From: Steven Gosseling Date: Fri, 26 Feb 2016 12:31:52 +0000 (+0100) Subject: [closertotruth] Add extractor X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=41c1023300596f62dff93d9275f5e4d7a6762e66;p=youtube-dl [closertotruth] Add extractor Removed print statement from code. Replaced two regex searches with the corret ones. Removed some unnecessary semicolumns fixed title extraction refactored everything to search_regex processed comments on commit 5650b0d, fixed feedback from flake8 Improved regexes and returns info dict now. Added support for closertotruth interview URL Added support for episodes page --- diff --git a/youtube_dl/extractor/closertotruth.py b/youtube_dl/extractor/closertotruth.py new file mode 100644 index 000000000..d04ff5e4f --- /dev/null +++ b/youtube_dl/extractor/closertotruth.py @@ -0,0 +1,69 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class CloserToTruthIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(episodes/|(series|interviews)/(?:[^#]+#video-)?(?P\d+))' + _TESTS = [ + { + 'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688', + 'md5': '5c548bde260a9247ddfdc07c7458ed29', + 'info_dict': { + 'id': '0_zof1ktre', + 'ext': 'mov', + 'title': 'Solutions to the Mind-Body Problem?', + 'upload_date': '20140221', + 'timestamp': 1392956007, + 'uploader_id': 'CTTXML' + } + }, + { + 'url': 'http://closertotruth.com/interviews/1725', + 'md5': 'b00598fd6a38372edb976408f72c5792', + 'info_dict': { + 'id': '0_19qv5rn1', + 'ext': 'mov', + 'title': 'AyaFr-002 - Francisco J. Ayala', + 'upload_date': '20140307', + 'timestamp': 1394236431, + 'uploader_id': 'CTTXML' + } + }, + { + 'url': 'http://closertotruth.com/episodes/how-do-brains-work', + 'md5': '4dd96aa0a5c296afa5c0bd24895c2f16', + 'info_dict': { + 'id': '0_iuxai6g6', + 'ext': 'mov', + 'title': 'How do Brains Work?', + 'upload_date': '20140221', + 'timestamp': 1392956024, + 'uploader_id': 'CTTXML' + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_title = self._search_regex(r'(.+) \|.+', webpage, 'video title') + + entry_id = self._search_regex(r']+id="(?:video-%s|embed-kaltura)"[^>]+data-kaltura="([^"]+)' % video_id, webpage, "video entry_id") + + interviewee_name = self._search_regex(r'
(.*).+', webpage, "video interviewee_name", False) + + if interviewee_name: + video_title = video_title + ' - ' + interviewee_name + + p_id = self._search_regex(r']+src=["\'].+?partner_id/(\d+)', webpage, "kaltura partner_id") + + return { + '_type': 'url_transparent', + 'id': entry_id, + 'url': 'kaltura:%s:%s' % (p_id, entry_id), + 'ie_key': 'Kaltura', + 'title': video_title + }