# skip over header material # Copyright (C) 1999 Sandy Harris. # # This program is free software; you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by the # Free Software Foundation; either version 2 of the License, or (at your # option) any later version. See . # # This program is distributed in the hope that it will be useful, but # WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License # for more details. # # RCSID $Id: html2txt.sed,v 1.1 2004/03/15 20:35:24 as Exp $ //,/<\/head>/d //,/<\/HEAD>/d /<^body$>/d s/// # eliminate possible DOS crud s/\015// #get rid of HTML comments s/// //d # citations & emphasis -> visible s//"/g s/<\/cite>/"/g s//*/g s/<\/em>/*/g s//!->/g s/<\/strong>/<-!/g s///g s/<\/b>//g s/
/Quote -->/ s/<\/blockquote>/<-- End Quote/ # mark headers s/
/Header 1: / s/
/Header 2: / s/
/Header 3: / s/
/Header 4: / s/
/Header 5: / s/
/Header 6: / # remove some cruft s/<\/h[1-6]>// /^$/d s/// # definition lists s/
// s/<\/dl>// s/^
$/-----------------------------------------/ s/^
/-----------------------------------------\ / s/
/\ / # other types of lists s/
// s/
// s/
// s/<\/ol>// s/<\/ul>// # tables s/// s/<\/table>// s/// s/
/ /g # line break and paragraph markers # different subst depending where they are in line s/^
// s/
$// s/
/\ / s/^
$// s/
$/\ / s/^
/\ / s/
/\ \ / s/<\/p>// # remove more cruft s/
// s/<\/pre>// s/<\/body>// s/<\/html// s/<\/BODY>// s/<\/HTML>//