Add support for sunporno.com
authorpeugeot <peugeot@psa.fr>
Sun, 31 Aug 2014 10:48:34 +0000 (12:48 +0200)
committerpeugeot <peugeot@psa.fr>
Sun, 31 Aug 2014 10:48:34 +0000 (12:48 +0200)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/sunporno.py [new file with mode: 0644]

index 1479d998a264b5ec7206d15f7acc5465dd309b6a..72b01505de24f40ade0819498b9def252743627f 100644 (file)
@@ -322,6 +322,7 @@ from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
+from .sunporno import SunPornoIE
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py
new file mode 100644 (file)
index 0000000..2a193de
--- /dev/null
@@ -0,0 +1,57 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
+
+
+class SunPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.sunporno.com/videos/807778/',
+        'md5': '6457d3c165fd6de062b99ef6c2ff4c86',
+        'info_dict': {
+            'id': '807778',
+            'ext': 'flv',
+            'title': 'md5:0a400058e8105d39e35c35e7c5184164',
+            'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
+            'duration': 302,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(
+            r'videoSource\s*=\s*\'<source\s*src="([^"]*)"', webpage, 'video URL')
+
+        title = self._html_search_regex(r'<title>([^<]*)</title>', webpage, 'title')
+
+        description = self._html_search_regex(
+            r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False)
+        
+        thumbnail = self._html_search_regex(
+            r'poster="([^"]*)"', webpage, 'thumbnail', fatal=False)
+
+        duration = parse_duration(self._search_regex(
+            r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False))
+
+        view_count = int_or_none(self._html_search_regex(
+            r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+        }