From 7e378287c4502d82aedb5272b8e9d5f6c1681fad Mon Sep 17 00:00:00 2001 From: HobbyistDev <105957301+HobbyistDev@users.noreply.github.com> Date: Sat, 1 Oct 2022 01:40:33 +0900 Subject: [PATCH] [extractor/malltv] Fix video_id extraction (#4883) Closes #4870 Authored by: HobbyistDev --- yt_dlp/extractor/malltv.py | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) diff --git a/yt_dlp/extractor/malltv.py b/yt_dlp/extractor/malltv.py index bfd6008b3..02f226be5 100644 --- a/yt_dlp/extractor/malltv.py +++ b/yt_dlp/extractor/malltv.py @@ -14,7 +14,7 @@ class MallTVIE(InfoExtractor): _VALID_URL = r'https?://(?:(?:www|sk)\.)?mall\.tv/(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', - 'md5': '1c4a37f080e1f3023103a7b43458e518', + 'md5': 'cd69ce29176f6533b65bff69ed9a5f2a', 'info_dict': { 'id': 't0zzt0', 'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', @@ -25,6 +25,11 @@ class MallTVIE(InfoExtractor): 'timestamp': 1538870400, 'upload_date': '20181007', 'view_count': int, + 'comment_count': int, + 'thumbnail': 'https://cdn.vpplayer.tech/agmipnzv/encode/vjsnigfq/thumbnails/retina.jpg', + 'average_rating': 9.060869565217391, + 'dislike_count': int, + 'like_count': int, } }, { 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', @@ -32,6 +37,24 @@ class MallTVIE(InfoExtractor): }, { 'url': 'https://sk.mall.tv/gejmhaus/reklamacia-nehreje-vyrobnik-tepla-alebo-spekacka', 'only_matching': True, + }, { + 'url': 'https://www.mall.tv/zivoty-slavnych/nadeje-vychodu-i-zapadu-jak-michail-gorbacov-zmenil-politickou-mapu-sveta-a-ziskal-za-to-nobelovu-cenu-miru', + 'info_dict': { + 'id': 'yx010y', + 'ext': 'mp4', + 'dislike_count': int, + 'description': 'md5:aee02bee5a8d072c6a8207b91d1905a9', + 'thumbnail': 'https://cdn.vpplayer.tech/agmipnzv/encode/vjsnjdeu/thumbnails/retina.jpg', + 'comment_count': int, + 'display_id': 'md5:0ec2afa94d2e2b7091c019cef2a43a9b', + 'like_count': int, + 'duration': 752, + 'timestamp': 1646956800, + 'title': 'md5:fe79385daaf16d74c12c1ec4a26687af', + 'view_count': int, + 'upload_date': '20220311', + 'average_rating': 9.685714285714285, + } }] def _real_extract(self, url): @@ -43,12 +66,12 @@ class MallTVIE(InfoExtractor): video = self._parse_json(self._search_regex( r'videoObject\s*=\s*JSON\.parse\(JSON\.stringify\(({.+?})\)\);', webpage, 'video object'), display_id) - video_source = video['VideoSource'] + video_id = self._search_regex( - r'/([\da-z]+)/index\b', video_source, 'video id') + r']+value\s*=\s*(\w+)', webpage, 'video id') formats = self._extract_m3u8_formats( - video_source + '.m3u8', video_id, 'mp4', 'm3u8_native') + video['VideoSource'], video_id, 'mp4', 'm3u8_native') self._sort_formats(formats) subtitles = {} @@ -69,7 +92,7 @@ class MallTVIE(InfoExtractor): info = self._search_json_ld(webpage, video_id, default={}) return merge_dicts({ - 'id': video_id, + 'id': str(video_id), 'display_id': display_id, 'title': video.get('Title'), 'description': clean_html(video.get('Description')),