[extractor/truth] Add extractor (#4609)

Closes #3865
Authored by: palewire
This commit is contained in:
Ben Welsh 2022-08-14 13:06:04 -07:00 committed by GitHub
parent 63be30e3e0
commit cb7cc448c0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 70 additions and 0 deletions

View File

@ -1794,6 +1794,7 @@
) )
from .trueid import TrueIDIE from .trueid import TrueIDIE
from .trunews import TruNewsIE from .trunews import TruNewsIE
from .truth import TruthIE
from .trutv import TruTVIE from .trutv import TruTVIE
from .tube8 import Tube8IE from .tube8 import Tube8IE
from .tubetugraz import TubeTuGrazIE, TubeTuGrazSeriesIE from .tubetugraz import TubeTuGrazIE, TubeTuGrazSeriesIE

69
yt_dlp/extractor/truth.py Normal file
View File

@ -0,0 +1,69 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
format_field,
int_or_none,
strip_or_none,
traverse_obj,
unified_timestamp,
)
class TruthIE(InfoExtractor):
_VALID_URL = r'https?://truthsocial\.com/@[^/]+/posts/(?P<id>\d+)'
_TESTS = [
{
'url': 'https://truthsocial.com/@realDonaldTrump/posts/108779000807761862',
'md5': '4a5fb1470c192e493d9efd6f19e514d3',
'info_dict': {
'id': '108779000807761862',
'ext': 'qt',
'title': 'Truth video #108779000807761862',
'description': None,
'timestamp': 1659835827,
'upload_date': '20220807',
'uploader': 'Donald J. Trump',
'uploader_id': 'realDonaldTrump',
'uploader_url': 'https://truthsocial.com/@realDonaldTrump',
'repost_count': int,
'comment_count': int,
'like_count': int,
},
},
{
'url': 'https://truthsocial.com/@ProjectVeritasAction/posts/108618228543962049',
'md5': 'fd47ba68933f9dce27accc52275be9c3',
'info_dict': {
'id': '108618228543962049',
'ext': 'mp4',
'title': 'md5:debde7186cf83f60ff7b44dbb9444e35',
'description': 'md5:de2fc49045bf92bb8dc97e56503b150f',
'timestamp': 1657382637,
'upload_date': '20220709',
'uploader': 'Project Veritas Action',
'uploader_id': 'ProjectVeritasAction',
'uploader_url': 'https://truthsocial.com/@ProjectVeritasAction',
'repost_count': int,
'comment_count': int,
'like_count': int,
},
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
status = self._download_json(f'https://truthsocial.com/api/v1/statuses/{video_id}', video_id)
uploader_id = strip_or_none(traverse_obj(status, ('account', 'username')))
return {
'id': video_id,
'url': status['media_attachments'][0]['url'],
'title': '',
'description': strip_or_none(clean_html(status.get('content'))) or None,
'timestamp': unified_timestamp(status.get('created_at')),
'uploader': strip_or_none(traverse_obj(status, ('account', 'display_name'))),
'uploader_id': uploader_id,
'uploader_url': format_field(uploader_id, None, 'https://truthsocial.com/@%s'),
'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')),
}