X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Frtve.py;h=b42442d127c13e69fc81cb27e71cf117d2cb96b2;hb=22d362831978ea2b83ea0c21a634237dc2406ab6;hp=8cf753902f65ed83d541f48776c1b58b3e9eee64;hpb=2b9faf55427b73cb978ddd661c32a5cb313f9331;p=youtube-dl diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 8cf753902..b42442d12 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -6,9 +6,11 @@ import re import time from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( - struct_unpack, + float_or_none, remove_end, + struct_unpack, ) @@ -54,11 +56,10 @@ def _decrypt_url(png): return url - class RTVEALaCartaIE(InfoExtractor): IE_NAME = 'rtve.es:alacarta' IE_DESC = 'RTVE a la carta' - _VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P\d+)' + _VALID_URL = r'http://www\.rtve\.es/(m/)?alacarta/videos/[^/]+/[^/]+/(?P\d+)' _TESTS = [{ 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/', @@ -67,6 +68,7 @@ class RTVEALaCartaIE(InfoExtractor): 'id': '2491869', 'ext': 'mp4', 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia', + 'duration': 5024.566, }, }, { 'note': 'Live stream', @@ -75,7 +77,11 @@ class RTVEALaCartaIE(InfoExtractor): 'id': '1694255', 'ext': 'flv', 'title': 'TODO', - } + }, + 'skip': 'The f4m manifest can\'t be used yet', + }, { + 'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve', + 'only_matching': True, }] def _real_extract(self, url): @@ -87,6 +93,20 @@ class RTVEALaCartaIE(InfoExtractor): png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id png = self._download_webpage(png_url, video_id, 'Downloading url information') video_url = _decrypt_url(png) + if not video_url.endswith('.f4m'): + auth_url = video_url.replace( + 'resources/', 'auth/resources/' + ).replace('.net.rtve', '.multimedia.cdn.rtve') + video_path = self._download_webpage( + auth_url, video_id, 'Getting video url') + # Use mvod1.akcdn instead of flash.akamaihd.multimedia.cdn to get + # the right Content-Length header and the mp4 format + video_url = compat_urlparse.urljoin( + 'http://mvod1.akcdn.rtve.es/', video_path) + + subtitles = None + if info.get('sbtFile') is not None: + subtitles = self.extract_subtitles(video_id, info['sbtFile']) return { 'id': video_id, @@ -94,13 +114,23 @@ class RTVEALaCartaIE(InfoExtractor): 'url': video_url, 'thumbnail': info.get('image'), 'page_url': url, + 'subtitles': subtitles, + 'duration': float_or_none(info.get('duration'), scale=1000), } + def _get_subtitles(self, video_id, sub_file): + subs = self._download_json( + sub_file + '.json', video_id, + 'Downloading subtitles info')['page']['items'] + return dict( + (s['lang'], [{'ext': 'vtt', 'url': s['src']}]) + for s in subs) + class RTVELiveIE(InfoExtractor): IE_NAME = 'rtve.es:live' IE_DESC = 'RTVE.es live streams' - _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias(?=/directo-la-1)|television)/(?P[a-zA-Z0-9-]+)' + _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P[a-zA-Z0-9-]+)' _TESTS = [{ 'url': 'http://www.rtve.es/noticias/directo-la-1/', @@ -131,8 +161,6 @@ class RTVELiveIE(InfoExtractor): png = self._download_webpage(png_url, video_id, 'Downloading url information') video_url = _decrypt_url(png) - print(video_url) - return { 'id': video_id, 'ext': 'flv',