mirror of https://github.com/blackjack4494/yt-dlc
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
76 lines
2.3 KiB
Python
76 lines
2.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import (
|
|
js_to_json,
|
|
smuggle_url,
|
|
)
|
|
|
|
|
|
class CNBCIE(InfoExtractor):
|
|
_VALID_URL = r'https?://video\.cnbc\.com/gallery/\?video=(?P<id>[0-9]+)'
|
|
_TEST = {
|
|
'url': 'http://video.cnbc.com/gallery/?video=3000503714',
|
|
'info_dict': {
|
|
'id': '3000503714',
|
|
'ext': 'mp4',
|
|
'title': 'Fighting zombies is big business',
|
|
'description': 'md5:0c100d8e1a7947bd2feec9a5550e519e',
|
|
'timestamp': 1459332000,
|
|
'upload_date': '20160330',
|
|
'uploader': 'NBCU-CNBC',
|
|
},
|
|
'params': {
|
|
# m3u8 download
|
|
'skip_download': True,
|
|
},
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
return {
|
|
'_type': 'url_transparent',
|
|
'ie_key': 'ThePlatform',
|
|
'url': smuggle_url(
|
|
'http://link.theplatform.com/s/gZWlPC/media/guid/2408950221/%s?mbr=true&manifest=m3u' % video_id,
|
|
{'force_smil_url': True}),
|
|
'id': video_id,
|
|
}
|
|
|
|
|
|
class CNBCNewIE(InfoExtractor):
|
|
IE_NAME = 'CNBC:new'
|
|
_VALID_URL = r'https?://(?:www)?\.cnbc\.com/video.*/(?P<id>[^.]+)'
|
|
_TEST = {
|
|
'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html',
|
|
'info_dict': {
|
|
'id': '7000031301',
|
|
'ext': 'mp4',
|
|
'title': 'Trump: I don\'t necessarily agree with raising rates',
|
|
'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3',
|
|
'timestamp': 1531958400,
|
|
'upload_date': '20180719',
|
|
'uploader': 'NBCU-CNBC',
|
|
},
|
|
'params': {
|
|
# m3u8 download
|
|
'skip_download': True,
|
|
},
|
|
}
|
|
|
|
CNBC_URL_TEMPLATE = 'http://video.cnbc.com/gallery/?video=%s'
|
|
|
|
def _real_extract(self, url):
|
|
display_id = self._match_id(url)
|
|
webpage = self._download_webpage(url, display_id)
|
|
video_id = self._parse_json(
|
|
self._search_regex(
|
|
r'(?s).*<script[^>]*>.*?({.+?content_id.+?}).*?</script>',
|
|
webpage, display_id),
|
|
display_id, transform_source=js_to_json
|
|
)['content_id']
|
|
|
|
return self.url_result(self.CNBC_URL_TEMPLATE % video_id, 'CNBC')
|