fix quoting in AsyncWgetFileGetter again

[videosite.git] / videosite / CollegeHumorGrabber.pm

diff --git a/videosite/CollegeHumorGrabber.pm b/videosite/CollegeHumorGrabber.pm
index 3bda5dd..c7851e3 100644 (file)
--- a/videosite/CollegeHumorGrabber.pm
+++ b/videosite/CollegeHumorGrabber.pm
@@ -3,29 +3,29 @@
 # (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 LWP::Simple qw(!get);
+use videosite::HTMLHelper;
 use XML::Simple;
-use HTML::Parser;
 use Data::Dumper;
 
 use strict;
 
 sub new {
     my $class = shift;
-    my $self = $class->SUPER::new();
-
-    $self->{'NAME'} = 'collegehumor';
-    $self->{'PATTERNS'} = ['(http://www.collegehumor.com/video:(\d+))'];
-
-    bless($self, $class);
-    $self->_prepare_parameters();
-
-    return $self;
+    my $self = $class->SUPER::new(
+        NAME => 'collegehumor',
+        _SELFTESTURL => 'http://www.collegehumor.com/video/5635400/pixar-intro-parody',
+        _SELFTESTTITLE => 'Pixar Intro Parody',
+        PATTERNS => ['(http://www.collegehumor.com/video:(\d+))',
+                     '(http://www.collegehumor.com/video/(\d+))'],
+        @_,
+    );
+
+    return bless($self, $class);
 }
 
 sub _parse {
@@ -49,7 +49,7 @@ 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 = $self->simple_get(sprintf('http://www.collegehumor.com/moogaloop/video/%s', $2)))) {
         $self->error('Could not download XML metadata');
         return undef;
     }
@@ -60,29 +60,7 @@ 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');