X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/848723ea972c09f28787db91d8c06e98a274ab89..97a8fc3ae80fb363c69c2e6b8c29b5373ac72aea:/youtube_dl/extractor/rutube.py?ds=sidebyside diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 4922dd7..889fa76 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -1,57 +1,83 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re -import json import itertools from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, +) +from ..utils import ( + determine_ext, unified_strdate, - ExtractorError, ) class RutubeIE(InfoExtractor): 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/', - 'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4', 'info_dict': { + 'id': '3eac3b4561676c17df9132a9a1e62e3e', + 'ext': 'mp4', 'title': 'Раненный кенгуру забежал в аптеку', 'description': 'http://www.ntdtv.ru ', 'duration': 80, 'uploader': 'NTDRussian', 'uploader_id': '29790', '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, + }, { + 'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661', + 'only_matching': True, + }] + + @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)] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id, - video_id, 'Downloading video JSON') - video = json.loads(api_response) - - api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id, - video_id, 'Downloading trackinfo JSON') - trackinfo = json.loads(api_response) - + 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 = trackinfo.get('author') or {} - m3u8_url = trackinfo['video_balancer'].get('m3u8') - if m3u8_url is None: - raise ExtractorError('Couldn\'t find m3u8 manifest url') + author = video.get('author') or {} + + options = self._download_json( + 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, + video_id, 'Downloading options JSON') + + 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 { 'id': video['id'], @@ -59,8 +85,7 @@ class RutubeIE(InfoExtractor): 'description': video['description'], 'duration': video['duration'], 'view_count': video['hits'], - 'url': m3u8_url, - 'ext': 'mp4', + 'formats': formats, 'thumbnail': video['thumbnail_url'], 'uploader': author.get('name'), 'uploader_id': compat_str(author['id']) if author else None, @@ -69,20 +94,60 @@ class RutubeIE(InfoExtractor): } +class RutubeEmbedIE(InfoExtractor): + IE_NAME = 'rutube:embed' + IE_DESC = 'Rutube embedded videos' + _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P[0-9]+)' + + _TESTS = [{ + 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', + 'info_dict': { + 'id': 'a10e53b86e8f349080f718582ce4c661', + 'ext': 'mp4', + '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', + 'uploader': 'subziro89 ILya', + 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89', + }, + 'params': { + 'skip_download': 'Requires ffmpeg', + }, + }, { + 'url': 'http://rutube.ru/play/embed/8083783', + 'only_matching': True, + }] + + def _real_extract(self, url): + embed_id = self._match_id(url) + webpage = self._download_webpage(url, embed_id) + + 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': { + 'id': '1800', + }, + 'playlist_mincount': 68, + }] _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): - api_response = self._download_webpage( + page = self._download_json( self._PAGE_TEMPLATE % (channel_id, pagenum), channel_id, 'Downloading page %s' % pagenum) - page = json.loads(api_response) results = page['results'] if not results: break @@ -100,18 +165,17 @@ class RutubeChannelIE(InfoExtractor): class RutubeMovieIE(RutubeChannelIE): 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' _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - movie_id = mobj.group('id') - api_response = self._download_webpage( + movie_id = self._match_id(url) + movie = self._download_json( self._MOVIE_TEMPLATE % movie_id, movie_id, 'Downloading movie JSON') - movie = json.loads(api_response) movie_name = movie['name'] return self._extract_videos(movie_id, movie_name) @@ -119,6 +183,13 @@ class RutubeMovieIE(RutubeChannelIE): class RutubePersonIE(RutubeChannelIE): 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': { + 'id': '313878', + }, + 'playlist_mincount': 37, + }] _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'