From 38e5559877e3342d5795d6a4e22e356a91cc1463 Mon Sep 17 00:00:00 2001 From: palewire Date: Mon, 15 Aug 2022 12:04:19 -0700 Subject: [PATCH] Backport update --- youtube_dl/extractor/truth.py | 50 +++++++++-------------------------- 1 file changed, 12 insertions(+), 38 deletions(-) diff --git a/youtube_dl/extractor/truth.py b/youtube_dl/extractor/truth.py index 1d8a671a2..cde353c76 100644 --- a/youtube_dl/extractor/truth.py +++ b/youtube_dl/extractor/truth.py @@ -2,19 +2,16 @@ from __future__ import unicode_literals from .common import InfoExtractor - from ..utils import ( clean_html, int_or_none, + strip_or_none, unified_timestamp, - strip_or_none ) class TruthIE(InfoExtractor): - """Extract videos from posts on Donald Trump's truthsocial.com.""" - - _VALID_URL = r'https://truthsocial\.com/@[^/]+/posts/(?P[\d]+)' + _VALID_URL = r'https?://truthsocial\.com/@[^/]+/posts/(?P\d+)' _TESTS = [ { 'url': 'https://truthsocial.com/@realDonaldTrump/posts/108779000807761862', @@ -22,7 +19,8 @@ class TruthIE(InfoExtractor): 'info_dict': { 'id': '108779000807761862', 'ext': 'qt', - 'title': 'Donald J. Trump - 0d8691160c73d663', + 'title': 'Truth video #108779000807761862', + 'description': None, 'timestamp': 1659835827, 'upload_date': '20220807', 'uploader': 'Donald J. Trump', @@ -39,7 +37,7 @@ class TruthIE(InfoExtractor): 'info_dict': { 'id': '108618228543962049', 'ext': 'mp4', - 'title': 'md5:48813a16498d21b07edf24e1af621e83', + 'title': 'md5:debde7186cf83f60ff7b44dbb9444e35', 'description': 'md5:e070ba6bcf6165957e26a7a94ef6d975', 'timestamp': 1657382637, 'upload_date': '20220709', @@ -52,44 +50,20 @@ class TruthIE(InfoExtractor): }, }, ] - _GEO_COUNTRIES = ['US'] # The site is only available in the US def _real_extract(self, url): - # Get data from API video_id = self._match_id(url) - status = self._download_json( - 'https://truthsocial.com/api/v1/statuses/' + video_id, - video_id - ) - - # Pull out video - url = status['media_attachments'][0]['url'] - - # Return the stuff - account = status.get('account') or {} - uploader = strip_or_none(account.get('display_name')) - uploader_id = strip_or_none(account.get('username')) - post = strip_or_none(clean_html(status.get('content'))) - - # Set the title, handling case where its too long or empty - if len(post) > 40: - title = post[:35] + "[...]" - elif len(post) == 0: - title = self._generic_title(url) - else: - title = post - if uploader: - title = '%s - %s' % (uploader, title) - + status = self._download_json(f'https://truthsocial.com/api/v1/statuses/{video_id}', video_id) + uploader_id = strip_or_none(status['account']['username']) return { 'id': video_id, - 'url': url, - 'title': title, - 'description': post, + 'url': status['media_attachments'][0]['url'], + 'title': 'Truth video #%s' % video_id, + 'description': strip_or_none(clean_html(status.get('content'))) or None, 'timestamp': unified_timestamp(status.get('created_at')), - 'uploader': uploader, + 'uploader': strip_or_none(status['account']['display_name']), 'uploader_id': uploader_id, - 'uploader_url': ('https://truthsocial.com/@' + uploader_id) if uploader_id else None, + 'uploader_url': 'https://truthsocial.com/@%s' % uploader_id, 'repost_count': int_or_none(status.get('reblogs_count')), 'like_count': int_or_none(status.get('favourites_count')), 'comment_count': int_or_none(status.get('replies_count')),