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

[cbs] add base extractor

Browse source
This commit is contained in:
remitamine 2016-04-01 10:12:29 +01:00
parent d8873d4def
commit 3e0c3d14d9
2 changed files with 14 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
youtube_dl/extractor/cbs.py
View file

@ -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<id>[^/]+)' _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
_TESTS = [{ _TESTS = [{
@ -52,15 +63,6 @@ class CBSIE(ThePlatformIE):
}] }]
TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?manifest=m3u&mbr=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 []
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)

13
youtube_dl/extractor/cbsnews.py
View file

@ -2,14 +2,14 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from .theplatform import ThePlatformIE from .cbs import CBSBaseIE
from ..utils import ( from ..utils import (
parse_duration, parse_duration,
find_xpath_attr, find_xpath_attr,
) )
class CBSNewsIE(ThePlatformIE): class CBSNewsIE(CBSBaseIE):
IE_DESC = 'CBS News' IE_DESC = 'CBS News'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)' _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\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): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)