Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtp.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class RTPIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?'
  11     _TESTS = [{
  12         'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
  13         'md5': 'e736ce0c665e459ddb818546220b4ef8',
  14         'info_dict': {
  15             'id': 'e174042',
  16             'ext': 'mp3',
  17             'title': 'Paixões Cruzadas',
  18             'description': 'As paixões musicais de António Cartaxo e António Macedo',
  19             'thumbnail': 're:^https?://.*\.jpg',
  20         },
  21     }, {
  22         'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas',
  23         'only_matching': True,
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         webpage = self._download_webpage(url, video_id)
  30         title = self._html_search_meta(
  31             'twitter:title', webpage, display_name='title', fatal=True)
  32         description = self._html_search_meta('description', webpage)
  33         thumbnail = self._og_search_thumbnail(webpage)
  34
  35         player_config = self._search_regex(
  36             r'(?s)RTPPLAY\.player\.newPlayer\(\s*(\{.*?\})\s*\)', webpage, 'player config')
  37         config = self._parse_json(player_config, video_id)
  38
  39         path, ext = config.get('file').rsplit('.', 1)
  40         formats = [{
  41             'format_id': 'rtmp',
  42             'ext': ext,
  43             'vcodec': config.get('type') == 'audio' and 'none' or None,
  44             'preference': -2,
  45             'url': 'rtmp://{streamer:s}/{application:s}'.format(**config),
  46             'app': config.get('application'),
  47             'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path),
  48             'page_url': url,
  49             'rtmp_live': config.get('live', False),
  50             'player_url': 'http://programas.rtp.pt/play/player.swf?v3',
  51             'rtmp_real_time': True,
  52         }]
  53
  54         # Construct regular HTTP download URLs
  55         replacements = {
  56             'audio': {
  57                 'format_id': 'mp3',
  58                 'pattern': r'^nas2\.share/wavrss/',
  59                 'repl': 'http://rsspod.rtp.pt/podcasts/',
  60                 'vcodec': 'none',
  61             },
  62             'video': {
  63                 'format_id': 'mp4_h264',
  64                 'pattern': r'^nas2\.share/h264/',
  65                 'repl': 'http://rsspod.rtp.pt/videocasts/',
  66                 'vcodec': 'h264',
  67             },
  68         }
  69         r = replacements[config['type']]
  70         if re.match(r['pattern'], config['file']) is not None:
  71             formats.append({
  72                 'format_id': r['format_id'],
  73                 'url': re.sub(r['pattern'], r['repl'], config['file']),
  74                 'vcodec': r['vcodec'],
  75             })
  76
  77         self._sort_formats(formats)
  78
  79         return {
  80             'id': video_id,
  81             'title': title,
  82             'formats': formats,
  83             'description': description,
  84             'thumbnail': thumbnail,
  85         }