From 171b7deda03afe5c41bec6503a87f5a013a86e63 Mon Sep 17 00:00:00 2001 From: Ethan Muir Date: Fri, 27 Oct 2023 01:52:11 -0400 Subject: [PATCH 1/2] Added changes to add nest extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/nest.py | 39 ++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) create mode 100644 youtube_dl/extractor/nest.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d9289e5bf..cd25189c6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -776,6 +776,7 @@ from .ndr import ( from .ndtv import NDTVIE from .netzkino import NetzkinoIE from .nerdcubed import NerdCubedFeedIE +from .nest import NestIE from .neteasemusic import ( NetEaseMusicIE, NetEaseMusicAlbumIE, diff --git a/youtube_dl/extractor/nest.py b/youtube_dl/extractor/nest.py new file mode 100644 index 000000000..f5409a00d --- /dev/null +++ b/youtube_dl/extractor/nest.py @@ -0,0 +1,39 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class NestIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?video.nest\.com/clip/(?P)(.mp4)?' + _TEST = { + 'url': 'https://video.nest.com/clip/73ddb6bd57c4485597a76e154a4429ea.mp4', + 'md5': '7ab4eb6d4c2480be1740cc014a76ee96', + 'info_dict': { + 'id': '73ddb6bd57c4485597a76e154a4429ea', + 'ext': 'mp4', + 'title': "\"\"", + 'description': '#caughtonNestCam', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + video_id = self._search_regex( + r'https:\/\/video.nest.com\/clip\/(.+?)(\.|")', webpage, 'video_id', fatal=False) + title = self._html_search_meta(['og:title', 'title'], webpage, 'title') + if title == "": + title = "\"\"" + description = self._html_search_meta(['og:description', 'description'], webpage, 'description') + ext = self._html_search_meta('og:video:type', webpage, 'ext') + if "/" in ext: + ext = ext[ext.index("/") + 1:] + return { + 'url': self._html_search_meta(['og:video:url', 'url'], webpage, 'url'), + 'id': video_id, + 'title': title, + 'description': description, + 'ext': ext, + 'thumbnail': self._html_search_meta(['og:image', 'image'], webpage, 'thumbnail'), + } \ No newline at end of file From e8eb999df445683af4e13fd672fba8dd340ce2da Mon Sep 17 00:00:00 2001 From: Ethan Muir Date: Fri, 27 Oct 2023 14:42:48 -0400 Subject: [PATCH 2/2] Added extractor for bandlab --- youtube_dl/extractor/bandlab.py | 169 +++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 4 + 2 files changed, 173 insertions(+) create mode 100644 youtube_dl/extractor/bandlab.py diff --git a/youtube_dl/extractor/bandlab.py b/youtube_dl/extractor/bandlab.py new file mode 100644 index 000000000..cb3a5b560 --- /dev/null +++ b/youtube_dl/extractor/bandlab.py @@ -0,0 +1,169 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +from ..compat import ( + compat_str, +) + +from ..utils import ( + strip_or_none, + try_get, + url_or_none, +) + + +class BandlabIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bandlab\.com/post/(?P[^/]+)' + + _TESTS = [{ + 'url': 'https://www.bandlab.com/post/f5f04998635a44ea819cacdba7ae2076_f8d8574c3bdaec11b6562818783151a1', + 'info_dict': { + 'id': 'f5f04998635a44ea819cacdba7ae2076_f8d8574c3bdaec11b6562818783151a1', + 'ext': 'm4a', + 'title': 'ON MY OWN (unreleased)', + 'artist': 'Michael MacDonald', + }, + }] + + def _real_extract(self, url): + track_id = self._match_id(url) + config = self._download_json( + 'http://www.bandlab.com/api/v1.3/posts/%s' % track_id, track_id) + track_url = config['track']['sample']['audioUrl'] + + return { + 'id': track_id, + 'title': config['track']['name'], + 'url': track_url, + 'artist': config['creator']['name'] + } + + +class BandlabAlbumOrPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bandlab\.com/[^/]+/(?Palbums|collections)/(?P[^/]+)' + _TRACK_ID_RE = r'.