python处理抓取中文编码和判断编码

版本python2.7

#coding:utf-8
import chardet
#抓取网页html
line = "http://www.pythontab.com"
html_1 = urllib2.urlopen(line,timeout=120).read()
encoding_dict = chardet.detect(html_1)
print encoding
web_encoding = encoding_dict[&＃39;encoding&＃39;]
#处理，整个html就不会是乱码。
if web_encoding == &＃39;utf-8&＃39; or web_encoding == &＃39;UTF-8&＃39;:
html = html_1
else :
html = html_1.decode(&＃39;gbk&＃39;,&＃39;ignore&＃39;).encode(&＃39;utf-8&＃39;)