Python抓取网页乱码的原因及解决方法

import urllib

import gzip

from StringIO import StringIO

req = urllib.urlopen("http://some.web.site")

info = req.info()

encoding = info.getheader('Content-Encoding')

content = req.read()

if encoding == 'gzip':

    buf = StringIO(content)

    gf = gzip.GzipFile(fileobj=buf)

    content = gf.read()

print content

import requests

print requests.get("http://some.web.site").text

pip install requests