url-html.el

   1 ;;; url-html.el --- Tools for dealing with html pages
   2
   3 ;; Copyright (C) 2008 William Xu
   4
   5 ;; Author: William Xu <william.xwl@gmail.com>
   6 ;; Version: 0.1
   7
   8 ;; This program is free software; you can redistribute it and/or modify
   9 ;; it under the terms of the GNU General Public License as published by
  10 ;; the Free Software Foundation; either version 3, or (at your option)
  11 ;; any later version.
  12
  13 ;; This program is distributed in the hope that it will be useful, but
  14 ;; WITHOUT ANY WARRANTY; without even the implied warranty of
  15 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  16 ;; General Public License for more details.
  17
  18 ;; You should have received a copy of the GNU General Public License
  19 ;; along with EMMS; see the file COPYING.  If not, write to the
  20 ;; Free Software Foundation, Inc., 51 Franklin St, Fifth Floor,
  21 ;; Boston, MA 02110-1301, USA.
  22
  23 ;;; Code:
  24
  25 (defun url-html-decode-buffer (&optional buffer)
  26   "Decode html BUFFER(default is current buffer).
  27 Usually used in buffer retrieved by `url-retrieve'. If no charset info
  28 is specified in html tag, default is 'utf-8."
  29   (unless buffer
  30     (setq buffer (current-buffer)))
  31   (with-current-buffer buffer
  32     (let ((coding 'utf-8))
  33       ;; (switch-to-buffer buffer)
  34       (when (save-excursion
  35               (goto-char (point-min))
  36               (re-search-forward "<meta http-equiv.*charset=[[:blank:]]*\\([a-zA-Z0-9_-]+\\)" nil t 1))
  37         (setq coding (intern (downcase (match-string 1)))))
  38       (set-buffer-multibyte t)
  39       (decode-coding-region (point-min) (point-max) coding))))
  40
  41
  42 (provide 'url-html)
  43
  44 ;;; url-html.el ends here