X-Git-Url: https://git.camperquake.de/gitweb.cgi?a=blobdiff_plain;f=videosite%2FBroadcasterGrabber.pm;h=4c371011cbc24f8fc71908b0b5b24e18fa95720e;hb=cc69ec1d9eb2ecf207b4c6b50a02062175e14314;hp=8d0cda9ef3ee25d7cda99ebc7606e8946e63ca34;hpb=24b7768511035a6793e01fc8da2fa245348e5d18;p=videosite.git

diff --git a/videosite/BroadcasterGrabber.pm b/videosite/BroadcasterGrabber.pm
index 8d0cda9..4c37101 100644
--- a/videosite/BroadcasterGrabber.pm
+++ b/videosite/BroadcasterGrabber.pm
@@ -3,28 +3,25 @@
 #
 # Grabber for broadcaster.com
 
-package BroadcasterGrabber;
+package videosite::BroadcasterGrabber;
 
-use GrabberBase;
-@ISA = qw(GrabberBase);
+use videosite::GrabberBase;
+@ISA = qw(videosite::GrabberBase);
 
-use LWP::Simple qw(!get);
-use HTML::Parser;
+use videosite::HTMLHelper;
 use Data::Dumper;
 
 use strict;
 
 sub new {
     my $class = shift;
-    my $self = $class->SUPER::new();
+    my $self = $class->SUPER::new(
+        NAME => 'broadcaster',
+        PATTERNS => ['(http://(?:[-a-zA-Z0-9_.]+\.)*broadcaster\.com/clip/(\d+))'],
+        @_,
+    );
 
-    $self->{'NAME'} = 'broadcaster';
-    $self->{'PATTERNS'} = ['(http://(?:[-a-zA-Z0-9_.]+\.)*broadcaster\.com/clip/(\d+))'];
-
-    bless($self, $class);
-    $self->_prepare_parameters();
-
-    return $self;
+    return bless($self, $class);
 }
 
 sub _parse {
@@ -33,10 +30,8 @@ sub _parse {
     my $pattern = shift;
     my $content;
     my $metadata = {};
-    my $p = HTML::Parser->new(api_version => 3);
-    my @accum;
-    my @text;
-    my $e;
+    my $p = videosite::HTMLHelper->new();
+    my $n;
 
     $url =~ m|$pattern|;
     $url = $1;
@@ -48,32 +43,22 @@ sub _parse {
     $metadata->{'TITLE'} = undef;
     $metadata->{'DLURL'} = undef;
 
-    unless(defined($content = LWP::Simple::get(sprintf('http://www.broadcaster.com/clip/%s', $2)))) {
+    unless(defined($content = $p->load(sprintf('http://www.broadcaster.com/clip/%s', $2)))) {
         $self->error('Could not download %s', $url);
         return undef;
     }
 
-    $p->handler(start => \@accum, "tagname, attr");
-    $p->handler(text => \@text, "text");
-    $p->report_tags(qw(script));
-    $p->utf8_mode(1);
-    $p->parse($content);
-
     # Look for the title
-    foreach $e (@text) {
-        if ($e->[0] =~ m|\&page_title=([^\x22]+)\x22|s) {
-            $metadata->{'TITLE'} = $1;
-            last;
-        }
-    }
+    ($metadata->{'TITLE'}) = grep { $_ =~ m|\&page_title=([^\x22]+)\x22|s && {$_ = $1} }
+            map { join("", @{$_->content()}) }
+            grep { defined($_->content()) }
+            $p->findnodes('script');
 
     # Look for the download URL
-    foreach $e (@text) {
-        if ($e->[0] =~ m|\&clip_loc=.+?cache.broadcaster.com.+?escape\(\x22([^\x22]+)\x22\)|s) {
-            $metadata->{'DLURL'} = 'http://cache.broadcaster.com/peoplecaster/' . $1;
-            last;
-        }
-    }
+    ($metadata->{'DLURL'}) = grep { $_ =~ m|\&clip_loc=.+?cache.broadcaster.com.+?escape\(\x22([^\x22]+)\x22\)|s && {$_ = 'http://cache.broadcaster.com/peoplecaster/' .$1} }
+            map { join("", @{$_->content()}) }
+            grep { defined($_->content()) }
+            $p->findnodes('script');
 
     unless(defined($metadata->{'DLURL'}) && defined($metadata->{'TITLE'})) {
         $self->error('Could not determine download URL');