Pulls the Original image url, title and description from a flickr description page. Doesn't download the page, but will take the html from the page on stdin.

flickr_ripper.pl

#!/usr/bin/perl

$re1='.*?';     # Non-greedy match on filler
$re2='(?:\\/[\\w\\.\\-]+)+';    # Uninteresting: unixpath
$re3='.*?';     # Non-greedy match on filler
$re4='((?:\\/[\\w\\.\\-]+)+_o.jpg)';    # Unix Path 1

$re=$re1.$re2.$re3.$re4;

while (<STDIN>) {
        $line = $_;
        chop($line);
        if (($line =~ m/$re/is) and ($got_orig == 0)) {
                $orig_url = $1;
                $got_orig = 1;
        }
        if (($line =~ m/<meta name="title" content="(.*)">/is) and ($got_title == 0)){
                $title=$1;
                $got_title = 1;
        }
        if (($line =~ m/<meta name="description" content="(.*)">/is) and ($got_desc == 0)){
                $desc=$1;
                $got_desc = 1;
        }
}
print ("Original image URL: http:/$orig_url\n");
print ("Title: $title\n");
print ("Description: $desc\n");