summary refs log tree commit diff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2015-09-08 14:37:53 +0600
committerSergey M․ <dstftw@gmail.com>2015-09-08 14:37:53 +0600
commit47004d9579839137bff17949f38db2844829bbd6 (patch)
tree1d8e910bdeeb878306153689e42a020b24af3979
parent12810c9cd3c2a5a50ca0ea309d27af2decc8b263 (diff)
downloadyoutube-dl-47004d9579839137bff17949f38db2844829bbd6.tar.gz
youtube-dl-47004d9579839137bff17949f38db2844829bbd6.tar.xz
youtube-dl-47004d9579839137bff17949f38db2844829bbd6.zip
[crunchyroll] Fix uploader and upload date extraction
-rw-r--r--youtube_dl/extractor/crunchyroll.py8
1 files changed, 6 insertions, 2 deletions
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index c5dbc682d..95952bc29 100644
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -275,10 +275,14 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
         if not video_description:
             video_description = None
-        video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
+        video_upload_date = self._html_search_regex(
+            [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
+            webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
         if video_upload_date:
             video_upload_date = unified_strdate(video_upload_date)
-        video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
+        video_uploader = self._html_search_regex(
+            r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
+            'video_uploader', fatal=False)
 
         playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
         playerdata_req = compat_urllib_request.Request(playerdata_url)