X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvrt.py;h=8e35f24e81e7e61240898ea3259914737365fd2f;hb=b5aad37f6bdc72acaca198202dc9f7eaa3185e51;hp=57ef8dc300355f1c49b2be0a2ee4e4fa27b4e4ca;hpb=f889cea109b4e2647e3fd6a462c9893b88b21e04;p=youtube-dl diff --git a/youtube_dl/extractor/vrt.py b/youtube_dl/extractor/vrt.py index 57ef8dc30..8e35f24e8 100644 --- a/youtube_dl/extractor/vrt.py +++ b/youtube_dl/extractor/vrt.py @@ -4,11 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import float_or_none +from ..utils import ( + determine_ext, + float_or_none, +) class VRTIE(InfoExtractor): - _VALID_URL = r'https?://(?:deredactie|sporza|cobra)\.be/cm/(?:[^/]+/)+(?P[^/]+)/*' + _VALID_URL = r'https?://(?:deredactie|sporza|cobra(?:\.canvas)?)\.be/cm/(?:[^/]+/)+(?P[^/]+)/*' _TESTS = [ # deredactie.be { @@ -36,7 +39,7 @@ class VRTIE(InfoExtractor): 'timestamp': 1413835980.560, 'upload_date': '20141020', 'duration': 3238, - } + } }, # cobra.be { @@ -52,6 +55,15 @@ class VRTIE(InfoExtractor): 'duration': 661, } }, + { + # YouTube video + 'url': 'http://deredactie.be/cm/vrtnieuws/videozone/nieuws/cultuurenmedia/1.2622957', + 'only_matching': True, + }, + { + 'url': 'http://cobra.canvas.be/cm/cobra/videozone/rubriek/film-videozone/1.2377055', + 'only_matching': True, + } ] def _real_extract(self, url): @@ -62,18 +74,37 @@ class VRTIE(InfoExtractor): video_id = self._search_regex( r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False) + src = self._search_regex( + r'data-video-src="([^"]+)"', webpage, 'video src', default=None) + + video_type = self._search_regex( + r'data-video-type="([^"]+)"', webpage, 'video type', default=None) + + if video_type == 'YouTubeVideo': + return self.url_result(src, 'Youtube') + formats = [] + mobj = re.search( r'data-video-iphone-server="(?P[^"]+)"\s+data-video-iphone-path="(?P[^"]+)"', webpage) if mobj: formats.extend(self._extract_m3u8_formats( '%s/%s' % (mobj.group('server'), mobj.group('path')), - video_id, 'mp4')) - mobj = re.search(r'data-video-src="(?P[^"]+)"', webpage) - if mobj: - formats.extend(self._extract_f4m_formats( - '%s/manifest.f4m' % mobj.group('src'), video_id)) + video_id, 'mp4', m3u8_id='hls', fatal=False)) + + if src: + if determine_ext(src) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + src, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + else: + formats.extend(self._extract_f4m_formats( + '%s/manifest.f4m' % src, video_id, f4m_id='hds', fatal=False)) + + if not formats and 'data-video-geoblocking="true"' in webpage: + self.raise_geo_restricted('This video is only available in Belgium') + self._sort_formats(formats) title = self._og_search_title(webpage) @@ -92,4 +123,4 @@ class VRTIE(InfoExtractor): 'timestamp': timestamp, 'duration': duration, 'formats': formats, - } \ No newline at end of file + }