For clarity sake with all of the code and changes and stuff here is the code that
works mostly the way I want with the 3 questions/problems/needs after the #'s, $text
contains actual html code:
#-------------------------
# get $title - EG the 'Your Title Here' in :: <title> Your Title Here </title>
# get $bdy_tg_at - EG the 'bgcolor="red" link="#EOEOEO"' in :: <body bgcolor="red"
link="#EOEOEO">
# This code removes <!-- comments --> automatically, which is what I want. But I'm not
sure how/why exactly it does.
# Should I start a new object that just grabs the title and bdy_tg_at ??
# I tried another example with fetched the title ok but
# it made the attributes :: bgcolor="red"=link="#EOEOEO"
# the attributes were in the same data as the body contents, so there was no way
to separate it fomr the content
# removed all html from the body content
use HTML::Parser;
my $temp;
my $html = HTML::Parser->new(
api_version => 3,
text_h => [sub{ $temp .= shift; }, 'dtext'],
start_h => [sub{ $temp .= shift; }, 'text'],
end_h => [sub{ $temp .= shift; }, 'text']);
$html->ignore_elements(qw(head script));
$html->ignore_tags(qw(html body));
$html->parse($text);
$html->eof;
my $ntemp;
my @t = split(/\n/, $temp);
foreach $t (@t) {
if($t =~ m/\w/) {
$ntemp .= "$t \n";
}
}
print "TITLE -$title- \n";
print "BDATT -$bdy_tg_at- \n";
print $ntemp;
#----------------------------
--
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
