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