yt_dlp/extractor/koo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     clean_html,
   6     try_get,
   7 )
   8
   9
  10 class KooIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?kooapp\.com/koo/[^/]+/(?P<id>[^/&#$?]+)'
  12     _TESTS = [{  # Test for video in the comments
  13         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/946c4189-bc2d-4524-b95b-43f641e2adde',
  14         'info_dict': {
  15             'id': '946c4189-bc2d-4524-b95b-43f641e2adde',
  16             'ext': 'mp4',
  17             'title': 'test for video in comment',
  18             'description': 'md5:daa77dc214add4da8b6ea7d2226776e7',
  19             'timestamp': 1632215195,
  20             'uploader_id': 'ytdlpTestAccount',
  21             'uploader': 'yt-dlpTestAccount',
  22             'duration': 7000,
  23             'upload_date': '20210921'
  24         },
  25         'params': {'skip_download': True}
  26     }, {  # Test for koo with long title
  27         'url': 'https://www.kooapp.com/koo/laxman_kumarDBFEC/33decbf7-5e1e-4bb8-bfd7-04744a064361',
  28         'info_dict': {
  29             'id': '33decbf7-5e1e-4bb8-bfd7-04744a064361',
  30             'ext': 'mp4',
  31             'title': 'md5:47a71c2337295330c5a19a8af1bbf450',
  32             'description': 'md5:06a6a84e9321499486dab541693d8425',
  33             'timestamp': 1632106884,
  34             'uploader_id': 'laxman_kumarDBFEC',
  35             'uploader': 'Laxman Kumar 🇮🇳',
  36             'duration': 46000,
  37             'upload_date': '20210920'
  38         },
  39         'params': {'skip_download': True}
  40     }, {  # Test for audio
  41         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/a2a9c88e-ce4b-4d2d-952f-d06361c5b602',
  42         'info_dict': {
  43             'id': 'a2a9c88e-ce4b-4d2d-952f-d06361c5b602',
  44             'ext': 'mp4',
  45             'title': 'Test for audio',
  46             'description': 'md5:ecb9a2b6a5d34b736cecb53788cb11e8',
  47             'timestamp': 1632211634,
  48             'uploader_id': 'ytdlpTestAccount',
  49             'uploader': 'yt-dlpTestAccount',
  50             'duration': 214000,
  51             'upload_date': '20210921'
  52         },
  53         'params': {'skip_download': True}
  54     }, {  # Test for video
  55         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/a3e56c53-c1ed-4ac9-ac02-ed1630e6b1d1',
  56         'info_dict': {
  57             'id': 'a3e56c53-c1ed-4ac9-ac02-ed1630e6b1d1',
  58             'ext': 'mp4',
  59             'title': 'Test for video',
  60             'description': 'md5:7afc4eb839074ddeb2beea5dd6fe9500',
  61             'timestamp': 1632211468,
  62             'uploader_id': 'ytdlpTestAccount',
  63             'uploader': 'yt-dlpTestAccount',
  64             'duration': 14000,
  65             'upload_date': '20210921'
  66         },
  67         'params': {'skip_download': True}
  68     }, {  # Test for link
  69         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/01bf5b94-81a5-4d8e-a387-5f732022e15a',
  70         'skip': 'No video/audio found at the provided url.',
  71         'info_dict': {
  72             'id': '01bf5b94-81a5-4d8e-a387-5f732022e15a',
  73             'title': 'Test for link',
  74             'ext': 'none',
  75         },
  76     }, {  # Test for images
  77         'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/dc05d9cd-a61d-45fd-bb07-e8019d8ca8cb',
  78         'skip': 'No video/audio found at the provided url.',
  79         'info_dict': {
  80             'id': 'dc05d9cd-a61d-45fd-bb07-e8019d8ca8cb',
  81             'title': 'Test for images',
  82             'ext': 'none',
  83         },
  84     }]
  85
  86     def _real_extract(self, url):
  87         id = self._match_id(url)
  88         data_json = self._download_json(f'https://www.kooapp.com/apiV1/ku/{id}?limit=20&offset=0&showSimilarKoos=true', 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']) == 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, 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         self._sort_formats(formats)
 107         return {
 108             'id': id,
 109             'title': clean_html(item_json.get('title')),
 110             'description': f'{clean_html(item_json.get("title"))}\n\n{clean_html(item_json.get("enTransliteration"))}',
 111             'timestamp': item_json.get('createdAt'),
 112             'uploader_id': item_json.get('handle'),
 113             'uploader': item_json.get('name'),
 114             'duration': media_json.get('duration'),
 115             'formats': formats,
 116         }