#!perl -wl
# vim: set ts=8:

# how to replace certain text (your $name) with a link (to $url)
# based on what tags it is in inside the url

# the one problem i see is that if text is already in <a> then we
# embed an <a href></a> into it, the text after the href but
# before the end of the original </a> will lose its properties.
# this can be accounted for, but i'm lazy

use strict;
use HTML::Parser;

# global variables

our ($name, $url, @tagstack, $out) =
        qw{pizza http://www.parseerror.com/};

# sub defs

sub start {
        my ($tag, $attr, $text) = @_;
        $tag .= " href" if defined $attr->{"href"};
        push @tagstack, $tag;
        output($text);
}

sub end {
        my ($tag, $text) = @_;
        shift @tagstack
                while (@tagstack && $tagstack[0] !~ /^$tag$/);
        shift @tagstack if @tagstack;
        output($text);
}

sub text {
        my ($text) = @_;
        if ($text =~ /\b$name\b/ && canreplace() && unlinked()) {
                $text =~ s#\b$name\b#<a href="$url">$name</a>#g;
        }
        output($text);
}

sub output {
        my ($txt) = @_;
        $out .= $txt if defined $txt;
}

# are we inside a tag we don't want to link?
sub canreplace {
        return ! grep {m/^(head|title)$/} @tagstack;
}

# are we inside a link right now?
sub unlinked {
        return ! grep {m/^a href$/} @tagstack;
}

# start code

my $p = HTML::Parser->new(
        "start_h"       => [ \&start, "tagname, attr, text" ]
        ,"end_h"        => [ \&end, "tagname, text" ]
        ,"text_h"       => [ \&text, "text" ]
);

$p->parse(q{
<html>
        <head>
                <title>pizza is delicious!</title>
        </head>
        <body>
                <a href="">pizza already linked</a>
                <b>some more pizza</b>
                <a>pizza in a but not linked</a>
        </body>
</html>
});

print $out;

[download]
i've put the code up on http://www.parseerror.com/scripts/replace_name.pl

perl -e'$_="nwdd\x7F^n\x7Flm{{llql0}qs\x14";s/./chr(ord$&^30)/ge;print'

In reply to Re: Search and replacing across 500,000 HTML documents by pizza_milkshake
in thread Search and replacing across 500,000 HTML documents by Anonymous Monk

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.