yt_dlp/extractor/parler.py

   1 from .common import InfoExtractor
   2 from .youtube import YoutubeIE
   3 from ..utils import (
   4     clean_html,
   5     format_field,
   6     int_or_none,
   7     strip_or_none,
   8     traverse_obj,
   9     unified_timestamp,
  10     urlencode_postdata,
  11 )
  12
  13
  14 class ParlerIE(InfoExtractor):
  15     IE_DESC = 'Posts on parler.com'
  16     _VALID_URL = r'https://parler\.com/feed/(?P<id>[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
  17     _TESTS = [
  18         {
  19             'url': 'https://parler.com/feed/df79fdba-07cc-48fe-b085-3293897520d7',
  20             'md5': '16e0f447bf186bb3cf64de5bbbf4d22d',
  21             'info_dict': {
  22                 'id': 'df79fdba-07cc-48fe-b085-3293897520d7',
  23                 'ext': 'mp4',
  24                 'thumbnail': 'https://bl-images.parler.com/videos/6ce7cdf3-a27a-4d72-bf9c-d3e17ce39a66/thumbnail.jpeg',
  25                 'title': 'Parler video #df79fdba-07cc-48fe-b085-3293897520d7',
  26                 'description': 'md5:6f220bde2df4a97cbb89ac11f1fd8197',
  27                 'timestamp': 1659744000,
  28                 'upload_date': '20220806',
  29                 'uploader': 'Tulsi Gabbard',
  30                 'uploader_id': 'TulsiGabbard',
  31                 'uploader_url': 'https://parler.com/TulsiGabbard',
  32                 'view_count': int,
  33                 'comment_count': int,
  34                 'repost_count': int,
  35             },
  36         },
  37         {
  38             'url': 'https://parler.com/feed/a7406eb4-91e5-4793-b5e3-ade57a24e287',
  39             'md5': '11687e2f5bb353682cee338d181422ed',
  40             'info_dict': {
  41                 'id': 'a7406eb4-91e5-4793-b5e3-ade57a24e287',
  42                 'ext': 'mp4',
  43                 'thumbnail': 'https://bl-images.parler.com/videos/317827a8-1e48-4cbc-981f-7dd17d4c1183/thumbnail.jpeg',
  44                 'title': 'Parler video #a7406eb4-91e5-4793-b5e3-ade57a24e287',
  45                 'description': 'This man should run for office',
  46                 'timestamp': 1659657600,
  47                 'upload_date': '20220805',
  48                 'uploader': 'Benny Johnson',
  49                 'uploader_id': 'BennyJohnson',
  50                 'uploader_url': 'https://parler.com/BennyJohnson',
  51                 'view_count': int,
  52                 'comment_count': int,
  53                 'repost_count': int,
  54             },
  55         },
  56         {
  57             'url': 'https://parler.com/feed/f23b85c1-6558-470f-b9ff-02c145f28da5',
  58             'md5': 'eaba1ff4a10fe281f5ce74e930ab2cb4',
  59             'info_dict': {
  60                 'id': 'r5vkSaz8PxQ',
  61                 'ext': 'mp4',
  62                 'thumbnail': 'https://i.ytimg.com/vi_webp/r5vkSaz8PxQ/maxresdefault.webp',
  63                 'title': 'Tom MacDonald Names Reaction',
  64                 'description': 'md5:33c21f0d35ae6dc2edf3007d6696baea',
  65                 'upload_date': '20220716',
  66                 'duration': 1267,
  67                 'uploader': 'Mahesh Chookolingo',
  68                 'uploader_id': 'maheshchookolingo',
  69                 'uploader_url': 'http://www.youtube.com/user/maheshchookolingo',
  70                 'channel': 'Mahesh Chookolingo',
  71                 'channel_id': 'UCox6YeMSY1PQInbCtTaZj_w',
  72                 'channel_url': 'https://www.youtube.com/channel/UCox6YeMSY1PQInbCtTaZj_w',
  73                 'categories': ['Entertainment'],
  74                 'tags': list,
  75                 'availability': 'public',
  76                 'live_status': 'not_live',
  77                 'view_count': int,
  78                 'comment_count': int,
  79                 'like_count': int,
  80                 'channel_follower_count': int,
  81                 'age_limit': 0,
  82                 'playable_in_embed': True,
  83             },
  84         },
  85     ]
  86
  87     def _real_extract(self, url):
  88         video_id = self._match_id(url)
  89         data = self._download_json(
  90             'https://parler.com/open-api/ParleyDetailEndpoint.php', video_id,
  91             data=urlencode_postdata({'uuid': video_id}))['data'][0]
  92         primary = data['primary']
  93
  94         embed = self._parse_json(primary.get('V2LINKLONG') or '', video_id, fatal=False)
  95         if embed:
  96             return self.url_result(embed[0], YoutubeIE)
  97
  98         return {
  99             'id': video_id,
 100             'url': traverse_obj(primary, ('video_data', 'videoSrc')),
 101             'thumbnail': traverse_obj(primary, ('video_data', 'thumbnailUrl')),
 102             'title': '',
 103             'description': strip_or_none(clean_html(primary.get('full_body'))) or None,
 104             'timestamp': unified_timestamp(primary.get('date_created')),
 105             'uploader': strip_or_none(primary.get('name')),
 106             'uploader_id': strip_or_none(primary.get('username')),
 107             'uploader_url': format_field(strip_or_none(primary.get('username')), None, 'https://parler.com/%s'),
 108             'view_count': int_or_none(primary.get('view_count')),
 109             'comment_count': int_or_none(traverse_obj(data, ('engagement', 'commentCount'))),
 110             'repost_count': int_or_none(traverse_obj(data, ('engagement', 'echoCount'))),
 111         }