#coding=utf-8import gzipimport http.cookiejarimport urllib.requestimport urllib.parseimport jsonimport osimport timeimport datetimedef getOpener(head):    # deal with the Cookies    cj = http.cookiejar.CookieJar()    PRo = urllib.request.HTTPCookieProcessor(cj)    opener = urllib.request.build_opener(pro)    header = []    for key, value in head.items():        elem = (key, value)        header.append(elem)    opener.addheaders = header    return openerdef ungzip(data):    try:        # 嘗試解壓        print('正在解壓.....')        data = gzip.decompress(data)        print('解壓完畢!')    except:        print('未經壓縮, 無需解壓')    return datadef writeFile(fname,data):    filename = r'files/'+fname+'.txt'    if os.path.exists(filename):        message = '文件 + '+filename +' 已存在，跳過'    else:        message = '文件 + '+filename +' 不存在，新建'                f=open(filename,'w')        f.write(data)        f.close()    print ('文件：'+fname+' 處理完畢。')'''讀取抓取數據開始日期如果不存在該日期，從10日前開始讀取如果存在從文件內日期開始讀取讀到今天'''header = {    'Connection': 'Keep-Alive',    'Accept': '*/*',    'Accept-Language': 'zh-CN,zh;q=0.8',    'User-Agent': 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.111 Safari/537.36',    'Accept-Encoding': 'gzip, deflate',    'Host': '',    'Referer' : ''}shUrl = 'http://query.sse.com.cn/infodisplay/showTradePublicFile.do?dateTx='#2015-09-28szUrl = ['http://www.szse.cn/szseWeb/common/szse/files/text/jy/jy',#150923.txt         'http://www.szse.cn/szseWeb/common/szse/files/text/smeTxt/gk/sme_jy',#150708.txt         'http://www.szse.cn/szseWeb/common/szse/files/text/nmTxt/gk/nm_jy']#150902.txtstartFileName = r'startDay.txt'endDay = datetime.datetime.now()if os.path.exists(startFileName):    print('日期配置文件存在，開始讀取')    f=open(startFileName,'rt')    s = f.readline()    f.close()    if s!='':        print('將從日期：'+s+' 開始讀取')        timeArray = time.strptime(s, "%Y%m%d")        timeStamp = int(time.mktime(timeArray))        fromDay = datetime.datetime.utcfromtimestamp(timeStamp)    else:        print('日期配置文件為空，將從10日前日期開始讀取')        fromDay = endDay - datetime.timedelta(days = 10)else:    print('日期配置文件不存在，將從10日前日期開始讀取')    fromDay = endDay - datetime.timedelta(days = 10)endDay = endDay + datetime.timedelta(days = 1)while fromDay.strftime("%Y%m%d")!=endDay.strftime("%Y%m%d"):    print(fromDay.strftime("%Y%m%d"))        '''    循環上面日期    抓取上證，深證，中小創交易龍虎榜數據    如果內容不為空    文件不存在    寫入文件    '''    #抓取上證龍虎榜數據    url = shUrl + fromDay.strftime("%Y-%m-%d")    print('讀取上證龍虎榜/n'+url)    header['Host'] = 'query.sse.com.cn'    header['Referer'] = 'http://www.sse.com.cn/disclosure/diclosure/public/'    try:        opener = getOpener(header)        op = opener.open(url)        data = op.read()        data = data.decode()        jsonData = json.loads(data)        outData = ''        if (jsonData['fileContents']!=''):            for info in jsonData['fileContents']:                outData= outData+ info+'/n'            writeFile(fromDay.strftime("%Y-%m-%d")+'_上證',outData)    except:        print(fromDay.strftime("%Y-%m-%d")+'跳過')        #抓取深證，中小創交易龍虎榜數據    i=1    for url in szUrl:        if(i==1):            name = '深證'        elif(i==2):            name = '中小板'        else:            name = '創業板'        url = url + fromDay.strftime("%y%m%d")+'.txt'        print('讀取'+name+'龍虎榜/n'+url)        header['Host'] = 'www.szse.cn'        header['Referer'] = 'http://www.szse.cn'        try:            opener = getOpener(header)            op = opener.open(url)            data = op.read()            data = ungzip(data)            data = data.decode('gbk')            writeFile(fromDay.strftime("%Y-%m-%d")+'_'+name,data)        except:            print(fromDay.strftime("%Y-%m-%d")+'跳過')        i=i+1        fromDay = fromDay + datetime.timedelta(days = 1)#最后更新日期為當前日期print('設置最新日期')fromDay = fromDay - datetime.timedelta(days = 1)f=open(startFileName,'w')f.write(fromDay.strftime("%Y%m%d"))f.close()print('讀取完成')