X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..e96056e11025aad125c364bd96b2a2df071dd2ae:/youtube_dl/extractor/rutv.py diff --git a/youtube_dl/extractor/rutv.py b/youtube_dl/extractor/rutv.py index f737b4e..d2713c1 100644 --- a/youtube_dl/extractor/rutv.py +++ b/youtube_dl/extractor/rutv.py @@ -1,4 +1,4 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re @@ -13,11 +13,15 @@ from ..utils import ( class RUTVIE(InfoExtractor): IE_DESC = 'RUTV.RU' _VALID_URL = r'''(?x) - https?://player\.(?:rutv\.ru|vgtrk\.com)/ - (?Pflash2v/container\.swf\?id= - |iframe/(?Pswf|video|live)/id/ - |index/iframe/cast_id/) - (?P\d+)''' + https?:// + (?:test)?player\.(?:rutv\.ru|vgtrk\.com)/ + (?P + flash\d+v/container\.swf\?id=| + iframe/(?Pswf|video|live)/id/| + index/iframe/cast_id/ + ) + (?P\d+) + ''' _TESTS = [ { @@ -84,23 +88,36 @@ class RUTVIE(InfoExtractor): 'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ', 'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c', }, + 'skip': 'Translation has finished', + }, + { + 'url': 'http://player.rutv.ru/iframe/live/id/21/showZoomBtn/false/isPlay/true/', + 'info_dict': { + 'id': '21', + 'ext': 'mp4', + 'title': 're:^Россия 24. Прямой эфир [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'is_live': True, + }, 'params': { - # rtmp download + # m3u8 download 'skip_download': True, }, - 'skip': 'Translation has finished', + }, + { + 'url': 'https://testplayer.vgtrk.com/iframe/live/id/19201/showZoomBtn/false/isPlay/true/', + 'only_matching': True, }, ] @classmethod def _extract_url(cls, webpage): mobj = re.search( - r']+?src=(["\'])(?Phttps?://player\.rutv\.ru/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage) + r']+?src=(["\'])(?Phttps?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage) if mobj: return mobj.group('url') mobj = re.search( - r']+?property=(["\'])og:video\1[^>]+?content=(["\'])(?Phttps?://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)', + r']+?property=(["\'])og:video\1[^>]+?content=(["\'])(?Phttps?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)', webpage) if mobj: return mobj.group('url') @@ -110,7 +127,7 @@ class RUTVIE(InfoExtractor): video_id = mobj.group('id') video_path = mobj.group('path') - if video_path.startswith('flash2v'): + if re.match(r'flash\d+v', video_path): video_type = 'video' elif video_path.startswith('iframe'): video_type = mobj.group('type') @@ -119,8 +136,10 @@ class RUTVIE(InfoExtractor): elif video_path.startswith('index/iframe/cast_id'): video_type = 'live' + is_live = video_type == 'live' + json_data = self._download_json( - 'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if video_type == 'live' else '', video_id), + 'http://player.rutv.ru/iframe/data%s/id/%s' % ('live' if is_live else 'video', video_id), video_id, 'Downloading JSON') if json_data['errors']: @@ -147,6 +166,7 @@ class RUTVIE(InfoExtractor): for transport, links in media['sources'].items(): for quality, url in links.items(): + preference = -1 if priority_transport == transport else -2 if transport == 'rtmp': mobj = re.search(r'^(?Prtmp://[^/]+/(?P.+))/(?P.+)$', url) if not mobj: @@ -156,16 +176,16 @@ class RUTVIE(InfoExtractor): 'play_path': mobj.group('playpath'), 'app': mobj.group('app'), 'page_url': 'http://player.rutv.ru', - 'player_url': 'http://player.rutv.ru/flash2v/osmf.swf?i=22', + 'player_url': 'http://player.rutv.ru/flash3v/osmf.swf?i=22', 'rtmp_live': True, 'ext': 'flv', 'vbr': int(quality), + 'preference': preference, } elif transport == 'm3u8': - fmt = { - 'url': url, - 'ext': 'mp4', - } + formats.extend(self._extract_m3u8_formats( + url, video_id, 'mp4', preference=preference, m3u8_id='hls')) + continue else: fmt = { 'url': url @@ -174,21 +194,18 @@ class RUTVIE(InfoExtractor): 'width': width, 'height': height, 'format_id': '%s-%s' % (transport, quality), - 'preference': -1 if priority_transport == transport else -2, }) formats.append(fmt) - if not formats: - raise ExtractorError('No media links available for %s' % video_id) - self._sort_formats(formats) return { 'id': video_id, - 'title': title, + 'title': self._live_title(title) if is_live else title, 'description': description, 'thumbnail': thumbnail, 'view_count': view_count, 'duration': duration, 'formats': formats, - } \ No newline at end of file + 'is_live': is_live, + }