yt_dlp/extractor/truth.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     format_field,
   5     int_or_none,
   6     strip_or_none,
   7     traverse_obj,
   8     unified_timestamp,
   9 )
  10
  11
  12 class TruthIE(InfoExtractor):
  13     _VALID_URL = r'https?://truthsocial\.com/@[^/]+/posts/(?P<id>\d+)'
  14     _TESTS = [
  15         {
  16             'url': 'https://truthsocial.com/@realDonaldTrump/posts/108779000807761862',
  17             'md5': '4a5fb1470c192e493d9efd6f19e514d3',
  18             'info_dict': {
  19                 'id': '108779000807761862',
  20                 'ext': 'qt',
  21                 'title': 'Truth video #108779000807761862',
  22                 'timestamp': 1659835827,
  23                 'upload_date': '20220807',
  24                 'uploader': 'Donald J. Trump',
  25                 'uploader_id': 'realDonaldTrump',
  26                 'uploader_url': 'https://truthsocial.com/@realDonaldTrump',
  27                 'repost_count': int,
  28                 'comment_count': int,
  29                 'like_count': int,
  30             },
  31         },
  32         {
  33             'url': 'https://truthsocial.com/@ProjectVeritasAction/posts/108618228543962049',
  34             'md5': 'fd47ba68933f9dce27accc52275be9c3',
  35             'info_dict': {
  36                 'id': '108618228543962049',
  37                 'ext': 'mp4',
  38                 'title': 'md5:debde7186cf83f60ff7b44dbb9444e35',
  39                 'description': 'md5:de2fc49045bf92bb8dc97e56503b150f',
  40                 'timestamp': 1657382637,
  41                 'upload_date': '20220709',
  42                 'uploader': 'Project Veritas Action',
  43                 'uploader_id': 'ProjectVeritasAction',
  44                 'uploader_url': 'https://truthsocial.com/@ProjectVeritasAction',
  45                 'repost_count': int,
  46                 'comment_count': int,
  47                 'like_count': int,
  48             },
  49         },
  50     ]
  51
  52     def _real_extract(self, url):
  53         video_id = self._match_id(url)
  54         status = self._download_json(f'https://truthsocial.com/api/v1/statuses/{video_id}', video_id)
  55         uploader_id = strip_or_none(traverse_obj(status, ('account', 'username')))
  56         return {
  57             'id': video_id,
  58             'url': status['media_attachments'][0]['url'],
  59             'title': '',
  60             'description': strip_or_none(clean_html(status.get('content'))) or None,
  61             'timestamp': unified_timestamp(status.get('created_at')),
  62             'uploader': strip_or_none(traverse_obj(status, ('account', 'display_name'))),
  63             'uploader_id': uploader_id,
  64             'uploader_url': format_field(uploader_id, None, 'https://truthsocial.com/@%s'),
  65             'repost_count': int_or_none(status.get('reblogs_count')),
  66             'like_count': int_or_none(status.get('favourites_count')),
  67             'comment_count': int_or_none(status.get('replies_count')),
  68         }