R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Added support for closertotruth interview URL

Browse Source
This commit is contained in:
Steven Gosseling 2016-03-08 15:56:49 +01:00
parent 29331a4d18
commit 13d7892560
1 changed files with 15 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
youtube_dl/extractor/closertotruth.py
View File

@ -1,13 +1,11 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
class CloserToTruthIE(InfoExtractor): class CloserToTruthIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?closertotruth\.com/series/[^#]+#video-(?P<id>\w+)' _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(series|interviews)/(?:[^#]+#video-)?(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688', 'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688',
'md5': '2aa5b8971633d86fe32152827846a5b4', 'md5': '2aa5b8971633d86fe32152827846a5b4',
@ -18,6 +16,16 @@ class CloserToTruthIE(InfoExtractor):
'upload_date': '20140307', 'upload_date': '20140307',
'timestamp': 1394236392, 'timestamp': 1394236392,
'uploader_id': 'CTTXML' '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'
} }
}] }]
@ -27,8 +35,9 @@ class CloserToTruthIE(InfoExtractor):
video_title = self._search_regex(r'<title>(.+) \|.+</title>', webpage, 'video title') video_title = self._search_regex(r'<title>(.+) \|.+</title>', webpage, 'video title')
entry_id = self._search_regex(r'<a[^>]+id="video-%s"[^>]+data-kaltura="([^"]+)' % video_id, webpage, "video entry_id") entry_id = self._search_regex(r'<a[^>]+id="(?:video-%s|embed-kaltura)"[^>]+data-kaltura="([^"]+)' % video_id, webpage, "video entry_id")
interviewee_name = re.sub(r'(<[^>]+>)', '', self._search_regex(r'<a href="\S+" id="video-' + video_id + '" data-kaltura="\w+">(.+)<span.+<\/a>', webpage, "video interviewee_name"))
interviewee_name = self._search_regex(r'<div id="(?:node_interview_full_group_white_wrapper|node_interview_series_full_group_ajax_content)"(?:.|\n)*<h3>(.*)<\/h3>', webpage, "video interviewee_name")
video_title = video_title + ' - ' + interviewee_name video_title = video_title + ' - ' + interviewee_name
@ -40,4 +49,4 @@ class CloserToTruthIE(InfoExtractor):
'url': 'kaltura:%s:%s' % (p_id, entry_id), 'url': 'kaltura:%s:%s' % (p_id, entry_id),
'ie_key': 'Kaltura', 'ie_key': 'Kaltura',
'title': video_title 'title': video_title
} }