aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/businessinsider.py
diff options
context:
space:
mode:
authorSergey M․ <[email protected]>2018-05-06 21:58:55 +0700
committerSergey M․ <[email protected]>2018-05-06 21:58:55 +0700
commit789b7774a771335c7d0b42c834195bef2e8617c8 (patch)
tree15b3c02ac6aff7185c17dc61f794aab67e1728dd /youtube_dl/extractor/businessinsider.py
parent660a230b2dcc734f018557c7898384ba438e9137 (diff)
downloadyoutube-dl-789b7774a771335c7d0b42c834195bef2e8617c8.tar.gz
youtube-dl-789b7774a771335c7d0b42c834195bef2e8617c8.zip
[businessinsider] Add extractor (closes #16387, closes #16388, closes #16389)
Diffstat (limited to 'youtube_dl/extractor/businessinsider.py')
-rw-r--r--youtube_dl/extractor/businessinsider.py42
1 files changed, 42 insertions, 0 deletions
diff --git a/youtube_dl/extractor/businessinsider.py b/youtube_dl/extractor/businessinsider.py
new file mode 100644
index 000000000..dfcf9bc6b
--- /dev/null
+++ b/youtube_dl/extractor/businessinsider.py
@@ -0,0 +1,42 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .jwplatform import JWPlatformIE
+
+
+class BusinessInsiderIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+ _TESTS = [{
+ 'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6',
+ 'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e',
+ 'info_dict': {
+ 'id': 'hZRllCfw',
+ 'ext': 'mp4',
+ 'title': "Here's how much radiation you're exposed to in everyday life",
+ 'description': 'md5:9a0d6e2c279948aadaa5e84d6d9b99bd',
+ 'upload_date': '20170709',
+ 'timestamp': 1499606400,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://www.businessinsider.nl/5-scientifically-proven-things-make-you-less-attractive-2017-7/',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ jwplatform_id = self._search_regex(
+ (r'data-media-id=["\']([a-zA-Z0-9]{8})',
+ r'id=["\']jwplayer_([a-zA-Z0-9]{8})',
+ r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})'),
+ webpage, 'jwplatform id')
+ return self.url_result(
+ 'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
+ video_id=video_id)