From b4760c778d0c92c6e3f2bc8346cd72c8f08595ae Mon Sep 17 00:00:00 2001 From: Deukhoofd <10423862+Deukhoofd@users.noreply.github.com> Date: Sat, 14 Sep 2024 00:50:15 +0200 Subject: [PATCH] [ie/beacon] Add extractor (#9901) Authored by: Deukhoofd --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/beacon.py | 68 +++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) create mode 100644 yt_dlp/extractor/beacon.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index e7b162512..4302076f0 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -217,6 +217,7 @@ BBCCoUkIPlayerGroupIE, BBCCoUkPlaylistIE, ) +from .beacon import BeaconTvIE from .beatbump import ( BeatBumpPlaylistIE, BeatBumpVideoIE, diff --git a/yt_dlp/extractor/beacon.py b/yt_dlp/extractor/beacon.py new file mode 100644 index 000000000..ae47687cc --- /dev/null +++ b/yt_dlp/extractor/beacon.py @@ -0,0 +1,68 @@ +import json + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, + traverse_obj, +) + + +class BeaconTvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?beacon\.tv/content/(?P[\w-]+)' + + _TESTS = [{ + 'url': 'https://beacon.tv/content/welcome-to-beacon', + 'md5': 'b3f5932d437f288e662f10f3bfc5bd04', + 'info_dict': { + 'id': 'welcome-to-beacon', + 'ext': 'mp4', + 'upload_date': '20240509', + 'description': 'md5:ea2bd32e71acf3f9fca6937412cc3563', + 'thumbnail': 'https://cdn.jwplayer.com/v2/media/I4CkkEvN/poster.jpg?width=720', + 'title': 'Your home for Critical Role!', + 'timestamp': 1715227200, + 'duration': 105.494, + }, + }, { + 'url': 'https://beacon.tv/content/re-slayers-take-trailer', + 'md5': 'd879b091485dbed2245094c8152afd89', + 'info_dict': { + 'id': 're-slayers-take-trailer', + 'ext': 'mp4', + 'title': 'The Re-Slayer’s Take | Official Trailer', + 'timestamp': 1715189040, + 'upload_date': '20240508', + 'duration': 53.249, + 'thumbnail': 'https://cdn.jwplayer.com/v2/media/PW5ApIw3/poster.jpg?width=720', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + content_data = traverse_obj(self._search_nextjs_data(webpage, video_id), ( + 'props', 'pageProps', '__APOLLO_STATE__', + lambda k, v: k.startswith('Content:') and v['slug'] == video_id, any)) + if not content_data: + raise ExtractorError('Failed to extract content data') + + jwplayer_data = traverse_obj(content_data, ( + (('contentVideo', 'video', 'videoData'), + ('contentPodcast', 'podcast', 'audioData')), {json.loads}, {dict}, any)) + if not jwplayer_data: + if content_data.get('contentType') not in ('videoPodcast', 'video', 'podcast'): + raise ExtractorError('Content is not a video/podcast', expected=True) + if traverse_obj(content_data, ('contentTier', '__ref')) != 'MemberTier:65b258d178f89be87b4dc0a4': + self.raise_login_required('This video/podcast is for members only') + raise ExtractorError('Failed to extract content') + + return { + **self._parse_jwplayer_data(jwplayer_data, video_id), + **traverse_obj(content_data, { + 'title': ('title', {str}), + 'description': ('description', {str}), + 'timestamp': ('publishedAt', {parse_iso8601}), + }), + }