yt_dlp/extractor/videopress.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     float_or_none,
   5     int_or_none,
   6     parse_age_limit,
   7     qualities,
   8     random_birthday,
   9     unified_timestamp,
  10     urljoin,
  11 )
  12
  13
  14 class VideoPressIE(InfoExtractor):
  15     _ID_REGEX = r'[\da-zA-Z]{8}'
  16     _PATH_REGEX = r'video(?:\.word)?press\.com/embed/'
  17     _VALID_URL = rf'https?://{_PATH_REGEX}(?P<id>{_ID_REGEX})'
  18     _EMBED_REGEX = [rf'<iframe[^>]+src=["\'](?P<url>(?:https?://)?{_PATH_REGEX}{_ID_REGEX})']
  19     _TESTS = [{
  20         'url': 'https://videopress.com/embed/kUJmAcSf',
  21         'md5': '706956a6c875873d51010921310e4bc6',
  22         'info_dict': {
  23             'id': 'kUJmAcSf',
  24             'ext': 'mp4',
  25             'title': 'VideoPress Demo',
  26             'thumbnail': r're:^https?://.*\.jpg',
  27             'duration': 634.6,
  28             'timestamp': 1434983935,
  29             'upload_date': '20150622',
  30             'age_limit': 0,
  31         },
  32     }, {
  33         # 17+, requires birth_* params
  34         'url': 'https://videopress.com/embed/iH3gstfZ',
  35         'only_matching': True,
  36     }, {
  37         'url': 'https://video.wordpress.com/embed/kUJmAcSf',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43
  44         query = random_birthday('birth_year', 'birth_month', 'birth_day')
  45         query['fields'] = 'description,duration,file_url_base,files,height,original,poster,rating,title,upload_date,width'
  46         video = self._download_json(
  47             f'https://public-api.wordpress.com/rest/v1.1/videos/{video_id}',
  48             video_id, query=query)
  49
  50         title = video['title']
  51
  52         file_url_base = video.get('file_url_base') or {}
  53         base_url = file_url_base.get('https') or file_url_base.get('http')
  54
  55         QUALITIES = ('std', 'dvd', 'hd')
  56         quality = qualities(QUALITIES)
  57
  58         formats = []
  59         for format_id, f in (video.get('files') or {}).items():
  60             if not isinstance(f, dict):
  61                 continue
  62             for ext, path in f.items():
  63                 if ext in ('mp4', 'ogg'):
  64                     formats.append({
  65                         'url': urljoin(base_url, path),
  66                         'format_id': f'{format_id}-{ext}',
  67                         'ext': determine_ext(path, ext),
  68                         'quality': quality(format_id),
  69                     })
  70         original_url = video.get('original')
  71         if original_url:
  72             formats.append({
  73                 'url': original_url,
  74                 'format_id': 'original',
  75                 'quality': len(QUALITIES),
  76                 'width': int_or_none(video.get('width')),
  77                 'height': int_or_none(video.get('height')),
  78             })
  79
  80         return {
  81             'id': video_id,
  82             'title': title,
  83             'description': video.get('description'),
  84             'thumbnail': video.get('poster'),
  85             'duration': float_or_none(video.get('duration'), 1000),
  86             'timestamp': unified_timestamp(video.get('upload_date')),
  87             'age_limit': parse_age_limit(video.get('rating')),
  88             'formats': formats,
  89         }