#!/usr/bin/perl --
use strict;
use warnings;
use XML::LibXML 1.70; ## for load_html/load_xml/location
Main( @ARGV );
exit( 0 );
sub Main {
    my $loc = shift or die "
Usage:
    $0  ko00010.html
    $0  http://example.com/ko00010.html\n\n";

    my $dom = XML::LibXML->new(
        qw/ recover 2 /
    )->load_html(
        location => $loc,
    );
    for my $node ( $dom->findnodes( '//table | //img  | // script | //
+style | //noscript ' ) ){
        $node->detach;
    }
    print $dom->find('//body')->[0]->textContent,"\n";
}
sub XML::LibXML::Node::detach {     my( $self ) = @_;     $self->paren
+tNode->removeChild( $self ); }

[download]

In reply to Re^5: Ignoring specific html tags before parsing by Anonymous Monk
in thread Ignoring specific html tags before parsing by ganeshPerlStarter

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.