+/(?P[^/]+)\.m4a' + _TESTS = [{ + 'url': 'https://www.bandlab.com/sbsdasani/albums/dc26e307-e51f-ed11-95d7-002248452390', + 'playlist': [ + { + 'info_dict': { + 'id': '91feeb36-8e10-4c91-ae57-ffac0a98c6b4', + 'title': 'How\'d I Lose You? (Intro)', + 'ext': 'm4a', + }, + }, + { + 'info_dict': { + 'id': 'd87c50a2-70cb-4937-9b97-3ae8646ca3aa', + 'title': 'Money $$$', + 'ext': 'm4a', + }, + }, + { + 'info_dict': { + 'id': 'ff2909ff-348f-448d-9d2c-7edbf2f0ec5e', + 'title': 'You\'ll Be Mine', + 'ext': 'm4a', + }, + }, + { + 'info_dict': { + 'id': '53786c38-1f3c-4921-9271-793a64af7186', + 'title': 'Who You Are', + 'ext': 'm4a', + }, + }, + { + 'info_dict': { + 'id': '0394bb27-113f-4d19-b902-f9c1fe6ba8a8', + 'title': 'In Your Eyes', + 'ext': 'm4a', + }, + }, + { + 'info_dict': { + 'id': '2aa44689-c7fa-4d0e-b28a-e0d1dd570372', + 'title': 'The Same', + 'ext': 'm4a', + }, + }, + { + 'info_dict': { + 'id': '281fe589-a559-4260-802d-78a6c7a973d8', + 'title': 'Fall In Love', + 'ext': 'm4a', + }, + }, + { + 'info_dict': { + 'id': '83a9dc0a-702f-40fd-82f6-ab847f6a7b46', + 'title': 'Tried So Hard', + 'ext': 'm4a', + }, + }, + { + 'info_dict': { + 'id': '3f6a4a1c-eb73-449f-bd45-f7958d6f2de1', + 'title': 'The End Of Everything', + 'ext': 'm4a', + }, + } + ], + 'info_dict': { + 'id': 'dc26e307-e51f-ed11-95d7-002248452390', + 'album': 'ENDLESS SUMMER', + 'artist': 'Michael MacDonald' + }, + }, { + 'url': 'https://www.bandlab.com/hexatetrahedronx/collections/8fb1041c-e865-eb11-9889-0050f28a2802', + 'playlist': [ + { + 'info_dict': { + 'id': '8f37e4aa-92c4-eb11-a7ad-0050f280467f', + 'title': 'psych ward', + 'ext': 'm4a' + } + } + ], + 'info_dict': { + 'id': '8fb1041c-e865-eb11-9889-0050f28a2802', + 'album': 'DOOMTAPE', + 'artist': '12days' + } + }] + + def _real_extract(self, url): + resource_id, kind = re.match(self._VALID_URL, url).group('id', 'kind') + config = self._download_json( + 'http://www.bandlab.com/api/v1.3/%s/%s' % (kind, resource_id), resource_id) + entries = [] + for track in try_get(config, lambda x: x['posts'], list) or []: + url, name = try_get( + track, + (lambda x: (x['track']['sample']['audioUrl'], x['track']['name']), + lambda x: (x['revision']['mixdown']['file'], x['revision']['song']['name'])), + tuple) or (None, '', ) + url = url_or_none(url) + name = strip_or_none(name) + if not (url and name): + continue + track_id = re.match(self._TRACK_ID_RE, url).group('id') + if not track_id: + continue + entries.append({ + 'url': url, + 'id': track_id, + 'title': name, + }) + + return { + '_type': 'playlist', + 'id': resource_id, + 'entries': entries, + 'album': try_get(config, lambda x: x['name'].strip(), compat_str), + 'artist': try_get(config, lambda x: x['creator']['name'].strip(), compat_str) + } \ No newline at end of file diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index cd25189c6..c2d6d7362 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -774,6 +774,10 @@ from .ndr import ( NJoyEmbedIE, ) from .ndtv import NDTVIE +from .bandlab import ( + BandlabIE, + BandlabAlbumOrPlaylistIE +) from .netzkino import NetzkinoIE from .nerdcubed import NerdCubedFeedIE from .nest import NestIE