Created
January 14, 2013 05:54
-
-
Save bvr/4527990 to your computer and use it in GitHub Desktop.
Find title and stream URL on dailymotion page
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
use 5.010; use strict; use warnings; | |
# ppm inst Mojolicious | |
use Mojo::UserAgent; | |
use Mojo::Cookie::Response; | |
use Mojo::Util 'url_unescape'; | |
use Mojo::JSON; | |
# debugging | |
use Path::Class; | |
use DDP; | |
my $url = shift or die "syntax: $0 url\n"; | |
my $ua = Mojo::UserAgent->new(max_redirects => 5); | |
$ua->cookie_jar->add( | |
Mojo::Cookie::Response->new( | |
domain => '.dailymotion.com', | |
path => '/', | |
name => 'family_filter', | |
value => 'off' | |
) | |
); | |
my $res = $ua->get($url)->res; | |
my $sequence = do { | |
$res->body =~ /"sequence":"(.*?)"/ | |
? url_unescape $1 | |
: die 'cannot find the sequence' | |
}; | |
# file('seq.json')->spew($sequence); | |
# get the title | |
say $res->dom->at('meta[property="og:title"]')->attrs('content'); | |
# list of urls | |
my $iter = struct_iter(Mojo::JSON->new->decode($sequence)); | |
while(my ($prefix, $value) = $iter->()) { | |
if($prefix =~ /URL$/ && $value =~ /(\d+)x(\d+)\/video\/.*?\.([a-z0-9]+)/) { | |
say "$1 $2 $3: $value"; | |
} | |
} | |
sub struct_iter { | |
my ($item_ref) = @_; | |
my @blocks = (['', $item_ref]); | |
return sub { | |
while(my $blk = shift @blocks) { | |
my ($prefix, $item) = @$blk; | |
for(ref $item) { | |
when('ARRAY') { | |
push @blocks, | |
map { ["$prefix/[$_]", $item->[$_]] } 0 .. $#$item; | |
} | |
when('HASH') { | |
push @blocks, | |
map { ["$prefix/$_", $item->{$_}] } sort keys %$item; | |
} | |
return ($prefix, $item); | |
} | |
} | |
return; | |
}; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment