python3访问sina首页中文的处理方法

"""
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"))