diff options
author | TRox1972 <TRox1972@users.noreply.github.com> | 2016-05-19 03:42:09 +0200 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2016-05-20 22:10:13 +0600 |
commit | 6756602be6b59c7bff57ccaeb33844cdc5636910 (patch) | |
tree | c5790bb93667c48838a0258c4aa9589aba6c7ecc | |
parent | 6c114b12104e8c9d0713d1cb2cd6c4ddc7872b7f (diff) |
[LocalNews8] add extractor (Closes #9200)
-rw-r--r-- | youtube_dl/extractor/extractors.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/localnews8.py | 29 |
2 files changed, 30 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 74aba2d5c..5b96a086d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -396,6 +396,7 @@ from .livestream import ( LivestreamShortenerIE, ) from .lnkgo import LnkGoIE +from .localnews8 import LocalNews8IE from .lovehomeporn import LoveHomePornIE from .lrt import LRTIE from .lynda import ( diff --git a/youtube_dl/extractor/localnews8.py b/youtube_dl/extractor/localnews8.py new file mode 100644 index 000000000..b38d1d58a --- /dev/null +++ b/youtube_dl/extractor/localnews8.py @@ -0,0 +1,29 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class LocalNews8IE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?localnews8\.com/.+?/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.localnews8.com/news/rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings/35183304', + 'md5': '477bdb188f177788c65db27ecb56649b', + 'info_dict': { + 'id': '35183304', + 'ext': 'mp4', + 'title': 'Rexburg business turns carbon fiber scraps into wedding ring', + 'description': 'The process was first invented by Lamborghini and less than a dozen companies around the world use it.', + 'duration': '153', + 'timestamp': '1441844822', + 'uploader_id': 'api', + }} + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + partner_id = self._search_regex(r'partnerId\s*:\s*"(\d+)"', webpage, video_id) + kaltura_id = self._search_regex(r'var\s+videoIdString\s*=\s*"kaltura:(.+)";', webpage, video_id) + + return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura') |