#!/usr/bin/python# -*- coding: utf-8 -*-#Filenaem: tqjinyan.pyimport os,sys,time,urllib2,reimport cookielibimport multiprocessingimport datetime,time#定義存儲完整的數據字典#keyWord: 具體短鏈接地址,發布時間,標題,平均每天瀏覽量,更新時間,總瀏覽量,鏈接地址userJinYanAll={}#提取用戶總共有多少經驗def tiquNumber(url):    regex = re.compile(r'&pn=(/d{1,10})"')    web=urllib2.urlopen(url).read()    num= regex.findall(web)    if not len(num):        num.append(1)    num=map(int,num)    num.sort()    return num[-1]#拼接每一頁的鏈接，返回鏈接的列表def retJinYanYe(url,num):    # 分頁頁面...'    yesNumLianjie=[]    for i in range(0,num+1,7):        yesNumLianjie.append(url+"&pn="+str(i))    return yesNumLianjie#返回分頁經驗def retNumTitle(jylist):    numjisu=0    for url in jylist:        numjisu+=1        #定義正則,鏈接,發布時間,標題        regex_href = re.compile(r'<p class="tit"><a href="(.{1,200})" title="')        regex_time=re.compile('<span class="exp-time">(.{1,12})</span>')        regex_title=re.compile('" title="(.{1,80})" target="_blank">')        #定義字典關鍵詞        regex_keyword=re.compile('e/(.{1,50}).html')        #獲取web分頁中的數據        web=urllib2.urlopen(url).read()        #獲取鏈接，發布時間，標題        href=regex_href.findall(web)        exp_time=regex_time.findall(web)        title=regex_title.findall(web)        #進行循環添加至列表的字典中        # print url        for i in range(0,len(title)):            #定義一個空列表，用于添加至列表字典中            userlist=[]            keyword = regex_keyword.findall(href[i])            # print keyword            userlist.append(href[i])            userlist.append(exp_time[i])            userlist.append(title[i])            # print keyword            userJinYanAll[keyword[0]]=userlist        # printstdout('/r正在獲取第  %i  頁的經驗信息...' % numjisu)        # print userJinYanAll#根據地址,使用cookie瀏覽具體頁面,返回瀏覽量,更新時間def retLiuLanNum(keyword,url,i):    loginUrl='http://jingyan.baidu.com'+url    #以cookie來訪問具體的網頁    # cj = cookielib.CookieJar()    # opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))    # urllib2.install_opener(opener)    # resp = urllib2.urlopen(loginUrl)    req=urllib2.Request(loginUrl,data="")    f=urllib2.urlopen(req).read()    regex_liulannum = re.compile(r'<span class="views">(/d{1,10})</span>')    regex_updateTime=re.compile(r'<time>(.{1,20})</time>')    viewsNum=regex_liulannum.findall(f)    updateTime=regex_updateTime.findall(f)    #平均流量    if int(viewsNum[0])!=0:        jianGeDay=pingJunNum(keyword,updateTime[0],viewsNum[0])        pjNum=int(viewsNum[0])/int(jianGeDay)/1.00        if pjNum<1:            userJinYanAll[keyword].append('-')        else:            userJinYanAll[keyword].append(str(pjNum))        # print pjNum    else:        userJinYanAll[keyword].append('-')    # print pingJunNum(keyword,updateTime,viewsNum)    # sys.exit()    # print viewsNum,updateTime    userJinYanAll[keyword].append(updateTime[0])    userJinYanAll[keyword].append(viewsNum[0])    userJinYanAll[keyword].append(loginUrl)    # print userJinYanAll    # sys.exit()
    #下面這句.因為格式需要<換成兩行,如需測試.自行優化下格式.
    print str(i)+"/t/t"+userJinYanAll[keyword][1]+"/t"+userJinYanAll[keyword][5]+
　　　　　　"/t"+userJinYanAll[keyword][3]+"/t"+userJinYanAll[keyword][2]+"/t"+userJinYanAll[keyword][6]def getcookie():    loginUrl='http://jingyan.baidu.com/article/ed2a5d1f1938f909f7be174f.html'    cj = cookielib.CookieJar()    opener=urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))    urllib2.install_opener(opener)    resp=urllib2.urlopen(loginUrl)    f = urllib2.urlopen(url= loginUrl)def menu(url):    try:        #獲取用戶姝經驗分頁        # print '提取經驗總數量...'        numYe=tiquNumber(url)        #根據分頁鏈接獲取每頁上面的鏈接        jylist=retJinYanYe(url,numYe)        # print '總共有:%s頁經驗.'%len(jylist)        # print '根據分頁信息獲取具體鏈接..'        # print jylist        retNumTitle(jylist)        # for t in jylist:            #根據鏈接生成字典數據            # retNumTitle(t)        # print '共有:%s篇經驗.'%len(userJinYanAll)        # print '獲取Cookie信息中...'        getcookie()        # print '獲取每篇經驗具體的經驗信息,此時間比較久,請耐心等待...'        # print '----------輸出具體的經驗列表----------'        # print '序列/t發布時間/t總瀏量/t平均每天的瀏覽量/t/t標題/t/t/t具體鏈接'        i=0        for k,v in userJinYanAll.items():            i+=1            retLiuLanNum(k,v[0],i)            # print "%s:%s"%(k,v)        # for k,v in userJinYanAll.items():            # print k,v            # print v[4]+"/t"+v[2]+"/t"+v[1]+"/t"+v[3]+"/t"+v[5]        # print '-'*50        # print userJinYanAll        return userJinYanAll        # userjianyanpaixu=sorted(userJinYanAll.iteritems(),key=lambda asd:asd[1],reverse=True)        # for k,v in userjianyanpaixu.items():        #     i+=1        #     print str(i)+"/t/t"+userjianyanpaixu[1]+"/t"+userjianyanpaixu[5]+"/t"+userjianyanpaixu[3]+
　　　　 #　　　　"/t"+userjianyanpaixu[2]+"/t"+userjianyanpaixu[6]        # # print userJinYanAll    except KeyboardInterrupt,e:        return e        # print "QUIT"def printstdout(printname):    sys.stdout.write("/r%s"%printname)    sys.stdout.flush()def pingJunNum(keyword,update,num):    # print keyword,update,num    updatetime=datetime.datetime.strptime(update,'%Y-%m-%d %H:%M')    newde=datetime.datetime.now()    chadate= newde-updatetime    return str(chadate).split(' ')[0]def sys_input():    url_baidu='http://jingyan.baidu.com/user/npublic/expList?un='    raw_str=urllib2.quote(raw_input('請輸入用戶百度經驗ID: '))    url=url_baidu+raw_str    menu(url)    # userjianyanpaixu=sorted(userJinYanAll.iteritems(),key=lambda asd:asd[1],reverse=True)    # print userjianyanpaixu    # for i in userjianyanpaixu:        # print i[1]def sys_input_wap(baidujyid):    url_baidu='http://jingyan.baidu.com/user/npublic/expList?un='    # raw_str=urllib2.quote(baidujyid)    url=url_baidu+baidujyid    returntest(url)    # return urldef returntest(url):    web=urllib2.urlopen(url).read()    return webif __name__=="__main__":    sys_input()