X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdrtuber.py;h=639f9182c5484a22f0056e25fc6aa7e56f193df5;hb=027eb5a6b041a91ca7fdd61826daaea24bec1cfb;hp=7b4b195093d4eaab240b7d2256116395a1722f08;hpb=94388f50b39e750f81e9baeb9fea0354f209d4e9;p=youtube-dl

diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
index 7b4b19509..639f9182c 100644
--- a/youtube_dl/extractor/drtuber.py
+++ b/youtube_dl/extractor/drtuber.py
@@ -3,46 +3,68 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import str_to_int
 
 
 class DrTuberIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<title_dash>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
     _TEST = {
         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
         'info_dict': {
             'id': '1740434',
+            'display_id': 'hot-perky-blonde-naked-golf',
             'ext': 'mp4',
-            'title': 'Hot Perky Blonde Naked Golf',
-            'categories': list,  # NSFW
+            'title': 'hot perky blonde naked golf',
+            'like_count': int,
+            'dislike_count': int,
+            'comment_count': int,
+            'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
             'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, display_id)
 
         video_url = self._html_search_regex(
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
+            [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
+            webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
-        categories_str = self._html_search_regex(
-            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
-        categories = categories_str.split(' ')
+        def extract_count(id_, name):
+            return str_to_int(self._html_search_regex(
+                r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
+                webpage, '%s count' % name, fatal=False))
+
+        like_count = extract_count('rate_likes', 'like')
+        dislike_count = extract_count('rate_dislikes', 'dislike')
+        comment_count = extract_count('comments_count', 'comment')
+
+        cats_str = self._search_regex(
+            r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
+        categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
 
         return {
             'id': video_id,
+            'display_id': display_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),
         }