X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/7df4343e553a9942a290e5e1dffe931261ab844e..3ea185de6ec59da4fe6e7a4553101b8398580333:/youtube_dl/extractor/voicerepublic.py diff --git a/youtube_dl/extractor/voicerepublic.py b/youtube_dl/extractor/voicerepublic.py index 254383d..59e1359 100644 --- a/youtube_dl/extractor/voicerepublic.py +++ b/youtube_dl/extractor/voicerepublic.py @@ -4,13 +4,14 @@ import re from .common import InfoExtractor from ..compat import ( - compat_urllib_request, + compat_str, compat_urlparse, ) from ..utils import ( ExtractorError, determine_ext, int_or_none, + sanitized_Request, ) @@ -18,14 +19,14 @@ class VoiceRepublicIE(InfoExtractor): _VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P[0-9a-z-]+)' _TESTS = [{ 'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state', - 'md5': '0554a24d1657915aa8e8f84e15dc9353', + 'md5': 'b9174d651323f17783000876347116e3', 'info_dict': { 'id': '2296', 'display_id': 'watching-the-watchers-building-a-sousveillance-state', 'ext': 'm4a', 'title': 'Watching the Watchers: Building a Sousveillance State', - 'description': 'md5:715ba964958afa2398df615809cfecb1', - 'thumbnail': 're:^https?://.*\.(?:png|jpg)$', + 'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.', + 'thumbnail': r're:^https?://.*\.(?:png|jpg)$', 'duration': 1800, 'view_count': int, } @@ -37,7 +38,7 @@ class VoiceRepublicIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - req = compat_urllib_request.Request( + req = sanitized_Request( compat_urlparse.urljoin(url, '/talks/%s' % display_id)) # Older versions of Firefox get redirected to an "upgrade browser" page req.add_header('User-Agent', 'youtube-dl') @@ -54,7 +55,7 @@ class VoiceRepublicIE(InfoExtractor): if data: title = data['title'] description = data.get('teaser') - talk_id = data.get('talk_id') or display_id + talk_id = compat_str(data.get('talk_id') or display_id) talk = data['talk'] duration = int_or_none(talk.get('duration')) formats = [{