X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Frtve.py;h=8d9be1b98ce3adf338e7259c52181f3e2216213c;hb=de5c54564874fd870fdfe3fd24f47e3e5f6cedf7;hp=c0fd23ff108f8b523a0e71f458147287954f429c;hpb=9c665ab72e5fc99989800109cdada5acc3af56c5;p=youtube-dl diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index c0fd23ff1..8d9be1b98 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -8,8 +8,10 @@ import time from .common import InfoExtractor from ..compat import compat_urlparse from ..utils import ( - struct_unpack, + float_or_none, remove_end, + std_headers, + struct_unpack, ) @@ -67,6 +69,7 @@ class RTVEALaCartaIE(InfoExtractor): 'id': '2491869', 'ext': 'mp4', 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia', + 'duration': 5024.566, }, }, { 'note': 'Live stream', @@ -82,13 +85,20 @@ class RTVEALaCartaIE(InfoExtractor): 'only_matching': True, }] + def _real_initialize(self): + user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8') + manager_info = self._download_json( + 'http://www.rtve.es/odin/loki/' + user_agent_b64, + None, 'Fetching manager info') + self._manager = manager_info['manager'] + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') info = self._download_json( 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id, video_id)['page']['items'][0] - png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id + png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id) png = self._download_webpage(png_url, video_id, 'Downloading url information') video_url = _decrypt_url(png) if not video_url.endswith('.f4m'): @@ -113,6 +123,7 @@ class RTVEALaCartaIE(InfoExtractor): '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): @@ -124,6 +135,47 @@ class RTVEALaCartaIE(InfoExtractor): for s in subs) +class RTVEInfantilIE(InfoExtractor): + IE_NAME = 'rtve.es:infantil' + IE_DESC = 'RTVE infantil' + _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P[^/]*)/video/(?P[^/]*)/(?P[0-9]+)/' + + _TESTS = [{ + 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/', + 'md5': '915319587b33720b8e0357caaa6617e6', + 'info_dict': { + 'id': '3040283', + 'ext': 'mp4', + 'title': 'Maneras de vivir', + 'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG', + 'duration': 357.958, + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + info = self._download_json( + 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id, + video_id)['page']['items'][0] + + webpage = self._download_webpage(url, video_id) + vidplayer_id = self._search_regex( + r' id="vidplayer([0-9]+)"', webpage, 'internal video ID') + + png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id + png = self._download_webpage(png_url, video_id, 'Downloading url information') + video_url = _decrypt_url(png) + + return { + 'id': video_id, + 'ext': 'mp4', + 'title': info['title'], + 'url': video_url, + 'thumbnail': info.get('image'), + 'duration': float_or_none(info.get('duration'), scale=1000), + } + + class RTVELiveIE(InfoExtractor): IE_NAME = 'rtve.es:live' IE_DESC = 'RTVE.es live streams'