aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorgfabiano <gfabiano40@gmail.com>2018-07-30 18:15:20 +0200
committerSergey M․ <dstftw@gmail.com>2018-10-29 23:54:14 +0700
commitffa7b2bfee7b94191ffc20ef00c22f708c97cddf (patch)
tree12d50496c833dc722625448f6ab46afdf3b3574d /youtube_dl/extractor
parent2943397e8701d3dcd28433e485e50459fdbda62a (diff)
[cbnc] Add support for new URL schema (closes #14193)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/cnbc.py41
-rw-r--r--youtube_dl/extractor/extractors.py5
2 files changed, 44 insertions, 2 deletions
diff --git a/youtube_dl/extractor/cnbc.py b/youtube_dl/extractor/cnbc.py
index d354d9f95..35c0b6124 100644
--- a/youtube_dl/extractor/cnbc.py
+++ b/youtube_dl/extractor/cnbc.py
@@ -1,8 +1,12 @@
# coding: utf-8
from __future__ import unicode_literals
+
from .common import InfoExtractor
-from ..utils import smuggle_url
+from ..utils import (
+ js_to_json,
+ smuggle_url,
+)
class CNBCIE(InfoExtractor):
@@ -34,3 +38,38 @@ class CNBCIE(InfoExtractor):
{'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')
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index f013d13c3..93574907b 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -209,7 +209,10 @@ from .cloudy import CloudyIE
from .clubic import ClubicIE
from .clyp import ClypIE
from .cmt import CMTIE
-from .cnbc import CNBCIE
+from .cnbc import (
+ CNBCIE,
+ CNBCNewIE,
+)
from .cnn import (
CNNIE,
CNNBlogsIE,