diff options
| author | Déstin Reed <TRox1972@noreply.github.com> | 2017-01-08 19:28:16 +0100 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-01-09 22:57:14 +0700 |
| commit | 7f0bdc7a31f6a1f9f71189603906d64af0a6ab74 (patch) | |
| tree | e8d1a8620b13d1b4b208e12d34d7675ce90afd4e | |
| parent | 022a5d663bc654a2d5f650f209dd7a8f86ac38a8 (diff) | |
[inc] Add extractor
| -rw-r--r-- | youtube_dl/extractor/extractors.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/inc.py | 40 |
2 files changed, 41 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 2e80ef152..5ba8efb0e 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -395,6 +395,7 @@ from .imgur import ( ImgurAlbumIE, ) from .ina import InaIE +from .inc import IncIE from .indavideo import ( IndavideoIE, IndavideoEmbedIE, diff --git a/youtube_dl/extractor/inc.py b/youtube_dl/extractor/inc.py new file mode 100644 index 000000000..279e53c15 --- /dev/null +++ b/youtube_dl/extractor/inc.py @@ -0,0 +1,40 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class IncIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?inc\.com(?:/[\w-]+)+/(?P<id>[\w-]+)(?:\.html)?' + _TESTS = [{ + 'url': 'http://www.inc.com/tip-sheet/bill-gates-says-these-5-books-will-make-you-smarter.html', + 'md5': '7416739c9c16438c09fa35619d6ba5cb', + 'info_dict': { + 'id': '1_wqig47aq', + 'ext': 'mov', + 'title': 'Bill Gates Says These 5 Books Will Make You Smarter', + 'description': 'md5:bea7ff6cce100886fc1995acb743237e', + 'timestamp': 1474414430, + 'upload_date': '20160920', + 'uploader_id': 'video@inc.com', + }, + }, { + 'url': 'http://www.inc.com/video/david-whitford/founders-forum-tripadvisor-steve-kaufer-most-enjoyable-moment-for-entrepreneur.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + partner_id = self._search_regex( + r'var\s+_bizo_data_partner_id\s*=\s*"(\d+)";', + webpage, + 'partner id') + + kaltura_id = self._parse_json(self._search_regex( + r'pageInfo\.videos\s*=\s*\[(.+)\];', + webpage, + 'kaltura id'), + display_id)['vid_kaltura_id'] + + return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura') |