yt_dlp/extractor/startv.py

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