X-Git-Url: https://git.camperquake.de/gitweb.cgi?a=blobdiff_plain;f=videosite%2FCollegeHumorGrabber.pm;h=fb032863b323fb506a9e7a8163a1cc2686ed0b97;hb=84bcf124e34f7e12c49f03c9841d863da9da0c8e;hp=3bda5dd5a8c0d7ed0eeffd76505674824d1915ba;hpb=b0f58504e0f59d7d607d4ef7c06495180f047311;p=videosite.git

diff --git a/videosite/CollegeHumorGrabber.pm b/videosite/CollegeHumorGrabber.pm
index 3bda5dd..fb03286 100644
--- a/videosite/CollegeHumorGrabber.pm
+++ b/videosite/CollegeHumorGrabber.pm
@@ -3,14 +3,14 @@
 # (c) 2007 by Ralf Ertzinger <ralf@camperquake.de>
 # licensed under GNU GPL v2
 
-package CollegeHumorGrabber;
+package videosite::CollegeHumorGrabber;
 
-use GrabberBase;
-@ISA = qw(GrabberBase);
+use videosite::GrabberBase;
+@ISA = qw(videosite::GrabberBase);
 
+use videosite::HTMLHelper;
 use LWP::Simple qw(!get);
 use XML::Simple;
-use HTML::Parser;
 use Data::Dumper;
 
 use strict;
@@ -20,7 +20,8 @@ sub new {
     my $self = $class->SUPER::new();
 
     $self->{'NAME'} = 'collegehumor';
-    $self->{'PATTERNS'} = ['(http://www.collegehumor.com/video:(\d+))'];
+    $self->{'PATTERNS'} = ['(http://www.collegehumor.com/video:(\d+))',
+                           '(http://www.collegehumor.com/video/(\d+))'];
 
     bless($self, $class);
     $self->_prepare_parameters();
@@ -49,7 +50,7 @@ sub _parse {
     $metadata->{'DLURL'} = undef;
 
     # Get the XML file containing the video metadata
-    unless(defined($content = LWP::Simple::get(sprintf('http://www.collegehumor.com/moogaloop/video:%s', $2)))) {
+    unless(defined($content = LWP::Simple::get(sprintf('http://www.collegehumor.com/moogaloop/video/%s', $2)))) {
         $self->error('Could not download XML metadata');
         return undef;
     }
@@ -60,29 +61,7 @@ sub _parse {
     }
 
     $metadata->{'DLURL'} = $t->{'video'}->{'file'};
-
-    # The XML does not contain the full title of the video, for
-    # reasons possibly known to some jerk at CollegeHumor.
-    # So we'll have to parse the actual HTML, too.
-    unless(defined($content = LWP::Simple::get(sprintf('http://www.collegehumor.com/video:%s', $2)))) {
-        $self->error('Could not download HTML');
-        return undef;
-    }
-    $p = HTML::Parser->new(api_version => 3);
-
-    $p->handler(start => \@accum, "tagname, attr");
-    $p->report_tags(qw(meta));
-    $p->utf8_mode(1);
-    $p->parse($content);
-
-    # Look for the title in the meta tags
-    foreach $t (@accum) {
-        if ('meta' eq $t->[0]) {
-            if ('title' eq $t->[1]->{'name'}) {
-                $metadata->{'TITLE'} = $t->[1]->{'content'};
-            }
-        }
-    }
+    $metadata->{'TITLE'} = $t->{'video'}->{'caption'};
 
     unless(defined($metadata->{'DLURL'}) && defined($metadata->{'TITLE'})) {
         $self->error('Could not extract download URL and title');