python实现html代码转义转换的例子

# cat html.py
#/usr/bin/python
#coding=utf-8
import HTMLParser
html_parser = HTMLParser.HTMLParser()
title = 'eclipse功能<template>学习。e.g : 快速在代码中插入时间戳 - 361way.com'
newtitle = html_parser.unescape(title)
print newtitle

Traceback (most recent call last):
  File "html.py", line 7, in
    newtitle = html_parser.unescape(title)
  File "/usr/lib64/python2.6/HTMLParser.py", line 390, in unescape
    return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|w{1,8}));", replaceEntities, s)
  File "/usr/lib64/python2.6/re.py", line 151, in sub
    return _compile(pattern, 0).sub(repl, string, count)
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe5 in position 7: ordinal not in range(128)

#/usr/bin/python
#coding=utf-8
import HTMLParser
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
html_parser = HTMLParser.HTMLParser()
title = 'eclipse功能<template>学习。e.g : 快速在代码中插入时间戳 - SegmentFault'
newtitle = html_parser.unescape(title)
print newtitle