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['encoding'] #处理，整个html就不会是乱码。 if web_encoding == 'utf-8' or web_encoding == 'utf-8': html = html_1 else : html = html_1.decode('gbk','ignore').encode('utf-8')