[SpankBang] Add new extractor

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 0f7d44616d5dd18f0e611a43b9c005da9b66bada..e6fdf12977e2316adc842daf9adb97b2d7edb201 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -471,6 +471,7 @@ from .southpark import (
     SouthparkDeIE,
 )
 from .space import SpaceIE
+from .spankbang import SpankBangIE
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE

diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py
new file mode 100644 (file)
index 0000000..8e845ef
--- /dev/null
+++ b/youtube_dl/extractor/spankbang.py
@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+import re
+
+class SpankBangIE(InfoExtractor):
+    """Extractor for http://spankbang.com"""
+    
+    _VALID_URL = r"https?://(?:www\.)?spankbang\.com/(?P<id>\w+)/video/.*"
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r"<h1>(?:<img.+?>)?(.*?)</h1>", webpage, "title")
+        
+        stream_key = self._html_search_regex(r"""var\s+stream_key\s*[=]\s*['"](.+?)['"]\s*;""", webpage, "stream_key")
+        
+        qualities = re.findall(r"<span.+?>([0-9]+p).*?</span>", webpage)
+        
+        formats = []
+        for q in sorted(qualities):
+            formats.append({
+                "format_id": q,
+                "format": q,
+                "ext": "mp4",
+                "url": "http://spankbang.com/_{}/{}/title/{}__mp4".format(video_id, stream_key, q)
+            })
+
+        return {
+            "id": video_id,
+            "title": title,
+            "description": self._og_search_description(webpage),
+            "formats": formats
+        }
+
+# vim: tabstop=4 expandtab