yt_dlp/extractor/uliza.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     int_or_none,
   5     make_archive_id,
   6     parse_qs,
   7     time_seconds,
   8 )
   9 from ..utils.traversal import traverse_obj
  10
  11
  12 class UlizaPlayerIE(InfoExtractor):
  13     _VALID_URL = r'https://player-api\.p\.uliza\.jp/v1/players/[^?#]+\?(?:[^#]*&)?name=(?P<id>[^#&]+)'
  14     _TESTS = [{
  15         'url': 'https://player-api.p.uliza.jp/v1/players/timeshift-disabled/pia/admin?type=normal&playerobjectname=ulizaPlayer&name=livestream01_dvr&repeatable=true',
  16         'info_dict': {
  17             'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
  18             'ext': 'mp4',
  19             'title': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
  20             'live_status': 'was_live',
  21             '_old_archive_ids': ['piaulizaportal 88f3109a-f503-4d0f-a9f7-9f39ac745d84'],
  22         },
  23     }, {
  24         'url': 'https://player-api.p.uliza.jp/v1/players/uliza_jp_gallery_normal/promotion/admin?type=presentation&name=cookings&targetid=player1',
  25         'info_dict': {
  26             'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
  27             'ext': 'mp4',
  28             'title': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
  29             'live_status': 'not_live',
  30             '_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
  31         },
  32     }, {
  33         'url': 'https://player-api.p.uliza.jp/v1/players/default-player/pia/admin?type=normal&name=pia_movie_uliza_fix&targetid=ulizahtml5&repeatable=true',
  34         'info_dict': {
  35             'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
  36             'ext': 'mp4',
  37             'title': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
  38             'live_status': 'not_live',
  39             '_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
  40         },
  41     }]
  42
  43     def _real_extract(self, url):
  44         display_id = self._match_id(url)
  45         player_data = self._download_webpage(
  46             url, display_id, headers={'Referer': 'https://player-api.p.uliza.jp/'},
  47             note='Fetching player data', errnote='Unable to fetch player data')
  48
  49         m3u8_url = self._search_regex(
  50             r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data, 'm3u8 url')
  51         video_id = parse_qs(m3u8_url).get('ss', [display_id])[0]
  52
  53         formats = self._extract_m3u8_formats(m3u8_url, video_id)
  54         m3u8_type = self._search_regex(
  55             r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
  56         return {
  57             'id': video_id,
  58             'title': video_id,
  59             'formats': formats,
  60             'live_status': {
  61                 'video': 'is_live',
  62                 'dvr': 'was_live',  # short-term archives
  63             }.get(m3u8_type, 'not_live'),  # VOD or long-term archives
  64             '_old_archive_ids': [make_archive_id('PIAULIZAPortal', video_id)],
  65         }
  66
  67
  68 class UlizaPortalIE(InfoExtractor):
  69     IE_DESC = 'ulizaportal.jp'
  70     _VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
  71     _TESTS = [{
  72         'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
  73         'info_dict': {
  74             'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
  75             'display_id': '005f18b7-e810-5618-cb82-0987c5755d44',
  76             'title': 'プレゼンテーションプレイヤーのサンプル',
  77             'live_status': 'not_live',
  78             '_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
  79         },
  80         'params': {
  81             'skip_download': True,
  82             'ignore_no_formats_error': True,
  83         },
  84     }, {
  85         'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
  86         'info_dict': {
  87             'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
  88             'display_id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
  89             'title': '【確認用】視聴サンプルページ（ULIZA）',
  90             'live_status': 'not_live',
  91             '_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
  92         },
  93         'params': {
  94             'skip_download': True,
  95             'ignore_no_formats_error': True,
  96         },
  97     }]
  98
  99     def _real_extract(self, url):
 100         video_id = self._match_id(url)
 101
 102         expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
 103         if expires and expires <= time_seconds():
 104             raise ExtractorError('The link is expired', video_id=video_id, expected=True)
 105
 106         webpage = self._download_webpage(url, video_id)
 107
 108         player_data_url = self._search_regex(
 109             r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
 110             webpage, 'player data url')
 111         return self.url_result(
 112             player_data_url, UlizaPlayerIE, url_transparent=True,
 113             display_id=video_id, video_title=self._html_extract_title(webpage))