From 65cfa2b057d7946fbe322155a778fe206556d0c6 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 20 Jul 2023 09:15:21 -0500 Subject: [PATCH] [ie/MuseAI] Add extractor (#7614) Closes #7543 Authored by: bashonly --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/museai.py | 112 ++++++++++++++++++++++++++++++++ 2 files changed, 113 insertions(+) create mode 100644 yt_dlp/extractor/museai.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index bcd8dbe00..ae73a9f96 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1142,6 +1142,7 @@ from .mtv import ( ) from .muenchentv import MuenchenTVIE from .murrtube import MurrtubeIE, MurrtubeUserIE +from .museai import MuseAIIE from .musescore import MuseScoreIE from .musicdex import ( MusicdexSongIE, diff --git a/yt_dlp/extractor/museai.py b/yt_dlp/extractor/museai.py new file mode 100644 index 000000000..7f66928c7 --- /dev/null +++ b/yt_dlp/extractor/museai.py @@ -0,0 +1,112 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + determine_ext, + float_or_none, + int_or_none, + js_to_json, + traverse_obj, + url_or_none, +) + + +class MuseAIIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?muse\.ai/(?:v|embed)/(?P\w+)' + _TESTS = [{ + 'url': 'https://muse.ai/embed/YdTWvUW', + 'md5': 'f994f9a38be1c3aaf9e37cbd7d76fe7c', + 'info_dict': { + 'id': 'YdTWvUW', + 'ext': 'mp4', + 'title': '2023-05-28-Grabien-1941111 (1)', + 'description': '', + 'uploader': 'Today News Africa', + 'uploader_id': 'TodayNewsAfrica', + 'upload_date': '20230528', + 'timestamp': 1685285044, + 'duration': 1291.3, + 'view_count': int, + 'availability': 'public', + }, + }, { + 'url': 'https://muse.ai/v/gQ4gGAA-0756', + 'md5': '52dbfc78e865e56dc19a1715badc35e8', + 'info_dict': { + 'id': 'gQ4gGAA', + 'ext': 'mp4', + 'title': '0756', + 'description': 'md5:0ca1483f9aac423e9a96ad00bb3a0785', + 'uploader': 'Aerial.ie', + 'uploader_id': 'aerial', + 'upload_date': '20210306', + 'timestamp': 1615072842, + 'duration': 21.4, + 'view_count': int, + 'availability': 'public', + }, + }] + _WEBPAGE_TESTS = [{ + 'url': 'https://muse.ai/docs', + 'playlist_mincount': 4, + 'info_dict': { + 'id': 'docs', + 'title': 'muse.ai | docs', + 'description': 'md5:6c0293431481582739c82ee8902687fa', + 'age_limit': 0, + 'thumbnail': 'https://muse.ai/static/imgs/poster-img-docs.png', + }, + 'params': {'allowed_extractors': ['all', '-html5']}, + }] + _EMBED_REGEX = [r']*\bsrc=["\'](?Phttps://muse\.ai/embed/\w+)'] + + @classmethod + def _extract_embed_urls(cls, url, webpage): + yield from super()._extract_embed_urls(url, webpage) + for embed_id in re.findall(r'