From 054a3ba7d1293f9fbe21800d62d1e5ddcbded238 Mon Sep 17 00:00:00 2001 From: Dong Heon Hee Date: Mon, 1 Jul 2024 07:00:33 +0900 Subject: [PATCH] [ie/afreecatv:catchstory] Add extractor (#10235) Closes #10112 Authored by: hui1601 --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/afreecatv.py | 39 ++++++++++++++++++++++++++++++++- 2 files changed, 39 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index c411efb5a..62a9c9864 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -76,6 +76,7 @@ ) from .aeonco import AeonCoIE from .afreecatv import ( + AfreecaTVCatchStoryIE, AfreecaTVIE, AfreecaTVLiveIE, AfreecaTVUserIE, diff --git a/yt_dlp/extractor/afreecatv.py b/yt_dlp/extractor/afreecatv.py index 7e628396f..f51b5a68b 100644 --- a/yt_dlp/extractor/afreecatv.py +++ b/yt_dlp/extractor/afreecatv.py @@ -72,7 +72,7 @@ class AfreecaTVIE(AfreecaTVBaseIE): )\?.*?\bnTitleNo=| vod\.afreecatv\.com/(PLAYER/STATION|player)/ ) - (?P\d+) + (?P\d+)/?(?:$|[?#&]) ''' _TESTS = [{ 'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=', @@ -253,6 +253,43 @@ def _real_extract(self, url): return self.playlist_result(entries, video_id, multi_video=True, **common_info) +class AfreecaTVCatchStoryIE(AfreecaTVBaseIE): + IE_NAME = 'afreecatv:catchstory' + IE_DESC = 'afreecatv.com catch story' + _VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P\d+)/catchstory' + _TESTS = [{ + 'url': 'https://vod.afreecatv.com/player/103247/catchstory', + 'info_dict': { + 'id': '103247', + }, + 'playlist_count': 2, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + data = self._download_json( + 'https://api.m.afreecatv.com/catchstory/a/view', video_id, headers={'Referer': url}, + query={'aStoryListIdx': '', 'nStoryIdx': video_id}, impersonate=True) + + return self.playlist_result(self._entries(data), video_id) + + @staticmethod + def _entries(data): + # 'files' is always a list with 1 element + yield from traverse_obj(data, ( + 'data', lambda _, v: v['story_type'] == 'catch', + 'catch_list', lambda _, v: v['files'][0]['file'], { + 'id': ('files', 0, 'file_info_key', {str}), + 'url': ('files', 0, 'file', {url_or_none}), + 'duration': ('files', 0, 'duration', {functools.partial(int_or_none, scale=1000)}), + 'title': ('title', {str}), + 'uploader': ('writer_nick', {str}), + 'uploader_id': ('writer_id', {str}), + 'thumbnail': ('thumb', {url_or_none}), + 'timestamp': ('write_timestamp', {int_or_none}), + })) + + class AfreecaTVLiveIE(AfreecaTVBaseIE): IE_NAME = 'afreecatv:live' IE_DESC = 'afreecatv.com livestreams'