下载TIMIT语料库源代码

import urllib, os

def getweb(url, localdir):
    usock = urllib.urlopen(url)
    webdat=usock.read()
    usock.close()
    webdat=webdat[webdat.find("Parent Directory</a>"):]
    allfile=webdat.split('href="')[1:]
    for childurl in allfile:
        childurl = childurl.split('"')[0]
        print "process:", childurl
        if(childurl[-1]=='/'):
            localdir = childurl[:-1]
            if not os.path.exists(localdir):
                os.mkdir(localdir)
            os.chdir(localdir)
            getweb(url+childurl, localdir)
            os.chdir("..")
        else:
            if os.path.exists(childurl): continue
            usock = urllib.urlopen(url+childurl)
            datsav = file(childurl, "wb+")
            while True:
                webdat=usock.read(10240)
                if len(webdat)<=0: break
                datsav.write(webdat)
            usock.close()
            datsav.close()
getweb("http://www.fon.hum.uva.nl/david/ma_ssp/2007/TIMIT/", "")