Merge branch 'lecture2go' of https://github.com/nichdu/youtube-dl into nichdu-lecture2go

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

diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py
index 172b69da18c37135fd0ad0121fc705b1e71ed1e0..639f9182c5484a22f0056e25fc6aa7e56f193df5 100644 (file)
--- a/youtube_dl/extractor/drtuber.py
+++ b/youtube_dl/extractor/drtuber.py
@@ -7,18 +7,19 @@ 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',
+            '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,
         }
@@ -27,35 +28,37 @@ 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'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
+            webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
-        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))
+        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))
 
-        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(' ')
+        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,