X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a4f82408d9a3d921d9c2af7e4d757f44737dc7ea..8c72ec3993d7183e9c1fcd2cab445a3196ad8723:/youtube_dl/extractor/dfb.py diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py index cb8e068..a4d0448 100644 --- a/youtube_dl/extractor/dfb.py +++ b/youtube_dl/extractor/dfb.py @@ -3,42 +3,55 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import unified_strdate class DFBIE(InfoExtractor): IE_NAME = 'tv.dfb.de' - _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P\d+)' + _VALID_URL = r'https?://tv\.dfb\.de/video/(?P[^/]+)/(?P\d+)' _TEST = { - 'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/', - # The md5 is different each time + 'url': 'http://tv.dfb.de/video/u-19-em-stimmen-zum-spiel-gegen-russland/11633/', + 'md5': 'ac0f98a52a330f700b4b3034ad240649', 'info_dict': { - 'id': '9070', - 'ext': 'flv', - 'title': 'Highlights des Empfangs in Berlin', - 'upload_date': '20140716', + 'id': '11633', + 'display_id': 'u-19-em-stimmen-zum-spiel-gegen-russland', + 'ext': 'mp4', + 'title': 'U 19-EM: Stimmen zum Spiel gegen Russland', + 'upload_date': '20150714', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + display_id, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, video_id) player_info = self._download_xml( 'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id, - video_id) + display_id) video_info = player_info.find('video') - - f4m_info = self._download_xml(video_info.find('url').text, video_id) - token_el = f4m_info.find('token') - manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' + stream_access_url = self._proto_relative_url(video_info.find('url').text.strip()) + + formats = [] + # see http://tv.dfb.de/player/js/ajax.js for the method to extract m3u8 formats + for sa_url in (stream_access_url, stream_access_url + '&area=&format=iphone'): + stream_access_info = self._download_xml(sa_url, display_id) + token_el = stream_access_info.find('token') + manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + if '.f4m' in manifest_url: + formats.extend(self._extract_f4m_formats( + manifest_url + '&hdcore=3.2.0', + display_id, f4m_id='hds', fatal=False)) + else: + formats.extend(self._extract_m3u8_formats( + manifest_url, display_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + self._sort_formats(formats) return { 'id': video_id, + 'display_id': display_id, 'title': video_info.find('title').text, - 'url': manifest_url, - 'ext': 'flv', - 'thumbnail': self._og_search_thumbnail(webpage), - 'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]), + 'thumbnail': 'http://tv.dfb.de/images/%s_640x360.jpg' % video_id, + 'upload_date': unified_strdate(video_info.find('time_date').text), + 'formats': formats, }