您好,登錄后才能下訂單哦!
小編給大家分享一下Python如何爬取qq空間說(shuō)說(shuō),相信大部分人都還不怎么了解,因此分享這篇文章給大家參考一下,希望大家閱讀完這篇文章后大有收獲,下面讓我們一起去了解一下吧!
具體代碼如下所示:
#coding:utf-8 #!/usr/bin/python3 from selenium import webdriver import time import re import importlib2 import sys importlib2.reload(sys) def startSpider(): driver = webdriver.Chrome('/Users/zachary/zachary/chromedriver.exe') #這個(gè)是chormedriver的地址 driver.get('https://qzone.qq.com/') driver.switch_to.frame('login_frame') driver.find_element_by_id('switcher_plogin').click() driver.find_element_by_id('u').clear() driver.find_element_by_id('u').send_keys('QQ號(hào)') #這里填寫(xiě)你的QQ號(hào) driver.find_element_by_id('p').clear() driver.find_element_by_id('p').send_keys('QQ密碼') #這里填寫(xiě)你的QQ密碼 driver.find_element_by_id('login_button').click() time.sleep(2) #設(shè)置爬取內(nèi)容保存路徑 f = open('/Users/zachary/Documents/shuoshuo.txt','w') #---------------獲得g_qzonetoken 和 gtk html = driver.page_source '''g_qzonetoken=re.search('window\.g_qzonetoken = \(function\(\)\{ try\{return (.*?);\} catch\(e\)',html)#從網(wǎng)頁(yè)源碼中提取g_qzonetoken''' g_qzonetoken = "e794139a284d6ea9e0b26826e541b55df37d0667a3544f534de25aebdb64628d3ab75e1d7104bbb22a" cookie = {}#初始化cookie字典 for elem in driver.get_cookies():#取cookies cookie[elem['name']] = elem['value'] gtk=getGTK(cookie)#通過(guò)getGTK函數(shù)計(jì)算gtk #print(g_qzonetoken) #print(gtk) #--------------獲得好友列表 注意下面的鏈接 driver.get('https://user.qzone.qq.com/proxy/domain/r.qzone.qq.com/cgi-bin/tfriend/friend_hat_get.cgi?hat_seed=1&uin=你的QQ號(hào)fupdate=1&g_tk='+str(gtk)+'&qzonetoken='+str(g_qzonetoken)+'&g_tk='+str(gtk)) friend_list = driver.page_source friend_list = str( friend_list ) abtract_pattern = re.compile('\"(.\d*)\":\{\\n"realname":"(.*?)"}',re.S) QQ_name_list = re.findall(abtract_pattern,str(friend_list)) #數(shù)組 print(QQ_name_list) numList=dict()# numList => (QQnum:QQname) #列表 for i in QQ_name_list: numList[str(i[0])]=str(i[1]) begin = 0 last_source = "" tag = 1 first = 0 firstTime="" #如果要爬取自己的說(shuō)說(shuō),手動(dòng)添加自己的qq號(hào) #numList['你的qq號(hào)']='你的名字' #print(numList) for key in numList.keys(): QQnum = key QQname = numList[QQnum] if QQnum == "好友qq號(hào)": #根據(jù)qq號(hào)查找指定好友說(shuō)說(shuō) count = 1 begin = 0 while tag==1 : #-------------進(jìn)入好友說(shuō)說(shuō)頁(yè)面 #'+QQnum+' '+str(begin)+' #print("Begin:"+str(begin)) driver.get('https://user.qzone.qq.com/proxy/domain/taotao.qq.com/cgi-bin/emotion_cgi_msglist_v6?uin='+QQnum+'&ftype=0&sort=0&pos='+str(begin)+'&num=40&replynum=200&g_tk='+str(gtk)+'&callback=_preloadCallback&code_version=1&format=jsonp&need_private_comment=1&qzonetoken='+str(g_qzonetoken)+'&g_tk='+str(gtk)) try: msg_list_json = driver.page_source except: begin = begin + 40 continue msg_list_json = str(msg_list_json) if last_source==msg_list_json : break else: last_source=msg_list_json #檢測(cè)是否沒(méi)有權(quán)限訪問(wèn) abtract_pattern = re.compile(',"message":"(.