yt_dlp/extractor/ustudio.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     unified_strdate,
   5     unescapeHTML,
   6 )
   7
   8
   9 class UstudioIE(InfoExtractor):
  10     IE_NAME = 'ustudio'
  11     _VALID_URL = r'https?://(?:(?:www|v1)\.)?ustudio\.com/video/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
  12     _TEST = {
  13         'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge',
  14         'md5': '58bbfca62125378742df01fc2abbdef6',
  15         'info_dict': {
  16             'id': 'Uxu2my9bgSph',
  17             'display_id': 'san_francisco_golden_gate_bridge',
  18             'ext': 'mp4',
  19             'title': 'San Francisco: Golden Gate Bridge',
  20             'description': 'md5:23925500697f2c6d4830e387ba51a9be',
  21             'thumbnail': r're:^https?://.*\.jpg$',
  22             'upload_date': '20111107',
  23             'uploader': 'Tony Farley',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id, display_id = self._match_valid_url(url).groups()
  29
  30         config = self._download_xml(
  31             'http://v1.ustudio.com/embed/%s/ustudio/config.xml' % video_id,
  32             display_id)
  33
  34         def extract(kind):
  35             return [{
  36                 'url': unescapeHTML(item.attrib['url']),
  37                 'width': int_or_none(item.get('width')),
  38                 'height': int_or_none(item.get('height')),
  39             } for item in config.findall('./qualities/quality/%s' % kind) if item.get('url')]
  40
  41         formats = extract('video')
  42         self._sort_formats(formats)
  43
  44         webpage = self._download_webpage(url, display_id)
  45
  46         title = self._og_search_title(webpage)
  47         upload_date = unified_strdate(self._search_regex(
  48             r'(?s)Uploaded by\s*.+?\s*on\s*<span>([^<]+)</span>',
  49             webpage, 'upload date', fatal=False))
  50         uploader = self._search_regex(
  51             r'Uploaded by\s*<a[^>]*>([^<]+)<',
  52             webpage, 'uploader', fatal=False)
  53
  54         return {
  55             'id': video_id,
  56             'display_id': display_id,
  57             'title': title,
  58             'description': self._og_search_description(webpage),
  59             'thumbnails': extract('image'),
  60             'upload_date': upload_date,
  61             'uploader': uploader,
  62             'formats': formats,
  63         }
  64
  65
  66 class UstudioEmbedIE(InfoExtractor):
  67     IE_NAME = 'ustudio:embed'
  68     _VALID_URL = r'https?://(?:(?:app|embed)\.)?ustudio\.com/embed/(?P<uid>[^/]+)/(?P<id>[^/]+)'
  69     _TEST = {
  70         'url': 'http://app.ustudio.com/embed/DeN7VdYRDKhP/Uw7G1kMCe65T',
  71         'md5': '47c0be52a09b23a7f40de9469cec58f4',
  72         'info_dict': {
  73             'id': 'Uw7G1kMCe65T',
  74             'ext': 'mp4',
  75             'title': '5 Things IT Should Know About Video',
  76             'description': 'md5:93d32650884b500115e158c5677d25ad',
  77             'uploader_id': 'DeN7VdYRDKhP',
  78         }
  79     }
  80
  81     def _real_extract(self, url):
  82         uploader_id, video_id = self._match_valid_url(url).groups()
  83         video_data = self._download_json(
  84             'http://app.ustudio.com/embed/%s/%s/config.json' % (uploader_id, video_id),
  85             video_id)['videos'][0]
  86         title = video_data['name']
  87
  88         formats = []
  89         for ext, qualities in video_data.get('transcodes', {}).items():
  90             for quality in qualities:
  91                 quality_url = quality.get('url')
  92                 if not quality_url:
  93                     continue
  94                 height = int_or_none(quality.get('height'))
  95                 formats.append({
  96                     'format_id': '%s-%dp' % (ext, height) if height else ext,
  97                     'url': quality_url,
  98                     'width': int_or_none(quality.get('width')),
  99                     'height': height,
 100                 })
 101         self._sort_formats(formats)
 102
 103         thumbnails = []
 104         for image in video_data.get('images', []):
 105             image_url = image.get('url')
 106             if not image_url:
 107                 continue
 108             thumbnails.append({
 109                 'url': image_url,
 110             })
 111
 112         return {
 113             'id': video_id,
 114             'title': title,
 115             'description': video_data.get('description'),
 116             'duration': int_or_none(video_data.get('duration')),
 117             'uploader_id': uploader_id,
 118             'tags': video_data.get('keywords'),
 119             'thumbnails': thumbnails,
 120             'formats': formats,
 121         }