Merge remote-tracking branch 'lenaten/8tracks'

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

diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
index db48a0524b6ae9e1fa0d415eae4f7e1133796d80..ca274dff691f2ad34d027f31bf814c8df850812d 100644 (file)
--- a/youtube_dl/extractor/drtuber.py
+++ b/youtube_dl/extractor/drtuber.py
@@ -13,12 +13,13 @@ class DrTuberIE(InfoExtractor):
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
         'info_dict': {
             'id': '1740434',
+            'display_id': 'hot-perky-blonde-naked-golf',
             'ext': 'mp4',
             'title': 'Hot Perky Blonde Naked Golf',
             'like_count': int,
             'dislike_count': int,
             'comment_count': int,
-            'categories': list,  # NSFW
+            'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
             'thumbnail': 're:https?://.*\.jpg$',
             'age_limit': 18,
         }
@@ -51,9 +52,9 @@ class DrTuberIE(InfoExtractor):
             r'<span class="comments_count">([\d,\.]+)</span>',
             webpage, 'comment count', fatal=False))
 
-        cats_str = self._html_search_regex(
-            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
-        categories = None if cats_str is None else cats_str.split(' ')
+        cats_str = self._search_regex(
+            r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
+        categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
 
         return {
             'id': video_id,