""" 如果只用普通的 import urllib.request html = urllib.request.urlopen("http://www.sina.com").read() print(html.decode('gbk')) 出现下面的错误 builtins.UnicodeDecodeError: 'gbk' codec can't decode byte 0x8b in position 1: illegal multibyte sequence 怎么办？原来是有的网站将网页用gzip压缩了 。 请看下面的代码 建议大家用python2 import urllib2 from StringIO import StringIO import gzip request = urllib2.Request('http://www.sina.com') request.add_header('Accept-encoding', 'gzip') response = urllib2.urlopen(request) if response.info().get('Content-Encoding') == 'gzip':     buf = StringIO( response.read())     f = gzip.GzipFile(fileobj=buf)     data = f.read() print data.decode("GBK").encode('utf-8') """ import io import urllib.request as r import gzip req = r.Request("http://www.sina.com", headers={"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36", "Accept-Encoding": "gzip"}) bs = r.urlopen(req).read() bi = io.BytesIO(bs) gf = gzip.GzipFile(fileobj=bi, mode="rb") print(gf.read().decode("gbk"))