From 48b813748d91acc7e9efc15075079a03faea18ee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 10 Sep 2017 18:39:13 +0700 Subject: [PATCH] [rutube] Rework and generalize playlist extractors (closes #13565) --- youtube_dl/extractor/rutube.py | 216 ++++++++++++++++----------------- 1 file changed, 108 insertions(+), 108 deletions(-) diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index a6b17c0ef..5a184879f 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -12,34 +12,60 @@ ) from ..utils import ( determine_ext, - unified_strdate, + unified_timestamp, try_get, int_or_none, ) -class RutubeIE(InfoExtractor): +class RutubeBaseIE(InfoExtractor): + def _extract_video(self, video, video_id=None, require_title=True): + title = video['title'] if require_title else video.get('title') + + age_limit = video.get('is_adult') + if age_limit is not None: + age_limit = 18 if age_limit is True else 0 + + uploader_id = try_get(video, lambda x: x['author']['id']) + category = try_get(video, lambda x: x['category']['name']) + + return { + 'id': video.get('id') or video_id, + 'title': title, + 'description': video.get('description'), + 'thumbnail': video.get('thumbnail_url'), + 'duration': int_or_none(video.get('duration')), + 'uploader': try_get(video, lambda x: x['author']['name']), + 'uploader_id': compat_str(uploader_id) if uploader_id else None, + 'timestamp': unified_timestamp(video.get('created_ts')), + 'category': [category] if category else None, + 'age_limit': age_limit, + 'view_count': int_or_none(video.get('hits')), + 'comment_count': int_or_none(video.get('comments_count')), + 'is_live': video.get('is_livestream'), + } + + +class RutubeIE(RutubeBaseIE): IE_NAME = 'rutube' IE_DESC = 'Rutube videos' _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P[\da-z]{32})' _TESTS = [{ 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', + 'md5': '79938ade01294ef7e27574890d0d3769', 'info_dict': { 'id': '3eac3b4561676c17df9132a9a1e62e3e', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Раненный кенгуру забежал в аптеку', 'description': 'http://www.ntdtv.ru ', 'duration': 80, 'uploader': 'NTDRussian', 'uploader_id': '29790', + 'timestamp': 1381943602, 'upload_date': '20131016', 'age_limit': 0, }, - 'params': { - # It requires ffmpeg (m3u8 download) - 'skip_download': True, - }, }, { 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661', 'only_matching': True, @@ -49,20 +75,14 @@ class RutubeIE(InfoExtractor): }, { 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252', 'only_matching': True, + }, { + 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source', + 'only_matching': True, }] @classmethod def suitable(cls, url): - parts = compat_urllib_parse_urlparse(url) - params = compat_parse_qs(parts.query) - - # see if URL without parameters is OK - res = super(RutubeIE, cls).suitable(url) - - if params: # we only allow pl_id parameter in the url - res = res and 'pl_id' in params and len(params) == 1 - - return res + return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url) @staticmethod def _extract_urls(webpage): @@ -72,12 +92,12 @@ def _extract_urls(webpage): def _real_extract(self, url): video_id = self._match_id(url) + video = self._download_json( 'http://rutube.ru/api/video/%s/?format=json' % video_id, video_id, 'Downloading video JSON') - # Some videos don't have the author field - author = video.get('author') or {} + info = self._extract_video(video, video_id) options = self._download_json( 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, @@ -99,19 +119,8 @@ def _real_extract(self, url): }) self._sort_formats(formats) - return { - 'id': video['id'], - 'title': video['title'], - 'description': video['description'], - 'duration': video['duration'], - 'view_count': video['hits'], - 'formats': formats, - 'thumbnail': video['thumbnail_url'], - 'uploader': author.get('name'), - 'uploader_id': compat_str(author['id']) if author else None, - 'upload_date': unified_strdate(video['created_ts']), - 'age_limit': 18 if video['is_adult'] else 0, - } + info['formats'] = formats + return info class RutubeEmbedIE(InfoExtractor): @@ -123,7 +132,8 @@ class RutubeEmbedIE(InfoExtractor): 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', 'info_dict': { 'id': 'a10e53b86e8f349080f718582ce4c661', - 'ext': 'mp4', + 'ext': 'flv', + 'timestamp': 1387830582, 'upload_date': '20131223', 'uploader_id': '297833', 'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix

восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89', @@ -131,7 +141,7 @@ class RutubeEmbedIE(InfoExtractor): 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89', }, 'params': { - 'skip_download': 'Requires ffmpeg', + 'skip_download': True, }, }, { 'url': 'http://rutube.ru/play/embed/8083783', @@ -145,10 +155,51 @@ def _real_extract(self, url): canonical_url = self._html_search_regex( r'\d+)' @@ -162,27 +213,8 @@ class RutubeChannelIE(InfoExtractor): _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json' - def _extract_videos(self, channel_id, channel_title=None): - entries = [] - for pagenum in itertools.count(1): - page = self._download_json( - self._PAGE_TEMPLATE % (channel_id, pagenum), - channel_id, 'Downloading page %s' % pagenum) - results = page['results'] - if not results: - break - entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results) - if not page['has_next']: - break - return self.playlist_result(entries, channel_id, channel_title) - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') - return self._extract_videos(channel_id) - - -class RutubeMovieIE(RutubeChannelIE): +class RutubeMovieIE(RutubePlaylistBaseIE): IE_NAME = 'rutube:movie' IE_DESC = 'Rutube movies' _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P\d+)' @@ -196,11 +228,11 @@ def _real_extract(self, url): movie = self._download_json( self._MOVIE_TEMPLATE % movie_id, movie_id, 'Downloading movie JSON') - movie_name = movie['name'] - return self._extract_videos(movie_id, movie_name) + return self._extract_playlist( + movie_id, playlist_name=movie.get('name')) -class RutubePersonIE(RutubeChannelIE): +class RutubePersonIE(RutubePlaylistBaseIE): IE_NAME = 'rutube:person' IE_DESC = 'Rutube person videos' _VALID_URL = r'https?://rutube\.ru/video/person/(?P\d+)' @@ -215,65 +247,33 @@ class RutubePersonIE(RutubeChannelIE): _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json' -class RutubePlaylistIE(InfoExtractor): +class RutubePlaylistIE(RutubePlaylistBaseIE): IE_NAME = 'rutube:playlist' IE_DESC = 'Rutube playlists' + _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P\d+)' _TESTS = [{ - 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source', + 'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag', 'info_dict': { - 'id': '4252', + 'id': '3097', }, - 'playlist_count': 25, + 'playlist_count': 27, + }, { + 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source', + 'only_matching': True, }] - _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?(?:.+)?pl_id=(?P\d+)' - _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/source/%s/?page=%s' + _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json' @staticmethod def suitable(url): params = compat_parse_qs(compat_urllib_parse_urlparse(url).query) - return params.get('pl_id') and int_or_none(params['pl_id'][0]) \ - and params.get('pl_type') + return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0]) + + def _next_page_url(self, page_num, playlist_id, item_kind): + return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num) def _real_extract(self, url): - playlist_id = self._match_id(url) - return self._extract_playlist(playlist_id) - - def _extract_playlist(self, playlist_id): - entries = [] - for pagenum in itertools.count(1): - page_url = self._PAGE_TEMPLATE % (playlist_id, pagenum) - - # download_json will sent an accept: application/xml header - page = self._download_json(page_url, playlist_id, - "Downloading metadata for page %s" % pagenum, - headers={'Accept': 'application/json'}) - - if not page['results']: - break - - results = page['results'] - for result in results: - entry = self.url_result(result.get('video_url'), 'Rutube') - category = try_get(result, lambda x: x['category']['name']) - entry.update({ - 'id': result.get('id'), - 'uploader': try_get(result, lambda x: x['author']['name']), - 'uploader_id': try_get(result, lambda x: x['author']['id']), - 'upload_date': unified_strdate(result.get('created_ts')), - 'title': result.get('title'), - 'description': result.get('description'), - 'thumbnail': result.get('thumbnail_url'), - 'duration': int_or_none(result.get('duration')), - 'category': [category] if category else None, - 'age_limit': 18 if result.get('is_adult') else 0, - 'view_count': int_or_none(result.get('hits')), - 'is_live': result.get('is_livestream'), - 'webpage_url': result.get('video_url'), - }) - entries.append(entry) - - if page['has_next'] is False: - break - - return self.playlist_result(entries, playlist_id, page['name']) + qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + playlist_kind = qs['pl_type'][0] + playlist_id = qs['pl_id'][0] + return self._extract_playlist(playlist_id, item_kind=playlist_kind)