yt_dlp/extractor/koo.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     try_get,
   5 )
   6
   7
   8 class KooIE(InfoExtractor):
   9     _WORKING = False
  10     _VALID_URL = r'https?://(?:www\.)?kooapp\.com/koo/[^/]+/(?P<id>[^/&#$?]+)'
  11     _TESTS = [{  # Test for video in the comments
  12         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/946c4189-bc2d-4524-b95b-43f641e2adde',
  13         'info_dict': {
  14             'id': '946c4189-bc2d-4524-b95b-43f641e2adde',
  15             'ext': 'mp4',
  16             'title': 'test for video in comment',
  17             'description': 'md5:daa77dc214add4da8b6ea7d2226776e7',
  18             'timestamp': 1632215195,
  19             'uploader_id': 'ytdlpTestAccount',
  20             'uploader': 'yt-dlpTestAccount',
  21             'duration': 7000,
  22             'upload_date': '20210921',
  23         },
  24         'params': {'skip_download': True},
  25     }, {  # Test for koo with long title
  26         'url': 'https://www.kooapp.com/koo/laxman_kumarDBFEC/33decbf7-5e1e-4bb8-bfd7-04744a064361',
  27         'info_dict': {
  28             'id': '33decbf7-5e1e-4bb8-bfd7-04744a064361',
  29             'ext': 'mp4',
  30             'title': 'md5:47a71c2337295330c5a19a8af1bbf450',
  31             'description': 'md5:06a6a84e9321499486dab541693d8425',
  32             'timestamp': 1632106884,
  33             'uploader_id': 'laxman_kumarDBFEC',
  34             'uploader': 'Laxman Kumar 🇮🇳',
  35             'duration': 46000,
  36             'upload_date': '20210920',
  37         },
  38         'params': {'skip_download': True},
  39     }, {  # Test for audio
  40         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/a2a9c88e-ce4b-4d2d-952f-d06361c5b602',
  41         'info_dict': {
  42             'id': 'a2a9c88e-ce4b-4d2d-952f-d06361c5b602',
  43             'ext': 'mp4',
  44             'title': 'Test for audio',
  45             'description': 'md5:ecb9a2b6a5d34b736cecb53788cb11e8',
  46             'timestamp': 1632211634,
  47             'uploader_id': 'ytdlpTestAccount',
  48             'uploader': 'yt-dlpTestAccount',
  49             'duration': 214000,
  50             'upload_date': '20210921',
  51         },
  52         'params': {'skip_download': True},
  53     }, {  # Test for video
  54         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/a3e56c53-c1ed-4ac9-ac02-ed1630e6b1d1',
  55         'info_dict': {
  56             'id': 'a3e56c53-c1ed-4ac9-ac02-ed1630e6b1d1',
  57             'ext': 'mp4',
  58             'title': 'Test for video',
  59             'description': 'md5:7afc4eb839074ddeb2beea5dd6fe9500',
  60             'timestamp': 1632211468,
  61             'uploader_id': 'ytdlpTestAccount',
  62             'uploader': 'yt-dlpTestAccount',
  63             'duration': 14000,
  64             'upload_date': '20210921',
  65         },
  66         'params': {'skip_download': True},
  67     }, {  # Test for link
  68         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/01bf5b94-81a5-4d8e-a387-5f732022e15a',
  69         'skip': 'No video/audio found at the provided url.',
  70         'info_dict': {
  71             'id': '01bf5b94-81a5-4d8e-a387-5f732022e15a',
  72             'title': 'Test for link',
  73             'ext': 'none',
  74         },
  75     }, {  # Test for images
  76         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/dc05d9cd-a61d-45fd-bb07-e8019d8ca8cb',
  77         'skip': 'No video/audio found at the provided url.',
  78         'info_dict': {
  79             'id': 'dc05d9cd-a61d-45fd-bb07-e8019d8ca8cb',
  80             'title': 'Test for images',
  81             'ext': 'none',
  82         },
  83     }]
  84
  85     def _real_extract(self, url):
  86         video_id = self._match_id(url)
  87         data_json = self._download_json(
  88             f'https://www.kooapp.com/apiV1/ku/{video_id}?limit=20&offset=0&showSimilarKoos=true', video_id)['parentContent']
  89         item_json = next(content['items'][0] for content in data_json
  90                          if try_get(content, lambda x: x['items'][0]['id']) == video_id)
  91         media_json = item_json['mediaMap']
  92         formats = []
  93
  94         mp4_url = media_json.get('videoMp4')
  95         video_m3u8_url = media_json.get('videoHls')
  96         if mp4_url:
  97             formats.append({
  98                 'url': mp4_url,
  99                 'ext': 'mp4',
 100             })
 101         if video_m3u8_url:
 102             formats.extend(self._extract_m3u8_formats(video_m3u8_url, video_id, fatal=False, ext='mp4'))
 103         if not formats:
 104             self.raise_no_formats('No video/audio found at the provided url.', expected=True)
 105
 106         return {
 107             'id': video_id,
 108             'title': clean_html(item_json.get('title')),
 109             'description': f'{clean_html(item_json.get("title"))}\n\n{clean_html(item_json.get("enTransliteration"))}',
 110             'timestamp': item_json.get('createdAt'),
 111             'uploader_id': item_json.get('handle'),
 112             'uploader': item_json.get('name'),
 113             'duration': media_json.get('duration'),
 114             'formats': formats,
 115         }