Add support for Vporn

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 1479d998a264b5ec7206d15f7acc5465dd309b6a..6d94984def2b1aa5e7a3e0c6c4720df6f291da47 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -393,6 +393,7 @@ from .vine import (
 from .viki import VikiIE
 from .vk import VKIE
 from .vodlocker import VodlockerIE
+from .vporn import VpornIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
 from .vulture import VultureIE

diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py
new file mode 100644 (file)
index 0000000..bdbd754
--- /dev/null
+++ b/youtube_dl/extractor/vporn.py
@@ -0,0 +1,44 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+class VpornIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?vporn\.com/[a-z]+/(?P<title_dash>[a-z-]+)/(?P<id>\d+)/?'
+    _TEST = {
+        'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
+        'md5': 'facf37c1b86546fa0208058546842c55',
+        'info_dict': {
+            'id': '497944',
+            'ext': 'mp4',
+            'title': 'Violet On Her 19th Birthday',
+            'description': 'Violet dances in front of the camera which is sure to get you horny.',
+            'duration': 393,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(r'<title>(.*?) - Vporn Video</title>', webpage, 'title')
+        video_url = self._html_search_regex(r'flashvars.videoUrlMedium  = "(.*?)"', webpage, 'video_url')
+        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)
+        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'duration': duration,
+        }