diff --git a/youtube_dl/extractor/closertotruth.py b/youtube_dl/extractor/closertotruth.py index 1e5fa1be5..66b41a9d3 100644 --- a/youtube_dl/extractor/closertotruth.py +++ b/youtube_dl/extractor/closertotruth.py @@ -7,7 +7,7 @@ from .common import InfoExtractor class CloserToTruthIE(InfoExtractor): - _VALID_URL = r'http?://(?:www\.)?closertotruth\.com/series/\S+#video-(?P\w+)' + _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/series/[^#]+#video-(?P\w+)' _TESTS = [{ 'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688', 'md5': '2aa5b8971633d86fe32152827846a5b4', @@ -27,12 +27,17 @@ class CloserToTruthIE(InfoExtractor): video_title = self._search_regex(r'(.+) \|.+', webpage, 'video title') - entry_id = self._search_regex(r'.+', webpage, "video entry_id") + entry_id = self._search_regex(r']+id="video-%s"[^>]+data-kaltura="([^"]+)' % video_id, webpage, "video entry_id") interviewee_name = re.sub(r'(<[^>]+>)', '', self._search_regex(r'(.+)', webpage, "video interviewee_name")) video_title = video_title + ' - ' + interviewee_name - # extract the partner id for kaltura.com - p_id = self._search_regex(r'', webpage, "kaltura partner_id") + p_id = self._search_regex(r']+src=["\'].+?partner_id/(\d+)', webpage, "kaltura partner_id") - return self.url_result('kaltura:%s:%s' % (p_id, entry_id), 'Kaltura', entry_id, video_title) + return { + '_type': 'url_transparent', + 'id': entry_id, + 'url': 'kaltura:%s:%s' % (p_id, entry_id), + 'ie_key': 'Kaltura', + 'title': video_title + } \ No newline at end of file