<script type="text/javascript"> 
if(document.charset){ 
 alert(document.charset+"!!!!"); 
 document.charset = 'GBK'; 
 alert(document.charset); 
} 
else if(document.characterSet){ 
 alert(document.characterSet+"????"); 
 document.characterSet = 'GBK'; 
 alert(document.characterSet); 
} 

import urllib 
rawdata = urllib.urlopen('http://www.1sucai.cn/').read() 
import chardet 
chardet.detect(rawdata) 
{'confidence': 0.99, 'encoding': 'GB2312'} 

import chardet 
a='abc' 
type(a) 
str 
chardet.detect(a) 
{'confidence': 1.0, 'encoding': 'ascii'} 
 
 
a ="我" 
chardet.detect(a) 
{'confidence': 0.73, 'encoding': 'windows-1252'} 
a.decode('windows-1252') 
u'\xe6\u02c6\u2018' 
chardet.detect(a.decode('windows-1252').encode('utf-8')) 
type(a.decode('windows-1252')) 
unicode 
type(a.decode('windows-1252').encode('utf-8')) 
str 
chardet.detect(a.decode('windows-1252').encode('utf-8')) 
{'confidence': 0.87625, 'encoding': 'utf-8'} 
 
 
a ="我是中国人" 
type(a) 
str 
{'confidence': 0.9690625, 'encoding': 'utf-8'} 
chardet.detect(a) 
# -*- coding:utf-8 -*- 
import chardet 
import urllib2 
#抓取网页html 
html = urllib2.urlopen('http://www.1sucai.cn/').read() 
print html 
mychar=chardet.detect(html) 
print mychar 
bianma=mychar['encoding'] 
if bianma == 'utf-8' or bianma == 'UTF-8': 
 html=html.decode('utf-8','ignore').encode('utf-8') 
else: 
 html =html.decode('gb2312','ignore').encode('utf-8') 
print html 
print chardet.detect(html) 

# -*- coding:utf-8 -*- 
 
print '中文'