2. 程式人生 > 其它 >爬取qq群資訊

爬取qq群資訊

阿新 • • 發佈：2021-01-26

技術標籤：python

獲取cookie和bkn引數

from selenium import webdriver
from selenium.webdriver import ChromeOptions
import time
import pyautogui
import redis

url='https://qun.qq.com/member.html#gid=453987149'

# 需要在這裡邊獲取Cookie，bkn，和所有群號碼，把所有群號碼存起來，然後在爬蟲裡邊一個一個取群號碼，Cookie和bkn的值就直接傳
# headers={
# "cookie": "SINAGLOBAL=6855701965715.122.1577692539947; __gads=ID=c5153c4711c3fa8d:T=1577692757:S=ALNI_MZn5p9pdEiyOo6N9NhaO3oLE1lKsg; _ga=GA1.2.789113268.1577692750; login_sid_t=62e1525776c0bc911756365be2f04f7c; cross_origin_proto=SSL; _s_tentry=cn.bing.com; Apache=8344750195808.959.1603933930414; ULV=1603933930438:89:2:2:8344750195808.959.1603933930414:1603763999621; wb_view_log=1920*10801; wb_view_log_3607491825=1920*10801; UOR=,,login.sina.com.cn; WBtopGlobal_register_version=2020102910; ALF=1635473639; SSOLoginState=1603937640; SCF=ApfIXjexvlOALW_AwBZGr5lNOOESACnJqp_QJtptKZ35jgGHHFSN2QNy3PWTydCN6YAT53oDzyHeUOE95ONOmSI.; SUB=_2A25ynlU4DeRhGeNN6lQU8ivFyjqIHXVR6sHwrDV8PUNbmtANLVr1kW9NScY2ECGW9SVd_9-19MZvuNdisoBSgzC4; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WhXgPg0.VYZ6lqP_5Dg2LWr5JpX5KzhUgL.Fo-0eKqfeo-4eKq2dJLoIEBLxK-L12BL1heLxK-LB-qLB.zLxKBLBonL12-LxK-LBKnL1-et; SUHB=05i629ijI_wSsQ; wvr=6; wb_view_log_5316525916=1920*10801; webim_unReadCount=%7B%22time%22%3A1603958917009%2C%22dm_pub_total%22%3A0%2C%22chat_group_client%22%3A0%2C%22chat_group_notice%22%3A0%2C%22allcountNum%22%3A0%2C%22msgbox%22%3A0%7D"
 

# }
# browser.add_cookie(headers)

option = ChromeOptions()
option.add_experimental_option('excludeSwitches', ['enable-automation'])
# url=""
# 設定中文
option.add_argument('lang=zh_CN.UTF-8')
# 更換頭部
option.add_argument('user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36"'
 
)
browser = webdriver.Chrome(options=option)
browser.get(url)#開啟瀏覽器預設網址
browser.maximize_window()
time.sleep(5)
# 模擬點選登陸
# browser.switch_to.frame('ptlogin_iframe')#frame切換，進入frame內部才可以進行點選
pyautogui.click(1016, 595)
# time.sleep(5)
# browser.find_element_by_xpath('//*[@id="bottom_qlogin"]').click()#使用xpath找到頭像按鈕元素
 

# print(browser.page_source)
# print(browser.execute_script('return event = event||window.event;x=event.clientX;y=event.clientY'))
# browser.find_element_by_id('img_out_3526748995').click()
time.sleep(2)

# print(browser.page_source)#列印網頁原始碼
# 獲取cookies
# 'Cookie': 'RK=3hYoIM4OUR; ptcz=22062646123ccd493ed12173c7b29ec0dbe8425bb3c65e1fd6f12f2d1709caea;
# pgv_pvid=4613506960; _qpsvr_localtk=0.6521903418751458; uin=o1784329053; [email protected]; p_uin=o1784329053;
# pt4_token=DLWBd9LdPUwpXTsYe-tg7eAM1dVCX9-HKjjvo6YdlHI_; p_skey=kd1ZrcOjDHPyY-9g6fSvQ8Mui8gnJdGt9J9PZIpkeLA_;
# traceid=1e9a5faf2a'

