guyskk/gitgitgit

learn git

gitgitgit's Issues

编码问题

unicode里面是utf-8编码

>>> old = u'\xe9\xa2\x98\xe5\x90\x8d/\xe8\xb4\xa3\xe4\xbb\xbb\xe8\x80\x85:'
>>> [chr(ord(x))for x in old]
['\xe9', '\xa2', '\x98', '\xe5', '\x90', '\x8d', '/', '\xe8', '\xb4', '\xa3', '\
xe4', '\xbb', '\xbb', '\xe8', '\x80', '\x85', ':']
>>> temp=[chr(ord(x))for x in old]
>>> "".join(temp)
'\xe9\xa2\x98\xe5\x90\x8d/\xe8\xb4\xa3\xe4\xbb\xbb\xe8\x80\x85:'
>>> chr
<built-in function chr>
>>> ord
<built-in function ord>
>>> ord('A')
65
>>> ord('a')
97
>>> chr(97)
'a'

unicode 转义

>>> s='\u554a\u54c8'
>>> s.decode('unicode-escape')
u'\u554a\u54c8'

html 转义

import HTMLParser
import cgi

escape_txt = '<abc>'

#unescape
hp = HTMLParser.HTMLParser()
unescape_txt = hp.unescape(escape_txt )

#escape
escape_txt = cgi.escape(unescape_txt)

http://www.cnblogs.com/xuxn/archive/2011/08/12/parse-html-escape-characters-in-python.html