From c9bd65185c0b3b490d0353e139d5484c93bd9774 Mon Sep 17 00:00:00 2001 From: Alex Karabanov Date: Tue, 25 Oct 2022 14:20:48 +0400 Subject: [PATCH] [extractor/zenyandex] Fix extractors (#3750, #5268) Closes #3736 Authored by: lksj, puc9, pukkandan Co-authored-by: puc9 <51006296+puc9@users.noreply.github.com> --- test/test_download.py | 3 +- yt_dlp/extractor/yandexvideo.py | 171 ++++++++++++++++++++++++-------- 2 files changed, 129 insertions(+), 45 deletions(-) diff --git a/test/test_download.py b/test/test_download.py index ee53efa1c4..7ee8c7c432 100755 --- a/test/test_download.py +++ b/test/test_download.py @@ -122,7 +122,8 @@ def print_skipping(reason): params['outtmpl'] = tname + '_' + params['outtmpl'] if is_playlist and 'playlist' not in test_case: params.setdefault('extract_flat', 'in_playlist') - params.setdefault('playlistend', test_case.get('playlist_mincount')) + params.setdefault('playlistend', test_case.get( + 'playlist_mincount', test_case.get('playlist_count', -2) + 1)) params.setdefault('skip_download', True) ydl = YoutubeDL(params, auto_init=False) diff --git a/yt_dlp/extractor/yandexvideo.py b/yt_dlp/extractor/yandexvideo.py index 0b621dbd25..7932edf335 100644 --- a/yt_dlp/extractor/yandexvideo.py +++ b/yt_dlp/extractor/yandexvideo.py @@ -1,5 +1,4 @@ import itertools -import re from .common import InfoExtractor from ..utils import ( @@ -7,6 +6,8 @@ extract_attributes, int_or_none, lowercase_escape, + parse_qs, + traverse_obj, try_get, url_or_none, ) @@ -23,7 +24,6 @@ class YandexVideoIE(InfoExtractor): ''' _TESTS = [{ 'url': 'https://yandex.ru/portal/video?stream_id=4dbb36ec4e0526d58f9f2dc8f0ecf374', - 'md5': 'e02a05bfaf0d9615ef07ae3a10f4faf4', 'info_dict': { 'id': '4dbb36ec4e0526d58f9f2dc8f0ecf374', 'ext': 'mp4', @@ -38,6 +38,7 @@ class YandexVideoIE(InfoExtractor): 'like_count': int, 'dislike_count': int, }, + 'params': {'skip_download': 'm3u8'}, }, { 'url': 'https://yandex.ru/portal/efir?stream_id=4dbb262b4fe5cf15a215de4f34eee34d&from=morda', 'only_matching': True, @@ -188,34 +189,35 @@ def _real_extract(self, url): class ZenYandexIE(InfoExtractor): - _VALID_URL = r'https?://zen\.yandex\.ru(?:/video)?/(media|watch)/(?:(?:id/[^/]+/|[^/]+/)(?:[a-z0-9-]+)-)?(?P[a-z0-9-]+)' + _VALID_URL = r'https?://(zen\.yandex|dzen)\.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': { - 'id': '6002240ff8b1af50bb2da5e3', - 'ext': 'mp4', - 'title': 'Извержение вулкана из спичек: зрелищный опыт', - 'description': 'md5:053ad3c61b5596d510c9a199dc8ee633', - '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:f3db3d995763b9bbb7b56d4ccdedea89', - 'thumbnail': 're:^https://avatars.mds.yandex.net/', + 'thumbnail': 're:^https://avatars.dzeninfra.ru/', 'uploader': 'AcademeG DailyStream' }, 'params': { 'skip_download': 'm3u8', 'format': 'bestvideo', }, + 'skip': 'The page does not exist', + }, { + 'url': 'https://dzen.