怎么通过网页内容误别出是否为中文网页？

首先取响应头里的编码,
如果是几种中文编码之一,则认为中文网页,
如果不是中文编码, 也不是几种unicode方案之一, 则不是中文.
否则再在

#! /usr/bin/env python
# -*- encoding: utf-8 -*-
import requests
import cld2

class Detector(object):
    zh_cn_encodes = ('gbk', 'gb2312', 'gb18030')
    def __init__(self, context):
        self.context = context

    def is_zh_cn_encoding(self, ctype):
        ctype = ctype.lower()
        for ec in self.zh_cn_encodes:
            if ec in ctype:
                return True
        return False

    def detect(self):
        assert type(self.context) == type(u''), 'detect unicode string only'
        ret = cld2.detect(self.context.encode('utf-8'))
        return ret[2][0][1] == 'zh'

    def url_detect(self):
        r = requests.get(self.context)
        assert r.status_code == 200, 'http code 200 is required'
        ctype = r.encoding
        if ctype and self.is_zh_cn_encoding(ctype):
            return True
        else:
            self.context = r.text
            return self.detect()

if __name__ == '__main__':
    print Detector(u'短中文有bug').detect()
    print Detector(u'网页文件一般没问题').detect()
    print Detector(u'これは日本で').detect()
    url = 'http://segmentfault.com/q/1010000000432652'
    print Detector(url).url_detect()
    url = 'https://code.google.com/p/chromium-compact-language-detector/source/browse/README'
    print Detector(url).url_detect()