From 40bd5c18153afe765caa6726302ee1dd8a9a2ce6 Mon Sep 17 00:00:00 2001 From: Aaron Tan <70739609+aaron-tan@users.noreply.github.com> Date: Thu, 22 Feb 2024 23:54:07 +1100 Subject: [PATCH] [caffeine.tv] Add new extractor (#32514) * Add CaffeineTVIE info extractor to support site caffeine.tv --------- Co-authored-by: dirkf --- youtube_dl/extractor/caffeine.py | 79 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 80 insertions(+) create mode 100644 youtube_dl/extractor/caffeine.py diff --git a/youtube_dl/extractor/caffeine.py b/youtube_dl/extractor/caffeine.py new file mode 100644 index 000000000..bffedb9a7 --- /dev/null +++ b/youtube_dl/extractor/caffeine.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + merge_dicts, + parse_iso8601, + T, + traverse_obj, + txt_or_none, + urljoin, +) + + +class CaffeineTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?caffeine\.tv/[^/]+/video/(?P[0-9a-f-]+)' + _TESTS = [{ + 'url': 'https://www.caffeine.tv/TsuSurf/video/cffc0a00-e73f-11ec-8080-80017d29f26e', + 'info_dict': { + 'id': 'cffc0a00-e73f-11ec-8080-80017d29f26e', + 'ext': 'mp4', + 'title': 'GOOOOD MORNINNNNN #highlights', + 'timestamp': 1654702180, + 'upload_date': '20220608', + 'uploader': 'TsuSurf', + 'duration': 3145, + 'age_limit': 17, + }, + 'params': { + 'format': 'bestvideo', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + json_data = self._download_json( + 'https://api.caffeine.tv/social/public/activity/' + video_id, + video_id) + broadcast_info = traverse_obj(json_data, ('broadcast_info', T(dict))) or {} + title = broadcast_info['broadcast_title'] + video_url = broadcast_info['video_url'] + + ext = determine_ext(video_url) + if ext == 'm3u8': + formats = self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8', + fatal=False) + else: + formats = [{'url': video_url}] + self._sort_formats(formats) + + return merge_dicts({ + 'id': video_id, + 'title': title, + 'formats': formats, + }, traverse_obj(json_data, { + 'uploader': ((None, 'user'), 'username'), + }, get_all=False), traverse_obj(json_data, { + 'like_count': ('like_count', T(int_or_none)), + 'view_count': ('view_count', T(int_or_none)), + 'comment_count': ('comment_count', T(int_or_none)), + 'tags': ('tags', Ellipsis, T(txt_or_none)), + 'is_live': 'is_live', + 'uploader': ('user', 'name'), + }), traverse_obj(broadcast_info, { + 'duration': ('content_duration', T(int_or_none)), + 'timestamp': ('broadcast_start_time', T(parse_iso8601)), + 'thumbnail': ('preview_image_path', T(lambda u: urljoin(url, u))), + 'age_limit': ('content_rating', T(lambda r: r and { + # assume Apple Store ratings [1] + # 1. https://en.wikipedia.org/wiki/Mobile_software_content_rating_system + 'FOUR_PLUS': 0, + 'NINE_PLUS': 9, + 'TWELVE_PLUS': 12, + 'SEVENTEEN_PLUS': 17, + }.get(r, 17))), + })) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b6d0f42f5..29b655c94 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -159,6 +159,7 @@ from .businessinsider import BusinessInsiderIE from .buzzfeed import BuzzFeedIE from .byutv import BYUtvIE from .c56 import C56IE +from .caffeine import CaffeineTVIE from .callin import CallinIE from .camdemy import ( CamdemyIE,