xpath_text,
xpath_element,
int_or_none,
- ExtractorError,
find_xpath_attr,
)
-class CBSIE(ThePlatformIE):
+class CBSBaseIE(ThePlatformIE):
+ def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
+ closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
+ return {
+ 'en': [{
+ 'ext': 'ttml',
+ 'url': closed_caption_e.attrib['value'],
+ }]
+ } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
+
+
+class CBSIE(CBSBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
_TESTS = [{
'title': 'Connect Chat feat. Garth Brooks',
'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
'duration': 1495,
+ 'timestamp': 1385585425,
+ 'upload_date': '20131127',
+ 'uploader': 'CBSI-NEW',
},
'params': {
# rtmp download
'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
'only_matching': True,
}]
- TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?manifest=m3u&mbr=true'
-
- def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
- closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
- return {
- 'en': [{
- 'ext': 'ttml',
- 'url': closed_caption_e.attrib['value'],
- }]
- } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
+ TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
def _real_extract(self, url):
display_id = self._match_id(url)
pid = xpath_text(item, 'pid')
if not pid:
continue
- try:
- tp_formats, tp_subtitles = self._extract_theplatform_smil(
- self.TP_RELEASE_URL_TEMPLATE % pid, content_id, 'Downloading %s SMIL data' % pid)
- except ExtractorError:
- continue
+ tp_release_url = self.TP_RELEASE_URL_TEMPLATE % pid
+ if '.m3u8' in xpath_text(item, 'contentUrl', default=''):
+ tp_release_url += '&manifest=m3u'
+ tp_formats, tp_subtitles = self._extract_theplatform_smil(
+ tp_release_url, content_id, 'Downloading %s SMIL data' % pid)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats)