X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fcbsnews.py;h=4aa6917a0b494df6465d810b237040f4a7f30c78;hb=d13bfc07b79bafa0be6829a18d0d2e273e83339b;hp=b5e78a65d0230a49758c45f8c37d188087eafffb;hpb=3e0c3d14d9ab49f3a98324e91763c849ef52a1df;p=youtube-dl diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index b5e78a65d..4aa6917a0 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -2,14 +2,13 @@ from __future__ import unicode_literals from .common import InfoExtractor -from .cbs import CBSBaseIE +from .cbs import CBSIE from ..utils import ( parse_duration, - find_xpath_attr, ) -class CBSNewsIE(CBSBaseIE): +class CBSNewsIE(CBSIE): IE_DESC = 'CBS News' _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P[\da-z_-]+)' @@ -27,13 +26,18 @@ class CBSNewsIE(CBSBaseIE): # rtmp download 'skip_download': True, }, + 'skip': 'Subscribers only', }, { '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': '20140404', + 'timestamp': 1396650660, + 'uploader': 'CBSI-NEW', 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 205, 'subtitles': { @@ -59,36 +63,15 @@ class CBSNewsIE(CBSBaseIE): 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 = {} - 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?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(guid) class CBSNewsLiveVideoIE(InfoExtractor): IE_DESC = 'CBS News Live Videos' _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P[\da-z_-]+)' + # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples _TEST = { 'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/', 'info_dict': { @@ -97,6 +80,7 @@ class CBSNewsLiveVideoIE(InfoExtractor): 'title': 'Clinton, Sanders Prepare To Face Off In NH', 'duration': 334, }, + 'skip': 'Video gone', } def _real_extract(self, url):