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:f3db3d995763b9bbb7b56d4ccdedea89', + 'thumbnail': r're:^https://avatars\.dzeninfra\.ru/', + 'uploader': 'AcademeG DailyStream', + 'upload_date': '20191111', + 'timestamp': 1573465585, + }, + 'params': {'skip_download': 'm3u8'}, }, { 'url': 'https://zen.yandex.ru/video/watch/6002240ff8b1af50bb2da5e3', 'info_dict': { @@ -223,21 +225,42 @@ class ZenYandexIE(InfoExtractor): 'ext': 'mp4', 'title': 'Извержение вулкана из спичек: зрелищный опыт', 'description': 'md5:053ad3c61b5596d510c9a199dc8ee633', - 'uploader': 'Популярная механика', + 'thumbnail': r're:^https://avatars\.dzeninfra\.ru/', + 'uploader': 'TechInsider', + 'timestamp': 1611378221, + 'upload_date': '20210123', }, - 'params': { - 'skip_download': 'm3u8', + 'params': {'skip_download': 'm3u8'}, + }, { + 'url': 'https://dzen.ru/video/watch/6002240ff8b1af50bb2da5e3', + 'info_dict': { + 'id': '6002240ff8b1af50bb2da5e3', + 'ext': 'mp4', + 'title': 'Извержение вулкана из спичек: зрелищный опыт', + 'description': 'md5:053ad3c61b5596d510c9a199dc8ee633', + 'thumbnail': 're:^https://avatars.dzeninfra.ru/', + 'uploader': 'TechInsider', + 'upload_date': '20210123', + 'timestamp': 1611378221, }, + '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, + }, { + 'url': 'https://dzen.ru/media/id/606fd806cc13cb3c58c05cf5/novyi-samsung-fold-3-moskvich-barahlit-612f93b7f8d48e7e945792a2?from=channel&rid=2286618386.482.1630817595976.42360', + 'only_matching': True, }] 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'data\s*=\s*({["\']_*serverState_*video.+?});', webpage, 'metadata'), id) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + redirect = self._search_json(r'var it\s*=\s*', webpage, 'redirect', id, default={}).get('retpath') + if redirect: + video_id = self._match_id(redirect) + webpage = self._download_webpage(redirect, video_id, note='Redirecting') + data_json = self._search_json( + r'data\s*=', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}') serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)', webpage, 'server state').replace('State', 'Settings') uploader = self._search_regex(r'(]+>)', @@ -254,11 +277,12 @@ def _real_extract(self, url): formats.extend(self._extract_m3u8_formats(s_url, id, 'mp4')) self._sort_formats(formats) return { - 'id': id, + 'id': video_id, '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')), + 'timestamp': int_or_none(video_json.get('publicationDate')), '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']), @@ -266,40 +290,99 @@ def _real_extract(self, url): class ZenYandexChannelIE(InfoExtractor): - _VALID_URL = r'https?://zen\.yandex\.ru/(?!media|video)(?:id/)?(?P[a-z0-9-_]+)' + _VALID_URL = r'https?://(zen\.yandex|dzen)\.ru/(?!media|video)(?:id/)?(?P[a-z0-9-_]+)' _TESTS = [{ 'url': 'https://zen.yandex.ru/tok_media', 'info_dict': { 'id': 'tok_media', + 'title': 'СПЕКТР', + 'description': 'md5:a9e5b3c247b7fe29fd21371a428bcf56', + }, + 'playlist_mincount': 169, + }, { + 'url': 'https://dzen.ru/tok_media', + 'info_dict': { + 'id': 'tok_media', + 'title': 'СПЕКТР', + 'description': 'md5:a9e5b3c247b7fe29fd21371a428bcf56', }, 'playlist_mincount': 169, }, { 'url': 'https://zen.yandex.ru/id/606fd806cc13cb3c58c05cf5', 'info_dict': { 'id': '606fd806cc13cb3c58c05cf5', + 'description': 'md5:517b7c97d8ca92e940f5af65448fd928', + 'title': 'AcademeG DailyStream', + }, + 'playlist_mincount': 657, + }, { + # Test that the playlist extractor finishes extracting when the + # channel has less than one page + 'url': 'https://zen.yandex.ru/jony_me', + 'info_dict': { + 'id': 'jony_me', + 'description': 'md5:a2c62b4ef5cf3e3efb13d25f61f739e1', + 'title': 'JONY ', + }, + 'playlist_count': 20, + }, { + # Test that the playlist extractor finishes extracting when the + # channel has more than one page of entries + 'url': 'https://zen.yandex.ru/tatyanareva', + 'info_dict': { + 'id': 'tatyanareva', + 'description': 'md5:296b588d60841c3756c9105f237b70c6', + 'title': 'Татьяна Рева', + 'entries': 'maxcount:200', + }, + 'playlist_count': 46, + }, { + 'url': 'https://dzen.ru/id/606fd806cc13cb3c58c05cf5', + 'info_dict': { + 'id': '606fd806cc13cb3c58c05cf5', + 'title': 'AcademeG DailyStream', + 'description': 'md5:517b7c97d8ca92e940f5af65448fd928', }, 'playlist_mincount': 657, }] - def _entries(self, id, url): - webpage = self._download_webpage(url, id) - data_json = self._parse_json(re.findall(r'var\s?data\s?=\s?({.+?})\s?;', webpage)[-1], id) - for key in data_json.keys(): - if key.startswith('__serverState__'): - data_json = data_json[key] - items = list(try_get(data_json, lambda x: x['feed']['items'], dict).values()) - more = try_get(data_json, lambda x: x['links']['more']) or None + def _entries(self, item_id, server_state_json, server_settings_json): + items = (traverse_obj(server_state_json, ('feed', 'items', ...)) + or traverse_obj(server_settings_json, ('exportData', 'items', ...))) + + more = (traverse_obj(server_state_json, ('links', 'more')) + or traverse_obj(server_settings_json, ('exportData', 'more', 'link'))) + + next_page_id = None for page in itertools.count(1): - for item in items: - video_id = item.get('publication_id') or item.get('publicationId') - video_url = item.get('link') - yield self.url_result(video_url, ie=ZenYandexIE.ie_key(), video_id=video_id.split(':')[-1]) - if not more: + for item in items or []: + if item.get('type') != 'gif': + continue + video_id = traverse_obj(item, 'publication_id', 'publicationId') or '' + yield self.url_result(item['link'], ZenYandexIE, video_id.split(':')[-1]) + + current_page_id = next_page_id + next_page_id = traverse_obj(parse_qs(more), ('next_page_id', -1)) + if not all((more, items, next_page_id, next_page_id != current_page_id)): break - data_json = self._download_json(more, id, note='Downloading Page %d' % page) - items = data_json.get('items', []) - more = try_get(data_json, lambda x: x['more']['link']) or None + + data = self._download_json(more, item_id, note=f'Downloading Page {page}') + items, more = data.get('items'), traverse_obj(data, ('more', 'link')) def _real_extract(self, url): - id = self._match_id(url) - return self.playlist_result(self._entries(id, url), playlist_id=id) + item_id = self._match_id(url) + webpage = self._download_webpage(url, item_id) + redirect = self._search_json( + r'var it\s*=\s*', webpage, 'redirect', item_id, default={}).get('retpath') + if redirect: + item_id = self._match_id(redirect) + webpage = self._download_webpage(redirect, item_id, note='Redirecting') + data = self._search_json( + r'var\s+data\s*=', webpage, 'channel data', item_id, contains_pattern=r'{\"__serverState__.+}') + server_state_json = traverse_obj(data, lambda k, _: k.startswith('__serverState__'), get_all=False) + server_settings_json = traverse_obj(data, lambda k, _: k.startswith('__serverSettings__'), get_all=False) + + return self.playlist_result( + self._entries(item_id, server_state_json, server_settings_json), + item_id, traverse_obj(server_state_json, ('channel', 'source', 'title')), + traverse_obj(server_state_json, ('channel', 'source', 'description')))