yt_dlp/extractor/startv.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_str,
   4 )
   5 from ..utils import (
   6     ExtractorError,
   7     clean_html,
   8     int_or_none,
   9     traverse_obj,
  10 )
  11
  12
  13 class StarTVIE(InfoExtractor):
  14     _VALID_URL = r"""(?x)
  15         https?://(?:www\.)?startv\.com\.tr/
  16         (?:
  17             (?:dizi|program)/(?:[^/?#&]+)/(?:bolumler|fragmanlar|ekstralar)|
  18             video/arsiv/(?:dizi|program)/(?:[^/?#&]+)
  19         )/
  20         (?P<id>[^/?#&]+)
  21     """
  22     IE_NAME = 'startv'
  23     _TESTS = [
  24         {
  25             'url': 'https://www.startv.com.tr/dizi/cocuk/bolumler/3-bolum',
  26             'md5': '72381a32bcc2e2eb5841e8c8bf68f127',
  27             'info_dict': {
  28                 'id': '904972',
  29                 'display_id': '3-bolum',
  30                 'ext': 'mp4',
  31                 'title': '3. Bölüm',
  32                 'description': 'md5:3a8049f05a75c2e8747116a673275de4',
  33                 'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
  34                 'timestamp': 1569281400,
  35                 'upload_date': '20190923'
  36             },
  37         },
  38         {
  39             'url': 'https://www.startv.com.tr/video/arsiv/dizi/avlu/44-bolum',
  40             'only_matching': True
  41         },
  42         {
  43             'url': 'https://www.startv.com.tr/dizi/cocuk/fragmanlar/5-bolum-fragmani',
  44             'only_matching': True
  45         },
  46         {
  47             'url': 'https://www.startv.com.tr/dizi/cocuk/ekstralar/5-bolumun-nefes-kesen-final-sahnesi',
  48             'only_matching': True
  49         },
  50         {
  51             'url': 'https://www.startv.com.tr/program/burcu-ile-haftasonu/bolumler/1-bolum',
  52             'only_matching': True
  53         },
  54         {
  55             'url': 'https://www.startv.com.tr/program/burcu-ile-haftasonu/fragmanlar/2-fragman',
  56             'only_matching': True
  57         },
  58         {
  59             'url': 'https://www.startv.com.tr/video/arsiv/program/buyukrisk/14-bolumde-hangi-unlu-ne-sordu-',
  60             'only_matching': True
  61         },
  62         {
  63             'url': 'https://www.startv.com.tr/video/arsiv/program/buyukrisk/buyuk-risk-334-bolum',
  64             'only_matching': True
  65         },
  66         {
  67             'url': 'https://www.startv.com.tr/video/arsiv/program/dada/dada-58-bolum',
  68             'only_matching': True
  69         }
  70     ]
  71
  72     def _real_extract(self, url):
  73         display_id = self._match_id(url)
  74         webpage = self._download_webpage(url, display_id)
  75         info_url = self._search_regex(
  76             r'(["\'])videoUrl\1\s*:\s*\1(?P<url>(?:(?!\1).)+)\1\s*',
  77             webpage, 'video info url', group='url')
  78
  79         info = traverse_obj(self._download_json(info_url, display_id), 'data', expected_type=dict)
  80         if not info:
  81             raise ExtractorError('Failed to extract API data')
  82
  83         video_id = compat_str(info.get('id'))
  84         title = info.get('title') or self._og_search_title(webpage)
  85         description = clean_html(info.get('description')) or self._og_search_description(webpage, default=None)
  86         thumbnail = self._proto_relative_url(
  87             self._og_search_thumbnail(webpage), scheme='http:')
  88
  89         formats = self._extract_m3u8_formats(
  90             traverse_obj(info, ('flavors', 'hls')), video_id, entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
  91
  92         return {
  93             'id': video_id,
  94             'display_id': display_id,
  95             'title': title,
  96             'description': description,
  97             'thumbnail': thumbnail,
  98             'timestamp': int_or_none(info.get('release_date')),
  99             'formats': formats
 100         }