[cbs] extract info from thunder videoPlayerService(closes #10728)

This commit is contained in:
Remita Amine 2016-09-22 19:27:57 +01:00
parent 4ddcb5999d
commit 45cae3b021

View File

@ -4,7 +4,9 @@
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
find_xpath_attr, find_xpath_attr,
ExtractorError, xpath_element,
xpath_text,
update_url_query,
) )
@ -47,27 +49,49 @@ class CBSIE(CBSBaseIE):
'only_matching': True, 'only_matching': True,
}] }]
def _extract_video_info(self, guid): def _extract_video_info(self, content_id):
path = 'dJ5BDC/media/guid/2198311517/' + guid items_data = self._download_xml(
smil_url = 'http://link.theplatform.com/s/%s?mbr=true' % path 'http://can.cbs.com/thunder/player/videoPlayerService.php',
formats, subtitles = self._extract_theplatform_smil(smil_url + '&manifest=m3u', guid) content_id, query={'partner': 'cbs', 'contentId': content_id})
for r in ('OnceURL&formats=M3U', 'HLS&formats=M3U', 'RTMP', 'WIFI', '3G'): video_data = xpath_element(items_data, './/item')
try: title = xpath_text(video_data, 'videoTitle', 'title', True)
tp_formats, _ = self._extract_theplatform_smil(smil_url + '&assetTypes=' + r, guid, 'Downloading %s SMIL data' % r.split('&')[0]) tp_path = 'dJ5BDC/media/guid/2198311517/%s' % content_id
formats.extend(tp_formats) tp_release_url = 'http://link.theplatform.com/s/' + tp_path
except ExtractorError:
asset_types = []
subtitles = {}
formats = []
for item in items_data.findall('.//item'):
asset_type = xpath_text(item, 'assetType')
if not asset_type or asset_type in asset_types:
continue continue
asset_types.append(asset_type)
query = {
'mbr': 'true',
'assetTypes': asset_type,
}
if asset_type.startswith('HLS') or asset_type in ('OnceURL', 'StreamPack'):
query['formats'] = 'MPEG4,M3U'
elif asset_type in ('RTMP', 'WIFI', '3G'):
query['formats'] = 'MPEG4,FLV'
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query(tp_release_url, query), content_id,
'Downloading %s SMIL data' % asset_type)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats) self._sort_formats(formats)
metadata = self._download_theplatform_metadata(path, guid)
info = self._parse_theplatform_metadata(metadata) info = self._extract_theplatform_metadata(tp_path, content_id)
info.update({ info.update({
'id': guid, 'id': content_id,
'title': title,
'series': xpath_text(video_data, 'seriesTitle'),
'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
'thumbnail': xpath_text(video_data, 'previewImageURL'),
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'series': metadata.get('cbs$SeriesTitle'),
'season_number': int_or_none(metadata.get('cbs$SeasonNumber')),
'episode': metadata.get('cbs$EpisodeTitle'),
'episode_number': int_or_none(metadata.get('cbs$EpisodeNumber')),
}) })
return info return info