[cbs] Add support for series playlists
This commit is contained in:
Paul Pritchard
parent
1cf0e3c31b
commit
1ac65a003a
@ -1,19 +1,25 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .theplatform import ThePlatformFeedIE
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
url_or_none,
|
||||
js_to_json,
|
||||
find_xpath_attr,
|
||||
parse_duration,
|
||||
xpath_element,
|
||||
xpath_text,
|
||||
update_url_query,
|
||||
urljoin,
|
||||
)
|
||||
import datetime
|
||||
|
||||
|
||||
class CBSBaseIE(ThePlatformFeedIE):
|
||||
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')
|
||||
closed_caption_e = find_xpath_attr(smil, self._xpath_ns(
|
||||
'.//param', namespace), 'name', 'ClosedCaptionURL')
|
||||
return {
|
||||
'en': [{
|
||||
'ext': 'ttml',
|
||||
@ -22,6 +28,88 @@ class CBSBaseIE(ThePlatformFeedIE):
|
||||
} if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
|
||||
|
||||
|
||||
class CBSPlaylistIE(InfoExtractor):
|
||||
IE_DESC = 'CBS series playlists'
|
||||
IE_NAME = 'cbs.com:playlist'
|
||||
_VALID_URL = r'(?i)https?://(?:www\.)cbs.com/shows/(?P<id>[\w-]+)/?$'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'https://www.cbs.com/shows/frasier/',
|
||||
'info_dict': {
|
||||
'id': 61456196,
|
||||
'title': 'Frasier',
|
||||
},
|
||||
'playlist_count': 264,
|
||||
},
|
||||
{
|
||||
'url': 'https://www.cbs.com/shows/star_trek/',
|
||||
'info_dict': {
|
||||
'id': 22927,
|
||||
'title': 'Star Trek: The Original Series (Remastered)',
|
||||
},
|
||||
'playlist_count': 79,
|
||||
},
|
||||
]
|
||||
|
||||
def extract_episode_info(self, url, json_data):
|
||||
episodes = json_data.get('result', {}).get('data')
|
||||
|
||||
entries = []
|
||||
for ep in episodes:
|
||||
series_title = ep.get('series_title')
|
||||
episode_url = url_or_none(urljoin(url, ep.get('url')))
|
||||
if episode_url:
|
||||
entries.append({
|
||||
'_type': 'url',
|
||||
'id': ep.get('content_id'),
|
||||
'ie_key': 'CBS',
|
||||
'title': ep.get('title'),
|
||||
'url': episode_url,
|
||||
'duration': parse_duration(ep.get('duration')),
|
||||
'thumbnail': ep.get('thumb', {}).get('large'),
|
||||
'upload_date': datetime.datetime.strptime(ep.get('airdate'), '%b %d, %Y').strftime('%Y%m%d'),
|
||||
'episode_title': ep.get('episode_title'),
|
||||
'episode_number': int_or_none(ep.get('episode_number')),
|
||||
'season_number': int_or_none(ep.get('season_number')),
|
||||
'series': ep.get('series_title'),
|
||||
})
|
||||
|
||||
return {'series_title': series_title, 'episodes': entries}
|
||||
|
||||
def _real_extract(self, url):
|
||||
show_name = self._match_id(url)
|
||||
webpage = self._download_webpage(url, show_name)
|
||||
|
||||
show_name_js = self._search_regex(
|
||||
r'new CBS\.Show\(([^)]*)\);', webpage, 'show_name')
|
||||
show = self._parse_json(show_name_js, show_name,
|
||||
transform_source=js_to_json)
|
||||
show_id = show.get('id')
|
||||
|
||||
entries = []
|
||||
if show_id:
|
||||
offset = 0
|
||||
limit = 10
|
||||
more_episodes = True
|
||||
while (more_episodes):
|
||||
episodes_url = urljoin(
|
||||
url, '/carousels/shows/%d/offset/%d/limit/%d/xs/0/' % (show_id, offset, limit))
|
||||
json_data = self._download_json(
|
||||
episodes_url, 'Downloading episode playlist')
|
||||
result = self.extract_episode_info(url, json_data)
|
||||
entries += result['episodes']
|
||||
series_title = result['series_title']
|
||||
total_episodes = json_data.get('result', {}).get('total')
|
||||
offset = offset + limit
|
||||
if offset > total_episodes:
|
||||
more_episodes = False
|
||||
|
||||
playlist = self.playlist_result(
|
||||
entries, show_id, playlist_title=series_title)
|
||||
print(playlist)
|
||||
return playlist
|
||||
|
||||
|
||||
class CBSIE(CBSBaseIE):
|
||||
_VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
|
||||
|
||||
@ -50,22 +138,21 @@ class CBSIE(CBSBaseIE):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
|
||||
def _extract_video_info(self, content_id):
|
||||
items_data = self._download_xml(
|
||||
'http://can.cbs.com/thunder/player/videoPlayerService.php',
|
||||
content_id, query={'partner': site, 'contentId': content_id})
|
||||
content_id, query={'partner': 'cbs', 'contentId': content_id})
|
||||
video_data = xpath_element(items_data, './/item')
|
||||
title = xpath_text(video_data, 'videoTitle', 'title', True)
|
||||
tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
|
||||
tp_path = 'dJ5BDC/media/guid/2198311517/%s' % content_id
|
||||
tp_release_url = 'http://link.theplatform.com/s/' + tp_path
|
||||
|
||||
asset_types = []
|
||||
subtitles = {}
|
||||
formats = []
|
||||
last_e = None
|
||||
for item in items_data.findall('.//item'):
|
||||
asset_type = xpath_text(item, 'assetType')
|
||||
if not asset_type or asset_type in asset_types or asset_type in ('HLS_FPS', 'DASH_CENC'):
|
||||
if not asset_type or asset_type in asset_types:
|
||||
continue
|
||||
asset_types.append(asset_type)
|
||||
query = {
|
||||
@ -76,17 +163,11 @@ class CBSIE(CBSBaseIE):
|
||||
query['formats'] = 'MPEG4,M3U'
|
||||
elif asset_type in ('RTMP', 'WIFI', '3G'):
|
||||
query['formats'] = 'MPEG4,FLV'
|
||||
try:
|
||||
tp_formats, tp_subtitles = self._extract_theplatform_smil(
|
||||
update_url_query(tp_release_url, query), content_id,
|
||||
'Downloading %s SMIL data' % asset_type)
|
||||
except ExtractorError as e:
|
||||
last_e = e
|
||||
continue
|
||||
formats.extend(tp_formats)
|
||||
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
|
||||
if last_e and not formats:
|
||||
raise last_e
|
||||
self._sort_formats(formats)
|
||||
|
||||
info = self._extract_theplatform_metadata(tp_path, content_id)
|
||||
|
||||
@ -173,7 +173,10 @@ from .cbc import (
|
||||
CBCWatchIE,
|
||||
CBCOlympicsIE,
|
||||
)
|
||||
from .cbs import CBSIE
|
||||
from .cbs import (
|
||||
CBSIE,
|
||||
CBSPlaylistIE,
|
||||
)
|
||||
from .cbslocal import CBSLocalIE
|
||||
from .cbsinteractive import CBSInteractiveIE
|
||||
from .cbsnews import (
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user