#!/usr/bin/perl
use strict;
use warnings;
use HTML::TreeBuilder;
use LWP::Simple;
use URI;
use Getopt::Std;
my %opts;
getopts('i', \%opts);
my ($tag, $href) = exists $opts{i} ? ('img', 'src') : ('a', 'href');
if (@ARGV < 1 or @ARGV > 2)
{
die "Invalid number of arguments";
}
my ($url, $regex) = @ARGV;
my $uri = URI->new($url);
my $tree;
$regex ||= '.';
if (-f $url)
{
$tree = HTML::TreeBuilder->new_from_file($url);
}
else
{
my $content = get($uri);
die unless defined $content;
$tree = HTML::TreeBuilder->new_from_content($content);
}
die unless defined $tree;
foreach my $link ($tree->look_down(_tag => $tag, $href => qr{$regex}))
{
my $link_url = URI->new_abs($link->attr($href), $uri);
print $link_url->as_string, "\n";
}
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.
|