From 3e0c3d14d9ab49f3a98324e91763c849ef52a1df Mon Sep 17 00:00:00 2001 From: remitamine Date: Fri, 1 Apr 2016 10:12:29 +0100 Subject: [PATCH] [cbs] add base extractor --- youtube_dl/extractor/cbs.py | 22 ++++++++++++---------- youtube_dl/extractor/cbsnews.py | 13 ++----------- 2 files changed, 14 insertions(+), 21 deletions(-) diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index 0cf56b9c7b..6e4079ca37 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -10,7 +10,18 @@ from ..utils import ( ) -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[^/]+)' _TESTS = [{ @@ -52,15 +63,6 @@ class CBSIE(ThePlatformIE): }] 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 [] - def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index e6b7f35845..b5e78a65d0 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -2,14 +2,14 @@ from __future__ import unicode_literals from .common import InfoExtractor -from .theplatform import ThePlatformIE +from .cbs import CBSBaseIE from ..utils import ( parse_duration, find_xpath_attr, ) -class CBSNewsIE(ThePlatformIE): +class CBSNewsIE(CBSBaseIE): IE_DESC = 'CBS News' _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P[\da-z_-]+)' @@ -49,15 +49,6 @@ class CBSNewsIE(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 [] - def _real_extract(self, url): video_id = self._match_id(url)