From 67685a541d647947d410d37ec312494ec6874de6 Mon Sep 17 00:00:00 2001 From: HobbyistDev <105957301+HobbyistDev@users.noreply.github.com> Date: Wed, 27 Jul 2022 20:48:42 +0900 Subject: [PATCH] [extractor/tempo] Add extractor (#4463) Authored by: HobbyistDev --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/tempo.py | 53 +++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+) create mode 100644 yt_dlp/extractor/tempo.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 5bd6a71bd..590e0114f 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -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 diff --git a/yt_dlp/extractor/tempo.py b/yt_dlp/extractor/tempo.py new file mode 100644 index 000000000..1cfb956e5 --- /dev/null +++ b/yt_dlp/extractor/tempo.py @@ -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[\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']+data-ivs-key\s*=\s*"(?P[\w]+)[^>]+\bdata-ivs-wid="(?P[\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(','), + }