Advanced Search

数値文字参照から文字へ変換

/ Published in: Python
Save to your folder(s)

Expand | Embed | Plain Text

Copy this code and paste it in your HTML 
  1. #!-*- coding:utf-8 -*-
  2. import htmlentitydefs
  3. import re
  4.  
  5. # 実体参照 & 文字参照を通常の文字に戻す
  6. def htmlentity2unicode(text):
  7.     # 正規表現のコンパイル
  8.     reference_regex = re.compile(u'&(#x?[0-9a-f]+|[a-z]+);', re.IGNORECASE)
  9.     num16_regex = re.compile(u'#x\d+', re.IGNORECASE)
  10.     num10_regex = re.compile(u'#\d+', re.IGNORECASE)
  11.  
  12.     result = u''
  13.     i = 0
  14.     while True:
  15.         # 実体参照 or 文字参照を見つける
  16.         match = reference_regex.search(text, i)
  17.         if match is None:
  18.             result += text[i:]
  19.             break
  20.  
  21.         result += text[i:match.start()]
  22.         i = match.end()
  23.         name = match.group(1)
  24.  
  25.         # 実体参照
  26.         if name in htmlentitydefs.name2codepoint.keys():
  27.             result += unichr(htmlentitydefs.name2codepoint[name])
  28.         # 文字参照
  29.         elif num16_regex.match(name):
  30.             # 16進数
  31.             result += unichr(int(u'0'+name[1:], 16))
  32.         elif num10_regex.match(name):
  33.             # 10進数
  34.             result += unichr(int(name[1:]))
  35.  
  36.     return result
  37.  
  38. # テストコード
  39. text = u"文字参照 & 実体参照 を通常の文字に戻します。";
  40. print htmlentity2unicode(text)

Report this snippet


Comments

RSS Icon Subscribe to comments

You need to login to post a comment.