''' 根据URL返回内容,有些页面可能需要gzip解压缩 ''' def getUrlContent(url): #返回页面内容 doc = urllib.request.urlopen(url).read() #解码 try: html=gzip.decompress(doc).decode("utf-8") except: html=doc.decode("utf-8") return html
转自:http://www.cnblogs.com/GarfieldTom/archive/2012/12/04/2802000.html