Merge pull request #9110 from remitamine/parse_duration

[youtube-dl] / youtube_dl / extractor / glide.py

diff --git a/youtube_dl/extractor/glide.py b/youtube_dl/extractor/glide.py
index 175d85197c022ae3f2e499546b43ad79101e9753..62ff84835c87b28d18ace1afa5eee19f894d198d 100644 (file)
--- a/youtube_dl/extractor/glide.py
+++ b/youtube_dl/extractor/glide.py
@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import unified_strdate
 
 
 class GlideIE(InfoExtractor):
@@ -14,20 +15,39 @@ class GlideIE(InfoExtractor):
             'id': 'UZF8zlmuQbe4mr+7dCiQ0w==',
             'ext': 'mp4',
             'title': 'Damon Timm\'s Glide message',
-            'thumbnail' : 'http://dk608k4lm7m9j.cloudfront.net/3ee7da5af87065a1eeb8c6c9a864ba5b_2.jpg'
+            'thumbnail': 're:^https?://.*?\.cloudfront\.net/.*\.jpg$',
+            'uploader': 'Damon Timm',
+            'upload_date': '20140919',
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
-        video_url = self._search_regex(r'<source src="(.*?)" type="video/mp4">', webpage, 'video_url')
-        thumbnail_url = self._search_regex(r'<img id="video-thumbnail" src="(.*?)" alt="Video thumbnail">', webpage, 'thumbnail_url')
+
+        title = self._html_search_regex(
+            r'<title>(.+?)</title>', webpage, 'title')
+        video_url = self._proto_relative_url(self._search_regex(
+            r'<source[^>]+src=(["\'])(?P<url>.+?)\1',
+            webpage, 'video URL', default=None,
+            group='url')) or self._og_search_video_url(webpage)
+        thumbnail = self._proto_relative_url(self._search_regex(
+            r'<img[^>]+id=["\']video-thumbnail["\'][^>]+src=(["\'])(?P<url>.+?)\1',
+            webpage, 'thumbnail url', default=None,
+            group='url')) or self._og_search_thumbnail(webpage)
+        uploader = self._search_regex(
+            r'<div[^>]+class=["\']info-name["\'][^>]*>([^<]+)',
+            webpage, 'uploader', fatal=False)
+        upload_date = unified_strdate(self._search_regex(
+            r'<div[^>]+class="info-date"[^>]*>([^<]+)',
+            webpage, 'upload date', fatal=False))
 
         return {
             'id': video_id,
             'title': title,
-            'url' : 'http:' + video_url,
-            'thumbnail' : 'http:' + thumbnail_url
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'upload_date': upload_date,
         }