jcgruenhage/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[cbs] allow to pass content id to the extractor(closes #9589)

Browse source
This commit is contained in:
remitamine 2016-05-23 09:30:26 +01:00
parent b1e9ebd080
commit 42a7439717
1 changed files with 9 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/cbs.py
View file

@ -1,5 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .theplatform import ThePlatformIE from .theplatform import ThePlatformIE
from ..utils import ( from ..utils import (
xpath_text, xpath_text,
@ -21,7 +23,7 @@ class CBSBaseIE(ThePlatformIE):
class CBSIE(CBSBaseIE): class CBSIE(CBSBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)' _VALID_URL = r'(?:cbs:(?P<content_id>\w+)|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<display_id>[^/]+))'
_TESTS = [{ _TESTS = [{
'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', 'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
@ -66,11 +68,12 @@ class CBSIE(CBSBaseIE):
TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) content_id, display_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id) if not content_id:
content_id = self._search_regex( webpage = self._download_webpage(url, display_id)
[r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"], content_id = self._search_regex(
webpage, 'content id') [r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"],
webpage, 'content id')
items_data = self._download_xml( items_data = self._download_xml(
'http://can.cbs.com/thunder/player/videoPlayerService.php', 'http://can.cbs.com/thunder/player/videoPlayerService.php',
content_id, query={'partner': 'cbs', 'contentId': content_id}) content_id, query={'partner': 'cbs', 'contentId': content_id})