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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urlparse
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     float_or_none,
  12     int_or_none,
  13     mimetype2ext,
  14     parse_iso8601,
  15     strip_jsonp,
  16 )
  17
  18
  19 class ArkenaIE(InfoExtractor):
  20     _VALID_URL = r'''(?x)
  21                         https?://
  22                             (?:
  23                                 video\.arkena\.com/play2/embed/player\?|
  24                                 play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
  25                             )
  26                         '''
  27     _TESTS = [{
  28         'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
  29         'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  30         'info_dict': {
  31             'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  32             'ext': 'mp4',
  33             'title': 'Big Buck Bunny',
  34             'description': 'Royalty free test video',
  35             'timestamp': 1432816365,
  36             'upload_date': '20150528',
  37             'is_live': False,
  38         },
  39     }, {
  40         'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
  47         'only_matching': True,
  48     }, {
  49         'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
  50         'only_matching': True,
  51     }]
  52
  53     @staticmethod
  54     def _extract_url(webpage):
  55         # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
  56         mobj = re.search(
  57             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1',
  58             webpage)
  59         if mobj:
  60             return mobj.group('url')
  61
  62     def _real_extract(self, url):
  63         mobj = re.match(self._VALID_URL, url)
  64         video_id = mobj.group('id')
  65         account_id = mobj.group('account_id')
  66
  67         # Handle http://video.arkena.com/play2/embed/player URL
  68         if not video_id:
  69             qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  70             video_id = qs.get('mediaId', [None])[0]
  71             account_id = qs.get('accountId', [None])[0]
  72             if not video_id or not account_id:
  73                 raise ExtractorError('Invalid URL', expected=True)
  74
  75         playlist = self._download_json(
  76             'https://play.arkena.com/config/avp/v2/player/media/%s/0/%s/?callbackMethod=_'
  77             % (video_id, account_id),
  78             video_id, transform_source=strip_jsonp)['Playlist'][0]
  79
  80         media_info = playlist['MediaInfo']
  81         title = media_info['Title']
  82         media_files = playlist['MediaFiles']
  83
  84         is_live = False
  85         formats = []
  86         for kind_case, kind_formats in media_files.items():
  87             kind = kind_case.lower()
  88             for f in kind_formats:
  89                 f_url = f.get('Url')
  90                 if not f_url:
  91                     continue
  92                 is_live = f.get('Live') == 'true'
  93                 exts = (mimetype2ext(f.get('Type')), determine_ext(f_url, None))
  94                 if kind == 'm3u8' or 'm3u8' in exts:
  95                     formats.extend(self._extract_m3u8_formats(
  96                         f_url, video_id, 'mp4',
  97                         entry_protocol='m3u8' if is_live else 'm3u8_native',
  98                         m3u8_id=kind, fatal=False, live=is_live))
  99                 elif kind == 'flash' or 'f4m' in exts:
 100                     formats.extend(self._extract_f4m_formats(
 101                         f_url, video_id, f4m_id=kind, fatal=False))
 102                 elif kind == 'dash' or 'mpd' in exts:
 103                     formats.extend(self._extract_mpd_formats(
 104                         f_url, video_id, mpd_id=kind, fatal=False))
 105                 elif kind == 'silverlight':
 106                     # TODO: process when ism is supported (see
 107                     # https://github.com/rg3/youtube-dl/issues/8118)
 108                     continue
 109                 else:
 110                     tbr = float_or_none(f.get('Bitrate'), 1000)
 111                     formats.append({
 112                         'url': f_url,
 113                         'format_id': '%s-%d' % (kind, tbr) if tbr else kind,
 114                         'tbr': tbr,
 115                     })
 116         self._sort_formats(formats)
 117
 118         description = media_info.get('Description')
 119         video_id = media_info.get('VideoId') or video_id
 120         timestamp = parse_iso8601(media_info.get('PublishDate'))
 121         thumbnails = [{
 122             'url': thumbnail['Url'],
 123             'width': int_or_none(thumbnail.get('Size')),
 124         } for thumbnail in (media_info.get('Poster') or []) if thumbnail.get('Url')]
 125
 126         return {
 127             'id': video_id,
 128             'title': title,
 129             'description': description,
 130             'timestamp': timestamp,
 131             'is_live': is_live,
 132             'thumbnails': thumbnails,
 133             'formats': formats,
 134         }