X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcbsnews.py;h=387537e766fc4886201285f221022181b2beeb53;hb=9558dcec9c7806c811f4fe8e7758977eaa01a702;hp=8f864699f93675afe2ce00db21a13c4110bff46b;hpb=66159b38aad38d55f84a358a0c2ed2add9a2946d;p=youtube-dl diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index 8f864699f..387537e76 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -2,13 +2,15 @@ from __future__ import unicode_literals from .common import InfoExtractor -from .theplatform import ThePlatformIE -from ..utils import parse_duration +from .cbs import CBSBaseIE +from ..utils import ( + parse_duration, +) -class CBSNewsIE(ThePlatformIE): +class CBSNewsIE(CBSBaseIE): IE_DESC = 'CBS News' - _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P[\da-z_-]+)' + _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P[\da-z_-]+)' _TESTS = [ { @@ -28,9 +30,12 @@ class CBSNewsIE(ThePlatformIE): { 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/', 'info_dict': { - 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack', + 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y', 'ext': 'mp4', 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack', + 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7', + 'upload_date': '19700101', + 'uploader': 'CBSI-NEW', 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 205, 'subtitles': { @@ -56,41 +61,13 @@ class CBSNewsIE(ThePlatformIE): webpage, 'video JSON info'), video_id) item = video_info['item'] if 'item' in video_info else video_info - title = item.get('articleTitle') or item.get('hed') - duration = item.get('duration') - thumbnail = item.get('mediaImage') or item.get('thumbnail') - - subtitles = {} - if 'mpxRefId' in video_info: - subtitles['en'] = [{ - 'ext': 'ttml', - 'url': 'http://www.cbsnews.com/videos/captions/%s.adb_xml' % video_info['mpxRefId'], - }] - - formats = [] - for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']: - pid = item.get('media' + format_id) - if not pid: - continue - release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?format=SMIL&mbr=true' % pid - tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid) - formats.extend(tp_formats) - subtitles = self._merge_subtitles(subtitles, tp_subtitles) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } + guid = item['mpxRefId'] + return self._extract_video_info('byGuid=%s' % guid, guid) class CBSNewsLiveVideoIE(InfoExtractor): IE_DESC = 'CBS News Live Videos' - _VALID_URL = r'http://(?:www\.)?cbsnews\.com/live/video/(?P[\da-z_-]+)' + _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P[\da-z_-]+)' _TEST = { 'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/', @@ -116,6 +93,7 @@ class CBSNewsLiveVideoIE(InfoExtractor): for entry in f4m_formats: # URLs without the extra param induce an 404 error entry.update({'extra_param_to_segment_url': hdcore_sign}) + self._sort_formats(f4m_formats) return { 'id': video_id,