# print(browser.get_cookies())
cookie = browser.get_cookies()
for lq in cookie:
  # print(lq)
  if lq["name"] == 'RK':
    # print(lq["value"])
    RK = lq["value"]
  elif lq["name"] == 'ptcz':
    # print(lq["value"])
    ptcz = lq["value"]
  elif lq["name"] == 'pgv_pvid':
    # print(lq["value"])
    pgv_pvid = lq["value"]
  elif lq["name"] == '_qpsvr_localtk':
    # print(lq["value"])
    _qpsvr_localtk = lq["value"]
  elif lq["name"] == 'uin':
    # print(lq["value"])
    uin = lq["value"]
  elif lq["name"] == 'skey':
    # print(lq["value"])
    skey = lq["value"]
  elif lq["name"] == 'p_uin':
    # print(lq["value"])
    p_uin = lq["value"]
  elif lq["name"] == 'pt4_token':
    # print(lq["value"])
    pt4_token = lq["value"]
  elif lq["name"] == 'p_skey':
    # print(lq["value"])
    p_skey = lq["value"]
  elif lq["name"] == 'traceid':
    # print(lq["value"])
    traceid = lq["value"]
# 拼接Cookies
cookies = 'RK='+RK+'; '+'ptcz='+ptcz+'; '+'_qpsvr_localtk='+_qpsvr_localtk+'; '+'uin='+uin+'; '+'skey='+skey+'; '+'p_uin='+p_uin+'; '+'pt4_token='+pt4_token+'; '+'p_skey='+p_skey+'; '+'traceid='+traceid+'; '
print(cookies)
# RK=31gEwhzu1Q;ptcz=b2456e2b484e6ec14abbfda2e37ed7dcdcd49215e0df8ef0ac601d2c8c589f3f;_qpsvr_localtk=0.5913548757973062;uin=o3526748995;[email protected];p_uin=o3526748995;pt4_token=K1YlECESkc03EeCGCBxhkpIFOYtZPWNCNFHeT4D*mrU_;p_skey=YkbDrjjcbxSMPo8pdKPDDfR*kpJ8ZINkwcnt9*ALBM4_;traceid=f00fb9b92c;
# _qpsvr_localtk=0.5913548757973062; uin=o3526748995; [email protected]; RK=31gEwhzu1Q; ptcz=b2456e2b484e6ec14abbfda2e37ed7dcdcd49215e0df8ef0ac601d2c8c589f3f; p_uin=o3526748995; pt4_token=K1YlECESkc03EeCGCBxhkpIFOYtZPWNCNFHeT4D*mrU_; p_skey=YkbDrjjcbxSMPo8pdKPDDfR*kpJ8ZINkwcnt9*ALBM4_; traceid=f00fb9b92c
# RK=31gEwhzu1Q; ptcz=75cea5abd61decb2916239bf7951fe4e43076a6a34a57b3fed25ec40ce416a61; _qpsvr_localtk=0.1803814196177329; uin=o3526748995; [email protected]; p_uin=o3526748995; pt4_token=TRmwjYWuulBbk-5rTyHf7zmYLxEmCsYGoSt4AKWOnPU_; p_skey=SBnVUwqCr2yaVQkdgLb*4Lk28g0ZJgBnsKIUoS0QlX0_; traceid=23a67f1f50;


# 執行js語句，然後獲取bkn的返回值
# 獲取bkn引數
bkn = browser.execute_script('return $.getCSRFToken()')
print(browser.execute_script('return $.getCSRFToken()'))

寫提取群號和爬蟲邏輯

import requests
import json
import time
from qq.getBkn import bkn,cookies
import xlwt
import random

def getqun():
    global user_agent
    user_agent = [
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
        "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
        "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36"]

    headers = {
        'User-Agent':user_agent[random.randint(0, len(user_agent)-1)],
        'Cookie': str(cookies)

    }

    global  qunid
    qunid = []
    global qunname
    qunname = []
    url = 'https://qun.qq.com/cgi-bin/qun_mgr/get_group_list'
    json_data = {
        'bkn': str(bkn)
    }

    res = requests.post(url, headers=headers, data=json_data)
    html_str = res.text
    print(html_str)
    a = json.loads(html_str)
    print(a)
    for quid in a["join"]:
        # print(quid)
        qunid.append(quid['gc'])
        # print(quid['gc'])
        qunname.append(quid['gn'])
        # print(quid['gn'])
    print(qunid)
    print(qunname)


if __name__ == '__main__':

    getqun()
    # print(qunid)
    # print(qunname)
    # print(len(qunid))
    # print(len(qunname))
    # print(qunid[0])
    # print(qunname[2])
    length = len(qunid)
    for q in range(0,length):
        time.sleep(5)
        print(qunname[q])
        book = xlwt.Workbook(encoding='utf-8', style_compression=0)
        sheet = book.add_sheet('群成員資訊', cell_overwrite_ok=True)
        col = ('賬號', '加入時間', '最後發言時間', '群暱稱', 'qq暱稱','q齡')
        for inser in range(0, 6):
            sheet.write(0, inser, col[inser])
        # flag =1
        i=0
        j=20
        headers = {
            'User-Agent':user_agent[random.randint(0, len(user_agent)-1)],
            'Cookie':str(cookies)
        }

