.8',143 'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',144 'user-agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/'

145 '59.0.3071.115 Safari/537.36',146 'connection': 'keep-alive'}147 cookie =web_login_cookie()148 print('cookie',cookie)149 g_tk =get_key(cookie)150 qzonetoken_friend = get_key_values(cookie,'ptcz=')151 uin_friend = get_key_values(cookie,'ptui_loginuin=')152 rd_friend = get_key_values(cookie,'_qpsvr_localtk=')153 print('friend_data','qzontoken:%s;uin:%s;rd:%s' %(qzonetoken_friend,uin_friend,rd_friend))154 headers['Cookie']=cookie155 params_friend = {"uin": uin_friend,"fupdate": 1,"action": 1,"do":1,"g_tk":g_tk,"rd":rd_friend,156 'qzonetoken':qzonetoken_friend}157 url_friend = 'https://user.qzone.qq.com/proxy/domain/r.qzone.qq.com/cgi-bin/tfriend/friend_ship_manager.cgi?'

158 data_friend_str = send_requests(req,headers,url_friend,params=params_friend)159 data_friend_dict = loads(data_friend_str[0+len('_Callback('):data_friend_str.find(');')])160 print('data_friend_dict:',data_friend_dict)161 if data_friend_dict['code'] != 0: #code = -3000 message = '请先登录'

162 time.sleep(10)163 main()164 else:165 data_friend_list = list(data_friend_dict['data']['items_list'])166 for i inrange(len(data_friend_list)):167 each_uin = data_friend_list[i]['uin']168 each_url = 'https://h5.qzone.qq.com/proxy/domain/base.qzone.qq.com/cgi-bin/user/cgi_userinfo_get_all?'

169 params_each = {"uin": each_uin, "fupdate": 1, "vuin": uin_friend, "g_tk": g_tk, "rd": rd_friend,170 'qzonetoken': qzonetoken_friend}171 time.sleep(1)172 data_each_str =send_requests(req,headers,each_url,params_each)173 try:174 data_each_dict = loads(data_each_str[0+len("_Callback("):data_each_str.find(");")])175 exceptjson.decoder.JSONDecodeError as e:176 with open('leak.txt','a',encoding='utf8') as file: #数据持久化，统计错误信息

177 file.write('except:' + str(each_uin) + " " + data_friend_list[i]['name'] + " " + e.msg + "\n")178 continue

179 print('data_each_dict:',data_each_dict)180 if data_each_dict['code'] == 0: #code = -4009 message = '没有访问权限'

181 friend_db(data_each_dict['data'],name=data_friend_list[i]['name'])182 else:183 with open('leak.txt','a',encoding='utf8') as file: #数据持久化，统计错误信息

184 file.write(('没有访问权限:' + str(each_uin) + " " + data_friend_list[i]['name'] + "\n"))185 main()

python爬取加密qq空间_python3.7 爬取QQ空间好友相关推荐

python爬取加密qq空间_python3爬虫爬取QQ好友空间说说
开发环境Win10 python 3.6.3 pycharm 2018.1 第三方库csv requests pymysql selenium 无头浏览器 PhantomJS 主要思路通过QQ邮箱导出 ...
python3抓取b站弹幕_python3写爬取B站视频弹幕功能
需要准备的环境: 一个B站账号,需要先登录,否则不能查看历史弹幕记录联网的电脑和顺手的浏览器,我用的Chrome Python3环境以及request模块,安装使用命令,换源比较快: pip3 in ...
python 12306查询不到车次_Python3.x 抓取12306车次信息,表格详情显示，让你学会思路，分析网站特点，爬取数据。12306车票查看器！...
我的例子都比较适合新手,那种老司机请绕道,谢谢! ps 前言最近学习Python,所以呢?跟大家一样,都是看看官网,看看教程,然后就准备搞一个小东西来试试,那么我使用的例子是实验楼中的12306火车 ...
python爬取音乐并保存_python3 实现爬取TOP500的音乐信息并存储到mongoDB数据库中
爬取TOP500的音乐信息,包括排名情况.歌曲名.歌曲时间. 网页版酷狗不能手动翻页进行下一步的浏览,仔细观察第一页的URL: 这里尝试将1改为2,再进行浏览,恰好是第二页的信息,再改为3,恰好是第三 ...
python爬取付费电影思路_python3爬虫爬取猫眼电影TOP100（含详细爬取思路）
待爬取的网页地址为https://maoyan.com/board/4,本次以requests.BeautifulSoup css selector为路线进行爬取,最终目的是把影片排名.图片.名称.演 ...
python爬取加密qq空间_使用python+selenium爬取qq空间好友动态
使用python+selenium爬取qq空间好友动态分析过程如下: 要想用selenium登陆qq空间,必须点击账号密码登陆按钮然后再填写账号密码登陆. 1.PNG 点击账号密码按钮后跳转到如下页 ...
python爬取qq音乐评论_爬虫：QQ音乐评论
QQ音乐评论有些小伙伴反馈,对于爬虫的完整流程,还是不清楚,这边就按顺序,给大家梳理一下反爬首先查看一下,我们要爬取的网页,是否反爬(各种侵害人家服务器的事情,我们不能干) QQ音乐网址:htt ...
Python网络爬虫数据采集实战：Scrapy框架爬取QQ音乐存入MongoDB
通过前七章的学习,相信大家对整个爬虫有了一个比较全貌的了解 ,其中分别涉及四个案例:静态网页爬取.动态Ajax网页爬取.Selenium浏览器模拟爬取和Fillder今日头条app爬取,基本 ...
python爬取凤凰新闻网_python3.6爬取凤凰网新闻-爬虫框架式思维
一.序言先前几篇爬虫的代码,是简单的脚本代码.在爬取小网页觉得挺简单.高效,但涉及复杂网页的时候,就要考虑成熟的爬虫框架与分布式.本篇博客作为无框架式爬虫和有框架式爬虫的一个过渡,介绍具有框架式思维 ...

python爬取加密qq空间_python3.7 爬取QQ空间好友

python爬取加密qq空间_python3.7 爬取QQ空间好友相关推荐

最新文章

热门文章