Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/stv.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 (
   8     compat_parse_qs,
   9     compat_urllib_parse_urlparse
  10 )
  11 from ..utils import (
  12     extract_attributes,
  13     float_or_none,
  14     int_or_none,
  15     str_or_none,
  16 )
  17
  18
  19 class STVPlayerIE(InfoExtractor):
  20     IE_NAME = 'stv:player'
  21     _VALID_URL = r'https?://player\.stv\.tv/(?P<type>episode|video)/(?P<id>[a-z0-9]{4})'
  22     _TEST = {
  23         'url': 'https://player.stv.tv/video/7srz/victoria/interview-with-the-cast-ahead-of-new-victoria/',
  24         'md5': '2ad867d4afd641fa14187596e0fbc91b',
  25         'info_dict': {
  26             'id': '6016487034001',
  27             'ext': 'mp4',
  28             'upload_date': '20190321',
  29             'title': 'Interview with the cast ahead of new Victoria',
  30             'description': 'Nell Hudson and Lily Travers tell us what to expect in the new season of Victoria.',
  31             'timestamp': 1553179628,
  32             'uploader_id': '1486976045',
  33         },
  34         'skip': 'this resource is unavailable outside of the UK',
  35     }
  36     _PUBLISHER_ID = '1486976045'
  37     _PTYPE_MAP = {
  38         'episode': 'episodes',
  39         'video': 'shortform',
  40     }
  41
  42     def _real_extract(self, url):
  43         ptype, video_id = re.match(self._VALID_URL, url).groups()
  44         webpage = self._download_webpage(url, video_id)
  45
  46         qs = compat_parse_qs(compat_urllib_parse_urlparse(self._search_regex(
  47             r'itemprop="embedURL"[^>]+href="([^"]+)',
  48             webpage, 'embed URL', default=None)).query)
  49         publisher_id = qs.get('publisherID', [None])[0] or self._PUBLISHER_ID
  50
  51         player_attr = extract_attributes(self._search_regex(
  52             r'(<[^>]+class="bcplayer"[^>]+>)', webpage, 'player', default=None)) or {}
  53
  54         info = {}
  55         duration = ref_id = series = video_id = None
  56         api_ref_id = player_attr.get('data-player-api-refid')
  57         if api_ref_id:
  58             resp = self._download_json(
  59                 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], api_ref_id),
  60                 api_ref_id, fatal=False)
  61             if resp:
  62                 result = resp.get('results') or {}
  63                 video = result.get('video') or {}
  64                 video_id = str_or_none(video.get('id'))
  65                 ref_id = video.get('guid')
  66                 duration = video.get('length')
  67                 programme = result.get('programme') or {}
  68                 series = programme.get('name') or programme.get('shortName')
  69                 subtitles = {}
  70                 _subtitles = result.get('_subtitles') or {}
  71                 for ext, sub_url in _subtitles.items():
  72                     subtitles.setdefault('en', []).append({
  73                         'ext': 'vtt' if ext == 'webvtt' else ext,
  74                         'url': sub_url,
  75                     })
  76                 info.update({
  77                     'description': result.get('summary'),
  78                     'subtitles': subtitles,
  79                     'view_count': int_or_none(result.get('views')),
  80                 })
  81         if not video_id:
  82             video_id = qs.get('videoId', [None])[0] or self._search_regex(
  83                 r'<link\s+itemprop="url"\s+href="(\d+)"',
  84                 webpage, 'video id', default=None) or 'ref:' + (ref_id or player_attr['data-refid'])
  85
  86         info.update({
  87             '_type': 'url_transparent',
  88             'duration': float_or_none(duration or player_attr.get('data-duration'), 1000),
  89             'id': video_id,
  90             'ie_key': 'BrightcoveNew',
  91             'series': series or player_attr.get('data-programme-name'),
  92             'url': 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id),
  93         })
  94         return info