kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[cnbc] Simplify extraction (closes #14280, closes #17110)

Browse source
This commit is contained in:
Sergey M․ 2018-10-29 23:53:39 +07:00
parent ffa7b2bfee
commit 94db1f7f3b
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 11 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
youtube_dl/extractor/cnbc.py
View file

@ -3,10 +3,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import smuggle_url
js_to_json,
smuggle_url,
)
class CNBCIE(InfoExtractor): class CNBCIE(InfoExtractor):
@ -40,36 +37,30 @@ class CNBCIE(InfoExtractor):
} }
class CNBCNewIE(InfoExtractor): class CNBCVideoIE(InfoExtractor):
IE_NAME = 'CNBC:new' _VALID_URL = r'https?://(?:www)?\.cnbc\.com/video/(?:[^/]+/)+(?P<id>[^./?#&]+)'
_VALID_URL = r'https?://(?:www)?\.cnbc\.com/video.*/(?P<id>[^.]+)'
_TEST = { _TEST = {
'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', 'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html',
'info_dict': { 'info_dict': {
'id': '7000031301', 'id': '7000031301',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Trump: I don\'t necessarily agree with raising rates', 'title': "Trump: I don't necessarily agree with raising rates",
'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3', 'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3',
'timestamp': 1531958400, 'timestamp': 1531958400,
'upload_date': '20180719', 'upload_date': '20180719',
'uploader': 'NBCU-CNBC', 'uploader': 'NBCU-CNBC',
}, },
'params': { 'params': {
# m3u8 download
'skip_download': True, 'skip_download': True,
}, },
} }
CNBC_URL_TEMPLATE = 'http://video.cnbc.com/gallery/?video=%s'
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)
video_id = self._parse_json( video_id = self._search_regex(
self._search_regex( r'content_id["\']\s*:\s*["\'](\d+)', webpage, display_id,
r'(?s).*<script[^>]*>.*?({.+?content_id.+?}).*?</script>', 'video id')
webpage, display_id), return self.url_result(
display_id, transform_source=js_to_json 'http://video.cnbc.com/gallery/?video=%s' % video_id,
)['content_id'] CNBCIE.ie_key())
return self.url_result(self.CNBC_URL_TEMPLATE % video_id, 'CNBC')

2
youtube_dl/extractor/extractors.py
View file

@ -211,7 +211,7 @@ from .clyp import ClypIE
from .cmt import CMTIE from .cmt import CMTIE
from .cnbc import ( from .cnbc import (
CNBCIE, CNBCIE,
CNBCNewIE, CNBCVideoIE,
) )
from .cnn import ( from .cnn import (
CNNIE, CNNIE,