*?)","name":',re.S) message = re.findall(abtract_pattern,str(msg_list_json)) if message!=[]: if str(message[0])=='對(duì)不起,主人設(shè)置了保密,您沒(méi)有權(quán)限查看':#對(duì)不起,主人設(shè)置了保密,您沒(méi)有權(quán)限查看 break #print(msg_list_json) #解析JSON #webDriver沒(méi)有現(xiàn)成的JSON解析器,所以采用獲取源碼的方式,然后使用正則表達(dá)式獲取具體細(xì)節(jié) msg_list_json = msg_list_json.split("msglist")[1]#拆分json,縮小范圍,也能加快解析速度 msg_list_json = msg_list_json.split("smoothpolicy")[0] msg_list_json = msg_list_json.split("commentlist")[1:] #說(shuō)說(shuō)動(dòng)態(tài)分4種:1、文字說(shuō)說(shuō)(或帶有配圖的文字說(shuō)說(shuō)) # 2、只有圖片的說(shuō)說(shuō) # 3、轉(zhuǎn)發(fā),并配有文字 # 4、轉(zhuǎn)發(fā),不配文字 for text in msg_list_json: # 1、先檢查說(shuō)說(shuō),用戶是否發(fā)送了文字,如果沒(méi)有文字,正則表達(dá)式匹配無(wú)效 abtract_pattern = re.compile('\}\],"content":"(.*?)","createTime":"(.*?)","created_time":(.*?),"',re.S) msg_time = re.findall(abtract_pattern,str(text)) if msg_time!=[]: # 2、如果作者說(shuō)說(shuō)有文字,那么檢查是否有轉(zhuǎn)發(fā)內(nèi)容 msg = str(msg_time[0][0]) sendTime = str(msg_time[0][1]) abtract_pattern = re.compile('\}\],"content":"(.*?)"},"rt_createTime":"(.*?)","',re.S) text = text.split("created_time")[1] msg_time2 = re.findall(abtract_pattern,str(text)) #合并發(fā)送內(nèi)容 格式:評(píng)論+轉(zhuǎn)發(fā)內(nèi)容 if msg_time2!=[]: msg = msg +" 轉(zhuǎn)發(fā)內(nèi)容:"+str(msg_time2[0][0]) else: # 3、說(shuō)說(shuō)內(nèi)容為空,檢查是否為 =>只有圖片的說(shuō)說(shuō) or 轉(zhuǎn)發(fā),不配文字 #獲取正文發(fā)送時(shí)間 (發(fā)送時(shí)間分為:正文發(fā)送時(shí)間 or 轉(zhuǎn)發(fā)時(shí)間) abtract_pattern = re.compile('"conlist":null,"content":"","createTime":"(.*?)",',re.S) msgNull_time = re.findall(abtract_pattern,str(text)) if msgNull_time!=[]: #如果有正文發(fā)送時(shí)間,那么就是這條說(shuō)說(shuō)僅含有圖片 =>只有圖片的說(shuō)說(shuō) msg = "圖片" sendTime = str(msgNull_time[0]) else: #如果沒(méi)有正文發(fā)送時(shí)間,那么就是說(shuō)這條說(shuō)為 =>轉(zhuǎn)發(fā),不配文字 abtract_pattern = re.compile('\}\],"content":"(.*?)"},"rt_createTime":"(.*?)","',re.S) msg_time = re.findall(abtract_pattern,str(text)) msg =" 轉(zhuǎn)發(fā)內(nèi)容:"+str(msg_time[0][0]) sendTime = str(msg_time[0][1]) #寫(xiě)入本地文件 #f.write('{},{},{},{}\n'.format(str(QQname),str(QQnum),sendTime,msg)) print(str(count)+" : "+str(QQname)+" : "+str(QQnum)+" : "+sendTime+" : "+msg) count = count + 1 begin = begin + 40 def getGTK(cookie): hashes = 5381 for letter in cookie['p_skey']: hashes += (hashes << 5) + ord(letter) return hashes & 0x7fffffff startSpider() print("爬取結(jié)束")
以上是“Python如何爬取qq空間說(shuō)說(shuō)”這篇文章的所有內(nèi)容,感謝各位的閱讀!相信大家都有了一定的了解,希望分享的內(nèi)容對(duì)大家有所幫助,如果還想學(xué)習(xí)更多知識(shí),歡迎關(guān)注億速云行業(yè)資訊頻道!
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如果涉及侵權(quán)請(qǐng)聯(lián)系站長(zhǎng)郵箱:is@yisu.com進(jìn)行舉報(bào),并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。