        url = 'https://qun.qq.com/cgi-bin/qun_mgr/search_group_members'
        # 先請求一次，獲取並計算相關引數，獲取第一頁的資料
        json_data = {
            'gc':str(qunid[q]),
            'st':str(i),
            'end':str(j),
            'sort':'0',
            'bkn':str(bkn)
        }
        i = i+21
        j= j+21
        res = requests.post(url, headers=headers,data = json_data)
        html_str = res.text
        # print(html_str)
        a = json.loads(html_str)#json轉為字典
        # 提取群裡面的總人數
        person = a["count"]
        # person = person+11
        # 計算出頁碼和最後一頁的個數
        c=int(person/21) #除最後一頁之外的頁數
        if person>21 and person<42:
            c=int(person/21)+1
        # print(c)
        d=person%21      #最後一頁的人數
        print(c,d)
        down = 1
        for lala in a["mems"]:

            joinTime = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(lala['join_time']))
            last_speak_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(lala['last_speak_time']))
            # sheet.write(lala['uin'],joinTime,last_speak_time,lala['card'],lala['nick'])
            data = [lala['uin'],joinTime,last_speak_time,lala['card'],lala['nick'],lala['qage']]
            for inser in range(0,6):
                sheet.write(down, inser, data[inser])
            down += 1
            print("賬號：",str(lala['uin']),"加入時間：",joinTime,"最後發言時間：",last_speak_time,"群暱稱",lala['card'],"qq暱稱：",lala['nick'],lala['qage'])

        # 得到相關引數後加入迴圈，進行迴圈請求，獲取中間頁碼資料
        if c>=2:
            code = 1
            for flag in range(1,c):
                # code = 1
                code+=1
                json_data = {
                    'gc':str(qunid[q]),
                    'st': str(i),
                    'end': str(j),
                    'sort': '0',
                    'bkn': str(bkn)
                }
                i = i + 21
                j = j + 21
                # if code==c-1:
                #     i = i + 21
                #     j = j + d
                res = requests.post(url, headers=headers, data=json_data)
                html_str = res.text
                # print(html_str)
                a = json.loads(html_str)  # json轉為字典
                # print(a)
                # 提取群裡面的總人數
                # person = a["count"]
                # # 計算出頁碼和最後一頁的個數
                # c = int(person / 21)  # 除最後一頁之外的頁數
                # d = person % 21  # 最後一頁的人數
                for lala in a["mems"]:
                    joinTime = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(lala['join_time']))
                    last_speak_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(lala['last_speak_time']))
                    # sheet.write(lala['uin'], joinTime, last_speak_time, lala['card'], lala['nick'])
                    data = [lala['uin'], joinTime, last_speak_time, lala['card'], lala['nick'], lala['qage']]
                    for inser in range(0, 6):
                        sheet.write(down, inser, data[inser])
                    down += 1
                    print("賬號：", str(lala['uin']), "加入時間：", joinTime, "最後發言時間：", last_speak_time, "群暱稱", lala['card'],
                          "qq暱稱：", lala['nick'], lala['qage'])



            # 獲取最後一頁的資料
            if c !=2:
                if d!=0:#保證這個最後一頁是存在的
                    j=j-20+d
                    # print(i,j)
                    json_data = {
                        'gc':str(qunid[q]),
                        'st': str(i),
                        'end': str(j),
                        'sort': '0',
                        'bkn': str(bkn)
                    }
                    res = requests.post(url, headers=headers, data=json_data)
                    html_str = res.text
                    a = json.loads(html_str)  # json轉為字典
                    for lala in a["mems"]:
                        joinTime = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(lala['join_time']))
                        last_speak_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(lala['last_speak_time']))
                        # sheet.write(lala['uin'], joinTime, last_speak_time, lala['card'], lala['nick'])
                        data = [lala['uin'], joinTime, last_speak_time, lala['card'], lala['nick'], lala['qage']]
                        for inser in range(0, 6):
                            sheet.write(down, inser, data[inser])
                        down += 1
                        print("賬號：", str(lala['uin']), "加入時間：", joinTime, "最後發言時間：", last_speak_time, "群暱稱", lala['card'],
                              "qq暱稱：", lala['nick'], lala['qage'])

        # 儲存excel檔案,以群名稱儲存
        savepath = 'C:/Users/Administrator/Desktop/shuju/'+str(qunname[q])+'.xls'
        book.save(savepath)

        print(a["mems"])
        print(html_str)
        print(c,d)
    # ss=12
    # c=ss/2
    # print(c)
    # print(type(person))
    # print(html_str)

