youtube-dl

commit eade1d7eabd0ab438004750b306c129fc3db9b94
parent 1a94ff68651f806b6ff8e8f663fef684ef3f42ac
Author: Sergey M․ <dstftw@gmail.com>
Date:   Tue,  2 Sep 2014 20:36:26 +0700

[drtuber] Extract counters

Diffstat:
M
youtube_dl/extractor/drtuber.py
 | 
17
+++++++++++++++++

1 file changed, 17 insertions(+), 0 deletions(-)
diff --git 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):
@@ -14,6 +15,9 @@ 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,
@@ -36,6 +40,16 @@ class DrTuberIE(InfoExtractor):
             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))
+
         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(' ')
@@ -45,6 +59,9 @@ class DrTuberIE(InfoExtractor):
             '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),
         }