yt_dlp/extractor/europa.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     orderedSet,
   5     parse_duration,
   6     parse_iso8601,
   7     parse_qs,
   8     qualities,
   9     unified_strdate,
  10     xpath_text
  11 )
  12
  13
  14 class EuropaIE(InfoExtractor):
  15     _VALID_URL = r'https?://ec\.europa\.eu/avservices/(?:video/player|audio/audioDetails)\.cfm\?.*?\bref=(?P<id>[A-Za-z0-9-]+)'
  16     _TESTS = [{
  17         'url': 'http://ec.europa.eu/avservices/video/player.cfm?ref=I107758',
  18         'md5': '574f080699ddd1e19a675b0ddf010371',
  19         'info_dict': {
  20             'id': 'I107758',
  21             'ext': 'mp4',
  22             'title': 'TRADE - Wikileaks on TTIP',
  23             'description': 'NEW  LIVE EC Midday press briefing of 11/08/2015',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'upload_date': '20150811',
  26             'duration': 34,
  27             'view_count': int,
  28             'formats': 'mincount:3',
  29         }
  30     }, {
  31         'url': 'http://ec.europa.eu/avservices/video/player.cfm?sitelang=en&ref=I107786',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://ec.europa.eu/avservices/audio/audioDetails.cfm?ref=I-109295&sitelang=en',
  35         'only_matching': True,
  36     }]
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40
  41         playlist = self._download_xml(
  42             'http://ec.europa.eu/avservices/video/player/playlist.cfm?ID=%s' % video_id, video_id)
  43
  44         def get_item(type_, preference):
  45             items = {}
  46             for item in playlist.findall('./info/%s/item' % type_):
  47                 lang, label = xpath_text(item, 'lg', default=None), xpath_text(item, 'label', default=None)
  48                 if lang and label:
  49                     items[lang] = label.strip()
  50             for p in preference:
  51                 if items.get(p):
  52                     return items[p]
  53
  54         query = parse_qs(url)
  55         preferred_lang = query.get('sitelang', ('en', ))[0]
  56
  57         preferred_langs = orderedSet((preferred_lang, 'en', 'int'))
  58
  59         title = get_item('title', preferred_langs) or video_id
  60         description = get_item('description', preferred_langs)
  61         thumbnail = xpath_text(playlist, './info/thumburl', 'thumbnail')
  62         upload_date = unified_strdate(xpath_text(playlist, './info/date', 'upload date'))
  63         duration = parse_duration(xpath_text(playlist, './info/duration', 'duration'))
  64         view_count = int_or_none(xpath_text(playlist, './info/views', 'views'))
  65
  66         language_preference = qualities(preferred_langs[::-1])
  67
  68         formats = []
  69         for file_ in playlist.findall('./files/file'):
  70             video_url = xpath_text(file_, './url')
  71             if not video_url:
  72                 continue
  73             lang = xpath_text(file_, './lg')
  74             formats.append({
  75                 'url': video_url,
  76                 'format_id': lang,
  77                 'format_note': xpath_text(file_, './lglabel'),
  78                 'language_preference': language_preference(lang)
  79             })
  80
  81         return {
  82             'id': video_id,
  83             'title': title,
  84             'description': description,
  85             'thumbnail': thumbnail,
  86             'upload_date': upload_date,
  87             'duration': duration,
  88             'view_count': view_count,
  89             'formats': formats
  90         }
  91
  92
  93 class EuroParlWebstreamIE(InfoExtractor):
  94     _VALID_URL = r'''(?x)
  95         https?://(?:multimedia|webstreaming)\.europarl\.europa\.eu/[^/#?]+/
  96         (?:embed/embed\.html\?event=|(?!video)[^/#?]+/[\w-]+_)(?P<id>[\w-]+)
  97     '''
  98     _TESTS = [{
  99         'url': 'https://multimedia.europarl.europa.eu/pl/webstreaming/plenary-session_20220914-0900-PLENARY',
 100         'info_dict': {
 101             'id': 'bcaa1db4-76ef-7e06-8da7-839bd0ad1dbe',
 102             'ext': 'mp4',
 103             'release_timestamp': 1663137900,
 104             'title': 'Plenary session',
 105             'release_date': '20220914',
 106         },
 107         'params': {
 108             'skip_download': True,
 109         }
 110     }, {
 111         'url': 'https://multimedia.europarl.europa.eu/pl/webstreaming/eu-cop27-un-climate-change-conference-in-sharm-el-sheikh-egypt-ep-delegation-meets-with-ngo-represen_20221114-1600-SPECIAL-OTHER',
 112         'info_dict': {
 113             'id': 'a8428de8-b9cd-6a2e-11e4-3805d9c9ff5c',
 114             'ext': 'mp4',
 115             'release_timestamp': 1668434400,
 116             'release_date': '20221114',
 117             'title': 'md5:d3550280c33cc70e0678652e3d52c028',
 118         },
 119         'params': {
 120             'skip_download': True,
 121         }
 122     }, {
 123         # embed webpage
 124         'url': 'https://webstreaming.europarl.europa.eu/ep/embed/embed.html?event=20220914-0900-PLENARY&language=en&autoplay=true&logo=true',
 125         'info_dict': {
 126             'id': 'bcaa1db4-76ef-7e06-8da7-839bd0ad1dbe',
 127             'ext': 'mp4',
 128             'title': 'Plenary session',
 129             'release_date': '20220914',
 130             'release_timestamp': 1663137900,
 131         },
 132         'params': {
 133             'skip_download': True,
 134         }
 135     }, {
 136         # live webstream
 137         'url': 'https://multimedia.europarl.europa.eu/en/webstreaming/euroscola_20221115-1000-SPECIAL-EUROSCOLA',
 138         'info_dict': {
 139             'ext': 'mp4',
 140             'id': '510eda7f-ba72-161b-7ee7-0e836cd2e715',
 141             'release_timestamp': 1668502800,
 142             'title': 'Euroscola 2022-11-15 19:21',
 143             'release_date': '20221115',
 144             'live_status': 'is_live',
 145         },
 146         'skip': 'not live anymore'
 147     }]
 148
 149     def _real_extract(self, url):
 150         display_id = self._match_id(url)
 151
 152         json_info = self._download_json(
 153             'https://vis-api.vuplay.co.uk/event/external', display_id,
 154             query={
 155                 'player_key': 'europarl|718f822c-a48c-4841-9947-c9cb9bb1743c',
 156                 'external_id': display_id,
 157             })
 158
 159         formats, subtitles = self._extract_mpd_formats_and_subtitles(json_info['streaming_url'], display_id)
 160         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 161             json_info['streaming_url'].replace('.mpd', '.m3u8'), display_id)
 162
 163         formats.extend(fmts)
 164         self._merge_subtitles(subs, target=subtitles)
 165
 166         return {
 167             'id': json_info['id'],
 168             'title': json_info.get('title'),
 169             'formats': formats,
 170             'subtitles': subtitles,
 171             'release_timestamp': parse_iso8601(json_info.get('published_start')),
 172             'is_live': 'LIVE' in json_info.get('state', '')
 173         }