yt_dlp/extractor/utreon.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     dict_get,
   4     int_or_none,
   5     str_or_none,
   6     try_get,
   7     unified_strdate,
   8     url_or_none,
   9 )
  10
  11
  12 class UtreonIE(InfoExtractor):
  13     IE_NAME = 'playeur'
  14     _VALID_URL = r'https?://(?:www\.)?(?:utreon|playeur)\.com/v/(?P<id>[\w-]+)'
  15     _TESTS = [{
  16         'url': 'https://utreon.com/v/z_I7ikQbuDw',
  17         'info_dict': {
  18             'id': 'z_I7ikQbuDw',
  19             'ext': 'mp4',
  20             'title': 'Freedom Friday meditation - Rising in the wind',
  21             'description': 'md5:a9bf15a42434a062fe313b938343ad1b',
  22             'uploader': 'Heather Dawn Elemental Health',
  23             'thumbnail': r're:^https?://.+\.jpg',
  24             'release_date': '20210723',
  25             'duration': 586,
  26         },
  27     }, {
  28         'url': 'https://utreon.com/v/jerJw5EOOVU',
  29         'info_dict': {
  30             'id': 'jerJw5EOOVU',
  31             'ext': 'mp4',
  32             'title': 'When I\'m alone, I love to reflect in peace, to make my dreams come true... [Quotes and Poems]',
  33             'description': 'md5:4026aa3a2c10169c3649926ac8ef62b6',
  34             'uploader': 'Frases e Poemas Quotes and Poems',
  35             'thumbnail': r're:^https?://.+\.jpg',
  36             'release_date': '20210723',
  37             'duration': 60,
  38         },
  39     }, {
  40         'url': 'https://utreon.com/v/C4ZxXhYBBmE',
  41         'info_dict': {
  42             'id': 'C4ZxXhYBBmE',
  43             'ext': 'mp4',
  44             'title': 'Biden’s Capital Gains Tax Rate to Test World’s Highest',
  45             'description': 'md5:995aa9ad0733c0e5863ebdeff954f40e',
  46             'uploader': 'Nomad Capitalist',
  47             'thumbnail': r're:^https?://.+\.jpg',
  48             'release_date': '20210723',
  49             'duration': 884,
  50         },
  51     }, {
  52         'url': 'https://utreon.com/v/Y-stEH-FBm8',
  53         'info_dict': {
  54             'id': 'Y-stEH-FBm8',
  55             'ext': 'mp4',
  56             'title': 'Creeper-Chan Pranks Steve! 💚 [MINECRAFT ANIME]',
  57             'description': 'md5:7a48450b0d761b96dec194be0c5ecb5f',
  58             'uploader': 'Merryweather Comics',
  59             'thumbnail': r're:^https?://.+\.jpg',
  60             'release_date': '20210718',
  61             'duration': 151,
  62         },
  63     }, {
  64         'url': 'https://playeur.com/v/Wzqp-UrxSeu',
  65         'info_dict': {
  66             'id': 'Wzqp-UrxSeu',
  67             'ext': 'mp4',
  68             'title': 'Update: Clockwork Basilisk Books on the Way!',
  69             'description': 'md5:d9756b0b1884c904655b0e170d17cea5',
  70             'uploader': 'Forgotten Weapons',
  71             'release_date': '20240208',
  72             'thumbnail': r're:^https?://.+\.jpg',
  73             'duration': 262,
  74         },
  75     }]
  76
  77     def _real_extract(self, url):
  78         video_id = self._match_id(url)
  79         json_data = self._download_json(
  80             'https://api.playeur.com/v1/videos/' + video_id,
  81             video_id)
  82         videos_json = json_data['videos']
  83         formats = [{
  84             'url': format_url,
  85             'format_id': format_key.split('_')[1],
  86             'height': int(format_key.split('_')[1][:-1]),
  87         } for format_key, format_url in videos_json.items() if url_or_none(format_url)]
  88         thumbnail = url_or_none(dict_get(json_data, ('cover_image_url', 'preview_image_url')))
  89         return {
  90             'id': video_id,
  91             'title': json_data['title'],
  92             'formats': formats,
  93             'description': str_or_none(json_data.get('description')),
  94             'duration': int_or_none(json_data.get('duration')),
  95             'uploader': str_or_none(try_get(json_data, lambda x: x['channel']['title'])),
  96             'thumbnail': thumbnail,
  97             'release_date': unified_strdate(json_data.get('published_datetime')),
  98         }