share/media/guardian.lua

   1 -- libquvi-scripts
   2 -- Copyright (C) 2011,2013  Toni Gundogdu <legatvs@gmail.com>
   3 --
   4 -- This file is part of libquvi-scripts <http://quvi.sourceforge.net/>.
   5 --
   6 -- This program is free software: you can redistribute it and/or
   7 -- modify it under the terms of the GNU Affero General Public
   8 -- License as published by the Free Software Foundation, either
   9 -- version 3 of the License, or (at your option) any later version.
  10 --
  11 -- This program is distributed in the hope that it will be useful,
  12 -- but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 -- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 -- GNU Affero General Public License for more details.
  15 --
  16 -- You should have received a copy of the GNU Affero General
  17 -- Public License along with this program.  If not, see
  18 -- <http://www.gnu.org/licenses/>.
  19 --
  20
  21 local Guardian = {} -- Utility functions unique to this script
  22
  23 -- Identify the media script.
  24 function ident(qargs)
  25   return {
  26     can_parse_url = Guardian.can_parse_url(qargs),
  27     domains = table.concat({'theguardian.com', 'guardian.co.uk'}, ',')
  28   }
  29 end
  30
  31 -- Parse the media properties.
  32 function parse(qargs)
  33   local p = Guardian.fetch(qargs)
  34
  35   qargs.duration_ms = Guardian.parse_duration(p)
  36
  37   qargs.title = (p:match('"og:title" content="(.-)"') or '')
  38                   :gsub('%s+%-%s+video','')
  39
  40   qargs.id = (p:match('prop8%s+=%s+["\'](.-)["\']') or '')
  41               :match('(%d+)') or ''
  42
  43   qargs.thumb_url = p:match('"thumbnail" content="(.-)"')
  44                       or p:match('"og:image" content="(.-)"') or ''
  45
  46   qargs.streams = Guardian.iter_streams(p)
  47
  48   return qargs
  49 end
  50
  51 --
  52 -- Utility functions
  53 --
  54
  55 function Guardian.can_parse_url(qargs)
  56   local U = require 'socket.url'
  57   local t = U.parse(qargs.input_url)
  58   if t and t.scheme and t.scheme:lower():match('^https?$')
  59        and t.host   and (t.host:lower():match('theguardian%.com$')
  60                          or t.host:lower():match('guardian%.co%.uk$'))
  61        and t.path   and (t.path:lower():match('/video/')
  62                          or t.path:lower():match('/audio/'))
  63   then
  64     return true
  65   else
  66     return false
  67   end
  68 end
  69
  70 function Guardian.fetch(qargs)
  71   local p = quvi.http.fetch(qargs.input_url).data
  72   local e = p:match('<div class="expired">.-<p>(.-)</p>.-</div>') or ''
  73   if #e >0 then error(e) end
  74   return p
  75 end
  76
  77 function Guardian.iter_streams(p)
  78   local u = p:match("%s+file.-:%s+'(.-)'")
  79               or error('no match: media stream URL')
  80   local S = require 'quvi/stream'
  81   local s = S.stream_new(u)
  82   s.video.height = tonumber(p:match('itemprop="height" content="(%d+)"') or 0)
  83   s.video.width = tonumber(p:match('itemprop="width" content="(%d+)"') or 0)
  84   return {s}
  85 end
  86
  87 function Guardian.parse_duration(p)
  88   local n = tonumber(p:match('duration%:%s+"?(%d+)"?') or 0) * 1000
  89   if n ==0 then
  90     local m,s = p:match('T(%d+)M(%d+)S')
  91     n = (tonumber(m)*60 + tonumber(s)) * 1000
  92   end
  93   return n
  94 end
  95
  96 -- vim: set ts=2 sw=2 tw=72 expandtab: