From c3c77cec300dd05938dcf175ab5fec536184589a Mon Sep 17 00:00:00 2001
From: Philipp Hagemeister <phihag@phihag.de>
Date: Sun, 23 Jun 2013 22:14:22 +0200
Subject: [youjizz] move into own file

---
 youtube_dl/extractor/youjizz.py | 45 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)
 create mode 100644 youtube_dl/extractor/youjizz.py

(limited to 'youtube_dl/extractor/youjizz.py')

diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py
new file mode 100644
index 000000000..d9efac76e
--- /dev/null
+++ b/youtube_dl/extractor/youjizz.py
@@ -0,0 +1,45 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+
+class YouJizzIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('videoid')
+
+        # Get webpage content
+        webpage = self._download_webpage(url, video_id)
+
+        # Get the video title
+        video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
+            webpage, u'title').strip()
+
+        # Get the embed page
+        result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
+        if result is None:
+            raise ExtractorError(u'ERROR: unable to extract embed page')
+
+        embed_page_url = result.group(0).strip()
+        video_id = result.group('videoid')
+
+        webpage = self._download_webpage(embed_page_url, video_id)
+
+        # Get the video URL
+        video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
+            webpage, u'video URL')
+
+        info = {'id': video_id,
+                'url': video_url,
+                'title': video_title,
+                'ext': 'flv',
+                'format': 'flv',
+                'player_url': embed_page_url}
+
+        return [info]
-- 
cgit v1.2.3