X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a070911bf98c751e4425008f1335cc57c86d30fc..8c72ec3993d7183e9c1fcd2cab445a3196ad8723:/youtube_dl/extractor/rutube.py diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 5b1c357..8f54d56 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -1,4 +1,4 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re @@ -7,79 +7,155 @@ import itertools from .common import InfoExtractor from ..compat import ( compat_str, + compat_parse_qs, + compat_urllib_parse_urlparse, ) from ..utils import ( - ExtractorError, - unified_strdate, + determine_ext, + bool_or_none, + int_or_none, + try_get, + unified_timestamp, + url_or_none, ) -class RutubeIE(InfoExtractor): +class RutubeBaseIE(InfoExtractor): + def _download_api_info(self, video_id, query=None): + if not query: + query = {} + query['format'] = 'json' + return self._download_json( + 'http://rutube.ru/api/video/%s/' % video_id, + video_id, 'Downloading video JSON', + 'Unable to download video JSON', query=query) + + @staticmethod + def _extract_info(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 if video_id else 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': bool_or_none(video.get('is_livestream')), + } + + def _download_and_extract_info(self, video_id, query=None): + return self._extract_info( + self._download_api_info(video_id, query=query), video_id) + + def _download_api_options(self, video_id, query=None): + if not query: + query = {} + query['format'] = 'json' + return self._download_json( + 'http://rutube.ru/api/play/options/%s/' % video_id, + video_id, 'Downloading options JSON', + 'Unable to download options JSON', + headers=self.geo_verification_headers(), query=query) + + def _extract_formats(self, options, video_id): + formats = [] + for format_id, format_url in options['video_balancer'].items(): + ext = determine_ext(format_url) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + format_url, video_id, f4m_id=format_id, fatal=False)) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + }) + self._sort_formats(formats) + return formats + + def _download_and_extract_formats(self, video_id, query=None): + return self._extract_formats( + self._download_api_options(video_id, query=query), video_id) + + +class RutubeIE(RutubeBaseIE): IE_NAME = 'rutube' IE_DESC = 'Rutube videos' - _VALID_URL = r'https?://rutube\.ru/video/(?P[\da-z]{32})' + _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P[\da-z]{32})' - _TEST = { + _TESTS = [{ 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', + 'md5': '1d24f180fac7a02f3900712e5a5764d6', 'info_dict': { 'id': '3eac3b4561676c17df9132a9a1e62e3e', 'ext': 'mp4', 'title': 'Раненный кенгуру забежал в аптеку', 'description': 'http://www.ntdtv.ru ', - 'duration': 80, + 'duration': 81, 'uploader': 'NTDRussian', 'uploader_id': '29790', + 'timestamp': 1381943602, 'upload_date': '20131016', + 'age_limit': 0, }, - 'params': { - # It requires ffmpeg (m3u8 download) - 'skip_download': True, - }, - } - - 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 {} + }, { + 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661', + 'only_matching': True, + }, { + 'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661', + 'only_matching': True, + }, { + 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252', + 'only_matching': True, + }, { + 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source', + 'only_matching': True, + }] - options = self._download_json( - 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, - video_id, 'Downloading options JSON') + @classmethod + def suitable(cls, url): + return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url) - m3u8_url = options['video_balancer'].get('m3u8') - if m3u8_url is None: - raise ExtractorError('Couldn\'t find m3u8 manifest url') - formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') + @staticmethod + def _extract_urls(webpage): + return [mobj.group('url') for mobj in re.finditer( + r']+?src=(["\'])(?P(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1', + webpage)] - 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, - } + def _real_extract(self, url): + video_id = self._match_id(url) + info = self._download_and_extract_info(video_id) + info['formats'] = self._download_and_extract_formats(video_id) + return info -class RutubeEmbedIE(InfoExtractor): +class RutubeEmbedIE(RutubeBaseIE): IE_NAME = 'rutube:embed' IE_DESC = 'Rutube embedded videos' - _VALID_URL = 'https?://rutube\.ru/video/embed/(?P[0-9]+)' + _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P[0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', 'info_dict': { 'id': 'a10e53b86e8f349080f718582ce4c661', 'ext': 'mp4', + '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', @@ -87,24 +163,78 @@ 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', + 'only_matching': True, + }, { + # private video + 'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ', + 'only_matching': True, + }] def _real_extract(self, url): embed_id = self._match_id(url) - webpage = self._download_webpage(url, embed_id) + # Query may contain private videos token and should be passed to API + # requests (see #19163) + query = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + options = self._download_api_options(embed_id, query) + video_id = options['effective_video'] + formats = self._extract_formats(options, video_id) + info = self._download_and_extract_info(video_id, query) + info.update({ + 'extractor_key': 'Rutube', + 'formats': formats, + }) + return info - canonical_url = self._html_search_regex( - r'\d+)' + _VALID_URL = r'https?://rutube\.ru/tags/video/(?P\d+)' _TESTS = [{ 'url': 'http://rutube.ru/tags/video/1800/', 'info_dict': { @@ -115,30 +245,11 @@ 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'http://rutube\.ru/metainfo/tv/(?P\d+)' + _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P\d+)' _TESTS = [] _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json' @@ -149,14 +260,14 @@ class RutubeMovieIE(RutubeChannelIE): 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'http://rutube\.ru/video/person/(?P\d+)' + _VALID_URL = r'https?://rutube\.ru/video/person/(?P\d+)' _TESTS = [{ 'url': 'http://rutube.ru/video/person/313878/', 'info_dict': { @@ -166,3 +277,37 @@ class RutubePersonIE(RutubeChannelIE): }] _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json' + + +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/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag', + 'info_dict': { + 'id': '3097', + }, + 'playlist_count': 27, + }, { + 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source', + 'only_matching': True, + }] + + _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json' + + @classmethod + def suitable(cls, url): + if not super(RutubePlaylistIE, cls).suitable(url): + return False + params = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + 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): + 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)