github/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2025-08-23 06:35:51 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Backport update

Browse source
This commit is contained in:
palewire 2022-08-15 12:04:19 -07:00
commit 38e5559877
No known key found for this signature in database
GPG key ID: A5AD4A9AD42D69AB
1 changed files with 12 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

50
youtube_dl/extractor/truth.py
View file

@ -2,19 +2,16 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html, clean_html,
int_or_none, int_or_none,
strip_or_none,
unified_timestamp, unified_timestamp,
strip_or_none
) )
class TruthIE(InfoExtractor): class TruthIE(InfoExtractor):
"""Extract videos from posts on Donald Trump's truthsocial.com.""" _VALID_URL = r'https?://truthsocial\.com/@[^/]+/posts/(?P<id>\d+)'
_VALID_URL = r'https://truthsocial\.com/@[^/]+/posts/(?P<id>[\d]+)'
_TESTS = [ _TESTS = [
{ {
'url': 'https://truthsocial.com/@realDonaldTrump/posts/108779000807761862', 'url': 'https://truthsocial.com/@realDonaldTrump/posts/108779000807761862',
@ -22,7 +19,8 @@ class TruthIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '108779000807761862', 'id': '108779000807761862',
'ext': 'qt', 'ext': 'qt',
'title': 'Donald J. Trump - 0d8691160c73d663', 'title': 'Truth video #108779000807761862',
'description': None,
'timestamp': 1659835827, 'timestamp': 1659835827,
'upload_date': '20220807', 'upload_date': '20220807',
'uploader': 'Donald J. Trump', 'uploader': 'Donald J. Trump',
@ -39,7 +37,7 @@ class TruthIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '108618228543962049', 'id': '108618228543962049',
'ext': 'mp4', 'ext': 'mp4',
'title': 'md5:48813a16498d21b07edf24e1af621e83', 'title': 'md5:debde7186cf83f60ff7b44dbb9444e35',
'description': 'md5:e070ba6bcf6165957e26a7a94ef6d975', 'description': 'md5:e070ba6bcf6165957e26a7a94ef6d975',
'timestamp': 1657382637, 'timestamp': 1657382637,
'upload_date': '20220709', '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): def _real_extract(self, url):
# Get data from API
video_id = self._match_id(url) video_id = self._match_id(url)
status = self._download_json( status = self._download_json(f'https://truthsocial.com/api/v1/statuses/{video_id}', video_id)
'https://truthsocial.com/api/v1/statuses/' + video_id, uploader_id = strip_or_none(status['account']['username'])
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)
return { return {
'id': video_id, 'id': video_id,
'url': url, 'url': status['media_attachments'][0]['url'],
'title': title, 'title': 'Truth video #%s' % video_id,
'description': post, 'description': strip_or_none(clean_html(status.get('content'))) or None,
'timestamp': unified_timestamp(status.get('created_at')), 'timestamp': unified_timestamp(status.get('created_at')),
'uploader': uploader, 'uploader': strip_or_none(status['account']['display_name']),
'uploader_id': uploader_id, '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')), 'repost_count': int_or_none(status.get('reblogs_count')),
'like_count': int_or_none(status.get('favourites_count')), 'like_count': int_or_none(status.get('favourites_count')),
'comment_count': int_or_none(status.get('replies_count')), 'comment_count': int_or_none(status.get('replies_count')),