最後參考下面的部落格把py檔案合併成exe
pyinstaller打包py檔案壓縮成exe

最後要記得將瀏覽器驅動放在exe所在的目錄下

相關推薦

爬取qq群資訊

技術標籤：python 獲取cookie和bkn引數 from selenium import webdriver from selenium.webdriver import ChromeOptions

爬取QQ音樂排行榜的相關音樂資訊

這次是爬取音樂的相關內容之後寫進資料庫： 具體的實驗程式碼如下： import requests

Python爬取豆瓣視訊資訊程式碼例項

這篇文章主要介紹了Python爬取豆瓣視訊資訊程式碼例項,文中通過示例程式碼介紹的非常詳細，對大家的學習或者工作具有一定的參考學習價值,需要的朋友可以參考下

Python實現的爬取豆瓣電影資訊功能案例

本文例項講述了Python實現的爬取豆瓣電影資訊功能。分享給大家供大家參考，具體如下：

Python爬蟲實現的根據分類爬取豆瓣電影資訊功能示例

本文例項講述了Python爬蟲實現的根據分類爬取豆瓣電影資訊功能。分享給大家供大家參考，具體如下：

python爬取本站電子書資訊併入庫的實現程式碼

入門級爬蟲：只抓取書籍名稱，資訊及下載地址並存儲到資料庫 資料庫工具類：DBUtil.py

Python如何使用正則表示式爬取京東商品資訊

京東（JD.com）是中國最大的自營式電商企業，2015年第一季度在中國自營式B2C電商市場的佔有率為56.3%。如此龐大的一個電商網站，上面的商品資訊是海量的，小編今天就帶小夥伴利用正則表示式，並且基於輸入的關鍵詞來

Python基於BeautifulSoup爬取京東商品資訊

今天小編利用美麗的湯來為大家演示一下如何實現京東商品資訊的精準匹配~~

Python如何爬取qq音樂歌詞到本地

前言 本文的文字及圖片來源於網路,僅供學習、交流使用,不具有任何商業用途,版權歸原作者所有,如有問題請及時聯絡我們以作處理。

Python爬取招聘網資訊

1、資料來源：職友集 2、程式碼 import requests import openpyxl import time from bs4 import BeautifulSoup #用於解析和提取網頁資料的

Python爬取12306車次資訊

1、資料來源：12306官網 2、程式碼 import requests import re def send_request(): headers = headers = {

Python爬取QQ音樂榜單資料

1、爬取QQ音樂榜單資料並存入資料庫（MySQL） 2、程式碼 import requests import json from bs4 import BeautifulSoup

Python爬取12306車次資訊程式碼詳解

詳情檢視下面的程式碼： 如果被識別就要新增一個cookie如果沒有被識別的話就要一個user—agent就好了。如果出現亂碼就設定編碼格式為utf-8

用 Python 爬取 QQ 空間說說和相簿

QQ 空間在 2005 年被騰訊開發，已經經歷了 15 個年頭，在還沒有微信的年代，看網友發表的心情、心事、照片大多都在 QQ 空間的裡。它承載了80、90 後的大量青春，下面我們一起用 selenium 模組匯出說說和相簿回憶青春

凌海爬取豆瓣電影資訊

昨天寫了一個小爬蟲，爬取了豆瓣上2017年中國大陸的電影資訊，網址為豆瓣選影視，爬取了電影的名稱、導演、編劇、主演、型別、上映時間、片長、評分和連結，並儲存到MongoDB中。

51job多執行緒爬取指定職業資訊資料

51job多執行緒爬取指定職業資訊資料 # datetime:2020/10/7 14:02 # 51job多執行緒 import requests

例項一>>爬取airbnb房屋資訊

from selenium import webdriver # 下載的geckodriver的儲存位置 driver = webdriver.Chrome(executable_path=\'D:\\\\chromedriver.exe\')

記一次python 爬蟲爬取深圳租房資訊的過程及遇到的問題

為了分析深圳市所有長租、短租公寓的資訊，爬取了某租房公寓網站上深圳區域所有在租公寓資訊，以下記錄了爬取過程以及爬取過程中遇到的問題：

通過python爬蟲爬取淘寶資訊

爬取內容 爬取淘寶上的褲子資訊，包括褲子名字，圖片，價格以及銷售量 爬取過程

python爬取貓眼電影資訊，取前100名看看哪些電影名列前茅

本文的文字及圖片來源於網路,僅供學習、交流使用,不具有任何商業用途,版權歸原作者所有,如有問題請及時聯絡我們以作處理