代码如下:

<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />

这里提供一种简单的办法解决：使用chardet判断网页的真实编码，同时从url请求返回的info判断标示编码。如果两种编码不同，则使用bs模块扩展为GB18030编码；如果相同则直接写入文件（这里设置系统默认编码为utf-8）。

import urllib2
import sys
import bs4
import chardet
reload(sys)
sys.setdefaultencoding('utf-8')
def download(url):
 htmlfile = open('test.html','w')
 try:
 result = urllib2.urlopen(url)
 content = result.read()
 info = result.info()
 result.close()
 except Exception,e:
 print 'download error!!!'
 print e
 else:
 if content != None:
 charset1 = (chardet.detect(content))['encoding'] #real encoding type
 charset2 = info.getparam('charset') #declared encoding type
 print charset1,' ', charset2
 # case1: charset is not None.
 if charset1 != None and charset2 != None and charset1.lower() != charset2.lower():
 newcont = bs4.BeautifulSoup(content, from_encoding='GB18030') #coding: GB18030
 for cont in newcont:
 htmlfile.write('%s
'%cont)
 # case2: either charset is None, or charset is the same.
 else:
 #print sys.getdefaultencoding()
 htmlfile.write(content) #default coding: utf-8
 htmlfile.close()
if __name__ == "__main__":
 url = 'http://www.gxlcms.com'
 download(url)

得到的test.html文件打开如下，可以看到使用的是UTF-8无BOM编码格式存储的，也就是我们设置的默认编码：

更多python抓取并保存html页面时乱码问题的相关文章请关注PHP中文网！