X-Git-Url: https://git.camperquake.de/gitweb.cgi?a=blobdiff_plain;f=videosite%2FYouTubeGrabber.pm;h=423184cb444852b3f5006b385e81d4db2377f6fb;hb=5420b8942fbbe6da34d37152f6079a5d98117596;hp=bf954cc98289cfbb484284e9c9a95b7e2653bd28;hpb=1b803a8856b61ffde5e2c8f9e3f91ea3bcd6d01f;p=videosite.git diff --git a/videosite/YouTubeGrabber.pm b/videosite/YouTubeGrabber.pm index bf954cc..423184c 100644 --- a/videosite/YouTubeGrabber.pm +++ b/videosite/YouTubeGrabber.pm @@ -35,6 +35,7 @@ my %videoformats = ( 22 => 'MP4/H264/AAC/720p', # isommp42, High 34 => 'FLV/H264/AAC/360p', # Main 35 => 'FLV/H264/AAC/480p', # Main + 36 => '3GP/MPEG4-Visual/240p', 37 => 'MP4/H264/AAC/1080p', # High 38 => 'MP4/H264/AAC/3072p', # High 43 => 'WebM/VP8/Vorbis/360p', @@ -52,33 +53,33 @@ my %videoformats = ( sub new { my $class = shift; - my $self = $class->SUPER::new(); - - $self->{'NAME'} = 'youtube'; - $self->{_SELFTESTURL} = 'http://www.youtube.com/watch?v=dMH0bHeiRNg'; - $self->{_SELFTESTTITLE} = 'Evolution of Dance - By Judson Laipply'; - $self->{'PATTERNS'} = ['(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/watch(?:_popup)?\?(?:.+=.+&|&)*v=([-a-zA-Z0-9_]+))', - '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/watch\#\!v=([-a-zA-Z0-9_]+))', - '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/v/([-a-zA-Z0-9_]+))', - '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/user/[[:alnum:]]+\?v=([-a-zA-Z0-9_]+))', - '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/(?:user/)?[[:alnum:]]+#p/(?:\w+/)+\d+/([-a-zA-Z0-9_]+))', - '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtu\.be/watch\?v=([-a-zA-Z0-9_]+))', - '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtu\.be/([-a-zA-Z0-9_]+))', - '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/user/\w+\?.*/([-a-zA-Z0-9_]+))']; - $self->{'_PARAMS'} = { - 'QUALITY' => ['normal', 'Quality of the video to download.', { - 'normal' => 'standard resolution flash video', - 'high' => 'higher resolution flash video', - 'h264' => 'high resolution MPEG4 video', - 'hd' => 'HD720 resolution'}], - 'USERNAME' => ['', 'Username to use for YouTube login'], - 'PASSWORD' => ['', 'Password to use for YouTube login'], - 'HTTPS' => [1, 'Whether to use HTTPS (if available) to connect to YouTube']}; - - bless($self, $class); - $self->_prepare_parameters(); - - return $self; + my $self = $class->SUPER::new( + NAME => 'youtube', + _SELFTESTURL => 'http://www.youtube.com/watch?v=dMH0bHeiRNg', + _SELFTESTTITLE => 'Evolution of Dance - By Judson Laipply', + PATTERNS => ['(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/watch(?:_popup)?\?.*?v=([-a-zA-Z0-9_]+))', + '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/watch\#\!v=([-a-zA-Z0-9_]+))', + '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/v/([-a-zA-Z0-9_]+))', + '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/embed/([-a-zA-Z0-9_]+))', + '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/user/[[:alnum:]]+\?v=([-a-zA-Z0-9_]+))', + '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/(?:user/)?[[:alnum:]]+#p/(?:\w+/)+\d+/([-a-zA-Z0-9_]+))', + '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtu\.be/watch\?v=([-a-zA-Z0-9_]+))', + '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtu\.be/([-a-zA-Z0-9_]+))', + '(https?://(?:[-a-zA-Z0-9_.]+\.)*youtube\.(?:com|de|co.uk)/user/\w+\?.*/([-a-zA-Z0-9_]+))'], + _PARAMS => { + QUALITY => ['normal', 'Quality of the video to download.', { + normal => 'standard resolution flash video', + high => 'higher resolution flash video', + h264 => 'high resolution MPEG4 video', + hd => 'HD720 resolution'}], + USERNAME => ['', 'Username to use for YouTube login'], + PASSWORD => ['', 'Password to use for YouTube login'], + HTTPS => [1, 'Whether to use HTTPS (if available) to connect to YouTube'] + }, + @_, + ); + + return bless($self, $class); } sub _parse { @@ -95,15 +96,28 @@ sub _parse { $self->debug("Matched id %s from pattern %s", $id, $pattern); $res = $self->_parse_by_video_info($url, $id); - if (defined($res) && ref($res)) { - return $res; + if (defined($res)) { + if (ref($res)) { + return $res; + } else { + $self->debug("_parse_by_video_info failed with status noretry"); + return undef; + } } else { + $self->debug("_parse_by_video_info failed with status retry"); $res = $self->_parse_by_scrape($url, $id); } return $res; } +# +# Try to get video information by using the API call. +# +# Returns hashref on success +# Returns undef on retryable error (try to scrape the website) +# Returns 0 on non-retryable error +# sub _parse_by_video_info { my $self = shift; my $url = shift; @@ -143,11 +157,19 @@ sub _parse_by_video_info { # Decode content $content = $self->decode_querystring($content); + $self->debug("Decoded get_video_info: %s", Dumper($content)); + if ($content->{'status'} ne 'ok') { $self->debug("Non OK status code found: %s", $content->{'status'}); return undef; } + # Check if this is live content + if (exists($content->{ps}) and ($content->{ps} eq 'live')) { + $self->error("Video URL seems to point to a live stream, cannot save this"); + return 0; + } + if (exists($content->{'fmt_url_map'})) { # Decode fmt_url_map $urls = $self->decode_hexurl($content->{'fmt_url_map'}); @@ -244,66 +266,7 @@ sub _parse_by_scrape { $e = $p->get_text(); $self->debug("Found script: %s", $e); -# if ($e =~ m|\x27SWF_ARGS\x27:\s+(.+),|) { -# my $args = $1; -# -# $self->debug("Found SWF_ARGS: %s", $args); -# $jsp = videosite::JSArrayParser->new(); -# $self->debug("Using %s to parse", ref($jsp)); -# $r = $jsp->parse($args); -# -# unless(defined($r)) { -# $self->error("Found information hash, but could not parse"); -# return undef; -# } -# -# if (exists($r->{'fmt_url_map'}) and ($r->{'fmt_url_map'} ne '')) { -# my $urls = $r->{'fmt_url_map'}; -# -# $self->debug("Video has fmt_url_map: %s", $urls); -# -# $urls = $self->decode_hexurl($urls); -# %urls = split(/[\|,]/, $urls); -# $self->debug("Pagetype: old (SWF_ARGS), fmt_url_map"); -# -# } elsif (exists($r->{'t'}) and ($r->{'t'} ne '')) { -# my $thash = $r->{'t'}; -# -# if (exists($r->{'fmt_map'}) && ($r->{'fmt_map'} ne '')) { -# my $fmt = $r->{'fmt_map'}; -# my @fmt; -# -# $self->debug('Video has fmt_map'); -# $fmt = $self->decode_hexurl($fmt); -# @fmt = split(/,/, $fmt); -# foreach (@fmt) { -# @_=split(/\//); -# $urls{$_[0]} = sprintf('http://www.youtube.com/get_video?video_id=%s&fmt=%d&t=%s', -# $metadata->{'ID'}, -# $_[0], -# $thash); -# } -# $self->debug("Pagetype: 2009 (SWF_ARGS), t with fmt_map"); -# -# } else { -# $urls{5} = sprintf('http://www.youtube.com/get_video?video_id=%s&t=%s', -# $metadata->{'ID'}, -# $thash); -# $self->debug("Pagetype: 2009 (SWF_ARGS), t without fmt_map"); -# } -# } else { -# $self->error('Neither fmt_url_map nor t found in video information hash'); -# return undef; -# } -# } elsif ($e =~ m|var swfHTML = .*fmt_url_map=([^\&]+)\&|) { -# my $urls = $1; -# $self->debug("Video has fmt_url_map: %s", $urls); -# -# $urls = $self->decode_hexurl($urls); -# %urls = split(/[\|,]/, $urls); -# $self->debug("Pagetype: 2010 (swfHTML), fmt_url_map"); -# } elsif ($e =~ m|\x27PLAYER_CONFIG\x27:\s+(.+)(?:\}\);)?|) { - if ($e =~ m|\x27PLAYER_CONFIG\x27:\s+(.+)(?:\}\);)?|) { + if ($e =~ m|ytplayer\.config\s*=\s*(.+);$|) { my $args = $1; $self->debug("Found PLAYER_CONFIG: %s", $args); @@ -506,6 +469,7 @@ sub _decode_url_encoded_fmt_stream_map { my $data = shift; my $dataencoded = shift; my @data; + my $h = {}; $data = $self->decode_hexurl($data) if $dataencoded; # This will @@ -521,7 +485,16 @@ sub _decode_url_encoded_fmt_stream_map { # From each array entry, pick the itag and the url values and return that # as a hash reference - return { map { $_->{'itag'}, $_->{'url'} } @data }; + + foreach (@data) { + if (exists($_->{'sig'})) { + $h->{$_->{'itag'}} = sprintf('%s&signature=%s', $_->{'url'}, $_->{'sig'}); + } else { + $h->{$_->{'itag'}} = $_->{'url'}; + } + } + + return $h; }