From a109acbf82244e8589e9bb509077c88240fbbb6e Mon Sep 17 00:00:00 2001 From: u-spec-png <54671367+u-spec-png@users.noreply.github.com> Date: Mon, 8 Nov 2021 18:36:01 +0000 Subject: [PATCH] [ZenYandex] Fix extractor (#1558) Closes #1545 Authored by: u-spec-png --- yt_dlp/extractor/yandexvideo.py | 60 ++++++++++++++++++++++++++------- 1 file changed, 47 insertions(+), 13 deletions(-) diff --git a/yt_dlp/extractor/yandexvideo.py b/yt_dlp/extractor/yandexvideo.py index 9974d65d6e..67095f2fd5 100644 --- a/yt_dlp/extractor/yandexvideo.py +++ b/yt_dlp/extractor/yandexvideo.py @@ -7,6 +7,7 @@ import re from .common import InfoExtractor from ..utils import ( determine_ext, + extract_attributes, int_or_none, try_get, url_or_none, @@ -148,7 +149,7 @@ class YandexVideoIE(InfoExtractor): class ZenYandexIE(InfoExtractor): - _VALID_URL = r'https?://zen\.yandex\.ru/media/(?:id/[^/]+/|[^/]+/)(?:[a-z0-9-]+)-(?P[a-z0-9-]+)' + _VALID_URL = r'https?://zen\.yandex\.ru(?:/video)?/(media|watch)/(?:(?:id/[^/]+/|[^/]+/)(?:[a-z0-9-]+)-)?(?P[a-z0-9-]+)' _TESTS = [{ 'url': 'https://zen.yandex.ru/media/popmech/izverjenie-vulkana-iz-spichek-zreliscnyi-opyt-6002240ff8b1af50bb2da5e3', 'info_dict': { @@ -156,19 +157,38 @@ class ZenYandexIE(InfoExtractor): 'ext': 'mp4', 'title': 'Извержение вулкана из спичек: зрелищный опыт', 'description': 'md5:053ad3c61b5596d510c9a199dc8ee633', - 'thumbnail': 'https://avatars.mds.yandex.net/get-zen-pub-og/3558619/pub_6002240ff8b1af50bb2da5e3_600bad814d953e4132a30b5e/orig', + 'thumbnail': 're:^https://avatars.mds.yandex.net/', 'uploader': 'Популярная механика', }, + 'params': { + 'skip_download': 'm3u8', + }, }, { 'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/vot-eto-focus-dedy-morozy-na-gidrociklah-60c7c443da18892ebfe85ed7', 'info_dict': { 'id': '60c7c443da18892ebfe85ed7', 'ext': 'mp4', 'title': 'ВОТ ЭТО Focus. Деды Морозы на гидроциклах', - 'description': 'md5:8684912f6086f298f8078d4af0e8a600', - 'thumbnail': 'https://avatars.mds.yandex.net/get-zen-pub-og/4410519/pub_60c7c443da18892ebfe85ed7_60c7c48e060a163121f42cc3/orig', + 'description': 'md5:f3db3d995763b9bbb7b56d4ccdedea89', + 'thumbnail': 're:^https://avatars.mds.yandex.net/', 'uploader': 'AcademeG DailyStream' }, + 'params': { + 'skip_download': 'm3u8', + 'format': 'bestvideo', + }, + }, { + 'url': 'https://zen.yandex.ru/video/watch/6002240ff8b1af50bb2da5e3', + 'info_dict': { + 'id': '6002240ff8b1af50bb2da5e3', + 'ext': 'mp4', + 'title': 'Извержение вулкана из спичек: зрелищный опыт', + 'description': 'md5:053ad3c61b5596d510c9a199dc8ee633', + 'uploader': 'Популярная механика', + }, + 'params': { + 'skip_download': 'm3u8', + }, }, { 'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/novyi-samsung-fold-3-moskvich-barahlit-612f93b7f8d48e7e945792a2?from=channel&rid=2286618386.482.1630817595976.42360', 'only_matching': True, @@ -177,23 +197,37 @@ class ZenYandexIE(InfoExtractor): def _real_extract(self, url): id = self._match_id(url) webpage = self._download_webpage(url, id) - data_json = self._parse_json(self._search_regex(r'w\._data\s?=\s?({.+?});', webpage, 'metadata'), id) - stream_json = try_get(data_json, lambda x: x['publication']['content']['gifContent'], dict) - stream_url = stream_json.get('stream') or try_get(stream_json, lambda x: x['streams']['url']) - formats = self._extract_m3u8_formats(stream_url, id) + data_json = self._parse_json( + self._search_regex(r'data\s*=\s*({["\']_*serverState_*video.+?});', webpage, 'metadata'), id) + serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)', + webpage, 'server state').replace('State', 'Settings') + uploader = self._search_regex(r'(]+>)', + webpage, 'uploader', default='') + uploader_name = extract_attributes(uploader).get('aria-label') + video_json = try_get(data_json, lambda x: x[serverstate]['exportData']['video'], dict) + stream_urls = try_get(video_json, lambda x: x['video']['streams']) + formats = [] + for s_url in stream_urls: + ext = determine_ext(s_url) + if ext == 'mpd': + formats.extend(self._extract_mpd_formats(s_url, id, mpd_id='dash')) + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats(s_url, id, 'mp4')) self._sort_formats(formats) return { 'id': id, - 'title': try_get(data_json, (lambda x: x['og']['title'], lambda x: x['publication']['content']['preview']['title'])), - 'uploader': data_json.get('authorName') or try_get(data_json, lambda x: x['publisher']['name']), - 'description': try_get(data_json, lambda x: x['og']['description']), - 'thumbnail': try_get(data_json, lambda x: x['og']['imageUrl']), + 'title': video_json.get('title') or self._og_search_title(webpage), 'formats': formats, + 'duration': int_or_none(video_json.get('duration')), + 'view_count': int_or_none(video_json.get('views')), + 'uploader': uploader_name or data_json.get('authorName') or try_get(data_json, lambda x: x['publisher']['name']), + 'description': self._og_search_description(webpage) or try_get(data_json, lambda x: x['og']['description']), + 'thumbnail': self._og_search_thumbnail(webpage) or try_get(data_json, lambda x: x['og']['imageUrl']), } class ZenYandexChannelIE(InfoExtractor): - _VALID_URL = r'https?://zen\.yandex\.ru/(?!media)(?:id/)?(?P[a-z0-9-_]+)' + _VALID_URL = r'https?://zen\.yandex\.ru/(?!media|video)(?:id/)?(?P[a-z0-9-_]+)' _TESTS = [{ 'url': 'https://zen.yandex.ru/tok_media', 'info_dict': {