etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-22 02:15:12 +00:00
Code Issues Projects Releases Wiki Activity

[extractor/tempo] Add extractor (#4463)

Browse source 
Authored by: HobbyistDev
This commit is contained in:
HobbyistDev 2022-07-27 20:48:42 +09:00 committed by GitHub
parent 964b5493a4
commit 67685a541d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 54 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
yt_dlp/extractor/_extractors.py
View file

@ -1727,6 +1727,7 @@
)
from .teletask import TeleTaskIE
from .telewebion import TelewebionIE
from .tempo import TempoIE
from .tennistv import TennisTVIE
from .tenplay import TenPlayIE
from .testurl import TestURLIE

53
yt_dlp/extractor/tempo.py Normal file
View file

@ -0,0 +1,53 @@
from .common import InfoExtractor
from ..utils import int_or_none, parse_iso8601, str_or_none, traverse_obj
class TempoIE(InfoExtractor):
_VALID_URL = r'https?://video\.tempo\.co/\w+/\d+/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://video.tempo.co/read/30058/anies-baswedan-ajukan-banding-putusan-ptun-batalkan-ump-dki',
'info_dict': {
'id': '2144438',
'ext': 'mp4',
'title': 'Anies Baswedan Ajukan Banding Putusan PTUN Batalkan UMP DKI',
'display_id': 'anies-baswedan-ajukan-banding-putusan-ptun-batalkan-ump-dki',
'duration': 84,
'description': 'md5:a6822b7c4c874fa7e5bd63e96a387b66',
'thumbnail': 'https://statik.tempo.co/data/2022/07/27/id_1128287/1128287_720.jpg',
'timestamp': 1658911277,
'upload_date': '20220727',
'tags': ['Anies Baswedan', ' PTUN', ' PTUN | Pengadilan Tata Usaha Negara', ' PTUN Batalkan UMP DKI', ' UMP DKI'],
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_key, widget_id = self._search_regex(
r'<ivs-player\s*[^>]+data-ivs-key\s*=\s*"(?P<player_key>[\w]+)[^>]+\bdata-ivs-wid="(?P<widget_id>[\w-]+)',
webpage, 'player_key, widget_id', group=('player_key', 'widget_id'))
json_ld_data = self._search_json_ld(webpage, display_id)
json_data = self._download_json(
f'https://ivxplayer.ivideosmart.com/prod/widget/{widget_id}',
display_id, query={'key': player_key})
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
json_data['player']['video_url'], display_id, ext='mp4')
return {
'id': str(json_data['ivx']['id']),
'display_id': display_id,
'formats': formats,
'subtitles': subtitles,
'title': (self._html_search_meta('twitter:title', webpage) or self._og_search_title(webpage)
or traverse_obj(json_data, ('ivx', 'name'))),
'duration': int_or_none(traverse_obj(json_data, ('ivx', 'duration'))),
'thumbnail': (self._html_search_meta('twitter:image:src', webpage) or self._og_search_thumbnail(webpage)
or traverse_obj(json_data, ('ivx', 'thumbnail_url'))),
'description': (json_ld_data.get('description') or self._html_search_meta(['description', 'twitter:description'], webpage)
or self._og_search_description(webpage)),
'timestamp': parse_iso8601(traverse_obj(json_data, ('ivx', 'created_at'))),
'tags': str_or_none(self._html_search_meta('keywords', webpage), '').split(','),
}