#!/usr/bin/perl
use HTML::Entities;
$doctype = "\n";
$filestring = "";
foreach (<>)
{
## SOME REGEXS TO STRIP OUT west HTML
chomp;
$filestring = $filestring . $_;
}
#print $filestring;
$filestring =~ s/\.htm//g;
$filestring =~ s///g;
$filestring =~ s/<\/span>//g;
#$filestring =~ s/<(SPAN|IMG|td|tr|table)[^>]+>//g;
## now remove styles
$filestring =~ s/.+<\/style>//g;
$filestring =~ s/]+>//g;
$filestring =~ s###g;
## try and deal with footnotes
#$filestring =~ s/\[FN(\d+)\]/$1<\/sup>/g;
#$filestring =~ s/FN(\d+)\./$1<\/sup>/g;
#$filestring =~ s/]+>//g;
#$filestring =~ s/<\/a>//g;
## put in anchors for original pages breaks
#$filestring =~ s/\*(\d\d?)<\/b>/<\/a>/g;
$filestring =~ s#<(p|div|h2|h3|h1)\b[^>]+>#<$1>#g;
$filestring =~ s##
\n#g;
$filestring =~ s#
#
##g;
$filestring =~ s##\n\n#g;
$filestring =~ s##\n#g;
$filestring =~ s##\n#g;
$filestring =~ s##\n#g;
$filestring =~ s##\n#g;
$filestring =~ s##\n#g;
$filestring =~ s##\n\n#g;
$filestring =~ s##\n\n#g;
$filestring =~ s#]+)>#\n\n#g;
$filestring =~ s#dtd">>#dtd">\n#g;
$filestring =~ s#Untitled\sDocument##g;
$filestring =~ s#]+>##g;
$filestring =~ s#<\?xml\b[^>]+>##g;
$filestring =~ s#]+>##g;
$filestring =~ s###g;
$filestring =~ s##\n#g;
$filestring =~ s##\n#g;
print $doctype;
print $filestring;