add support for view count
authorpeugeot <peugeot@psa.fr>
Sat, 30 Aug 2014 18:54:38 +0000 (20:54 +0200)
committerpeugeot <peugeot@psa.fr>
Sat, 30 Aug 2014 18:54:38 +0000 (20:54 +0200)
youtube_dl/extractor/vporn.py

index bdbd7543da0b93617aa53379158cf28a37684ea6..0d182b650779574e520f9f574ab108b7fa819cd4 100644 (file)
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 class VpornIE(InfoExtractor):
     _VALID_URL = r'http?://(?:www\.)?vporn\.com/[a-z]+/(?P<title_dash>[a-z-]+)/(?P<id>\d+)/?'
@@ -30,15 +31,18 @@ class VpornIE(InfoExtractor):
         description = self._html_search_regex(r'<div class="description_txt">(.*?)</div>', webpage, 'description')
         thumbnail = 'http://www.vporn.com' + self._html_search_regex(r'flashvars.imageUrl = "(.*?)"', webpage, 'description')
 
-        mobj = re.search(
-            r'<span class="f_right">duration (?P<minutes>\d+) min (?P<seconds>\d+) sec </span>', webpage)
+        mobj = re.search(r'<span class="f_right">duration (?P<minutes>\d+) min (?P<seconds>\d+) sec </span>', webpage)
         duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
 
+        mobj = re.search(r'<span>((?P<thousands>\d+),)?(?P<units>\d+) VIEWS</span>', webpage)
+        view_count = int(mobj.group('thousands')) * 1000 + int(mobj.group('units')) if mobj else None
+
         return {
             'id': video_id,
             'url': video_url,
             'thumbnail': thumbnail,
             'title': title,
             'description': description,
-            'duration': duration,
+            'duration': int_or_none(duration),
+            'view_count': int_or_none(view_count),
         }