X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdrtuber.py;h=e8870c4607d4e4f0293f134610ed8f1f8d48e956;hb=6496ccb41398971373a2f7162a0684dd12f0b56e;hp=9a13925b46cb5e6e72810c28fbfed27ea6ce52cd;hpb=11fc065c5733171efcf3db75ce1de3ada143f433;p=youtube-dl

diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
index 9a13925b4..e8870c460 100644
--- a/youtube_dl/extractor/drtuber.py
+++ b/youtube_dl/extractor/drtuber.py
@@ -3,18 +3,25 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    NO_DEFAULT,
+    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,
+            'comment_count': int,
+            'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
             'thumbnail': 're:https?://.*\.jpg$',
             'age_limit': 18,
         }
@@ -23,28 +30,47 @@ class DrTuberIE(InfoExtractor):
     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'class="title_watch"[^>]*><p>([^<]+)<',
+             r'<p[^>]+class="title_substrate">([^<]+)</p>',
+             r'<title>([^<]+) - \d+'),
+            webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', 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(' ')
+        def extract_count(id_, name, default=NO_DEFAULT):
+            return str_to_int(self._html_search_regex(
+                r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
+                webpage, '%s count' % name, default=default, fatal=False))
+
+        like_count = extract_count('rate_likes', 'like')
+        dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
+        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),
         }