[drtuber] Extract counters

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

diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
index 7b4b195093d4eaab240b7d2256116395a1722f08..172b69da18c37135fd0ad0121fc705b1e71ed1e0 100644 (file)
--- a/youtube_dl/extractor/drtuber.py
+++ b/youtube_dl/extractor/drtuber.py
@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import str_to_int
 
 
 class DrTuberIE(InfoExtractor):
@@ -14,8 +15,12 @@ class DrTuberIE(InfoExtractor):
             'id': '1740434',
             'ext': 'mp4',
             'title': 'Hot Perky Blonde Naked Golf',
+            'like_count': int,
+            'dislike_count': int,
+            'comment_count': int,
             'categories': list,  # NSFW
             'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
         }
     }
 
@@ -35,14 +40,28 @@ class DrTuberIE(InfoExtractor):
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
-        categories_str = self._html_search_regex(
+        like_count = str_to_int(self._html_search_regex(
+            r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
+            webpage, 'like count', fatal=False))
+        dislike_count = str_to_int(self._html_search_regex(
+            r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
+            webpage, 'like count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            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 = categories_str.split(' ')
+        categories = None if cats_str is None else cats_str.split(' ')
 
         return {
             'id': video_id,
             'url': video_url,
             'title': title,
             'thumbnail': thumbnail,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
             'categories': categories,
+            'age_limit': self._rta_search(webpage),
         }