yt_dlp/extractor/videopress.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     determine_ext,
   6     float_or_none,
   7     int_or_none,
   8     parse_age_limit,
   9     qualities,
  10     random_birthday,
  11     unified_timestamp,
  12     urljoin,
  13 )
  14
  15
  16 class VideoPressIE(InfoExtractor):
  17     _ID_REGEX = r'[\da-zA-Z]{8}'
  18     _PATH_REGEX = r'video(?:\.word)?press\.com/embed/'
  19     _VALID_URL = r'https?://%s(?P<id>%s)' % (_PATH_REGEX, _ID_REGEX)
  20     _TESTS = [{
  21         'url': 'https://videopress.com/embed/kUJmAcSf',
  22         'md5': '706956a6c875873d51010921310e4bc6',
  23         'info_dict': {
  24             'id': 'kUJmAcSf',
  25             'ext': 'mp4',
  26             'title': 'VideoPress Demo',
  27             'thumbnail': r're:^https?://.*\.jpg',
  28             'duration': 634.6,
  29             'timestamp': 1434983935,
  30             'upload_date': '20150622',
  31             'age_limit': 0,
  32         },
  33     }, {
  34         # 17+, requires birth_* params
  35         'url': 'https://videopress.com/embed/iH3gstfZ',
  36         'only_matching': True,
  37     }, {
  38         'url': 'https://video.wordpress.com/embed/kUJmAcSf',
  39         'only_matching': True,
  40     }]
  41
  42     @staticmethod
  43     def _extract_urls(webpage):
  44         return re.findall(
  45             r'<iframe[^>]+src=["\']((?:https?://)?%s%s)' % (VideoPressIE._PATH_REGEX, VideoPressIE._ID_REGEX),
  46             webpage)
  47
  48     def _real_extract(self, url):
  49         video_id = self._match_id(url)
  50
  51         query = random_birthday('birth_year', 'birth_month', 'birth_day')
  52         query['fields'] = 'description,duration,file_url_base,files,height,original,poster,rating,title,upload_date,width'
  53         video = self._download_json(
  54             'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
  55             video_id, query=query)
  56
  57         title = video['title']
  58
  59         file_url_base = video.get('file_url_base') or {}
  60         base_url = file_url_base.get('https') or file_url_base.get('http')
  61
  62         QUALITIES = ('std', 'dvd', 'hd')
  63         quality = qualities(QUALITIES)
  64
  65         formats = []
  66         for format_id, f in (video.get('files') or {}).items():
  67             if not isinstance(f, dict):
  68                 continue
  69             for ext, path in f.items():
  70                 if ext in ('mp4', 'ogg'):
  71                     formats.append({
  72                         'url': urljoin(base_url, path),
  73                         'format_id': '%s-%s' % (format_id, ext),
  74                         'ext': determine_ext(path, ext),
  75                         'quality': quality(format_id),
  76                     })
  77         original_url = video.get('original')
  78         if original_url:
  79             formats.append({
  80                 'url': original_url,
  81                 'format_id': 'original',
  82                 'quality': len(QUALITIES),
  83                 'width': int_or_none(video.get('width')),
  84                 'height': int_or_none(video.get('height')),
  85             })
  86         self._sort_formats(formats)
  87
  88         return {
  89             'id': video_id,
  90             'title': title,
  91             'description': video.get('description'),
  92             'thumbnail': video.get('poster'),
  93             'duration': float_or_none(video.get('duration'), 1000),
  94             'timestamp': unified_timestamp(video.get('upload_date')),
  95             'age_limit': parse_age_limit(video.get('rating')),
  96             'formats': formats,
  97         }