From f2cd958c0a09bca580a955c60c19e177f6ff45b8 Mon Sep 17 00:00:00 2001
From: mc2avr <mc2avr@googlemail.com>
Date: Thu, 23 May 2013 21:42:03 +0200
Subject: add ZDFIE and _download_with_mplayer(mms://,rtsp://)

---
 youtube_dl/InfoExtractors.py | 59 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

(limited to 'youtube_dl/InfoExtractors.py')

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 42e4d0352..4ca744daf 100755
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -4052,6 +4052,64 @@ class ARDIE(InfoExtractor):
             info["url"] = stream["video_url"]
         return [info]
 
+class ZDFIE(InfoExtractor):
+    _VALID_URL = r'^http://www\.zdf\.de\/ZDFmediathek\/(.*beitrag\/video\/)(?P<video_id>[^/\?]+)(?:\?.*)?'
+    _TITLE = r'<h1(?: class="beitragHeadline")?>(?P<title>.*)</h1>'
+    _MEDIA_STREAM = r'<a href="(?P<video_url>.+(?P<media_type>.streaming).+/zdf/(?P<quality>[^\/]+)/[^"]*)".+class="play".+>'
+    _MMS_STREAM = r'href="(?P<video_url>mms://[^"]*)"'
+    _RTSP_STREAM = r'(?P<video_url>rtsp://[^"]*.mp4)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        video_id = mobj.group('video_id')
+
+        html = self._download_webpage(url, video_id)
+        streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
+        if streams is None:
+            raise ExtractorError(u'No media url found.')
+
+        # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' und mms url
+        # s['media_type'] == 'hstreaming' -> use 'Quicktime' und rtsp url
+        # choose first/default media type and highest quality for now
+        for s in streams:        #find 300 - dsl1000mbit
+            if s['quality'] == '300' and s['media_type'] == 'wstreaming':
+                stream_=s
+                break
+        for s in streams:        #find veryhigh - dsl2000mbit
+            if s['quality'] == 'veryhigh' and s['media_type'] == 'wstreaming': # 'hstreaming' - rtsp is not working
+                stream_=s
+                break
+        if stream_ is None:
+            raise ExtractorError(u'No stream found.')
+
+        media_link = self._download_webpage(stream_['video_url'], video_id,'Get stream URL')
+
+        self.report_extraction(video_id)
+        mobj = re.search(self._TITLE, html)
+        if mobj is None:
+            raise ExtractorError(u'Cannot extract title')
+        title = unescapeHTML(mobj.group('title'))
+
+        mobj = re.search(self._MMS_STREAM, media_link)
+        if mobj is None:
+            mobj = re.search(self._RTSP_STREAM, media_link)
+            if mobj is None:
+                raise ExtractorError(u'Cannot extract mms:// or rtsp:// URL')
+        mms_url = mobj.group('video_url')
+
+        mobj = re.search('(.*)[.](?P<ext>[^.]+)', mms_url)
+        if mobj is None:
+            raise ExtractorError(u'Cannot extract extention')
+        ext = mobj.group('ext')
+
+        return [{'id': video_id,
+                 'url': mms_url,
+                 'title': title,
+                 'ext': ext
+                 }]
+
 class TumblrIE(InfoExtractor):
     _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
 
@@ -4440,6 +4498,7 @@ def gen_extractors():
         SpiegelIE(),
         LiveLeakIE(),
         ARDIE(),
+        ZDFIE(),
         TumblrIE(),
         BandcampIE(),
         RedTubeIE(),
-- 
cgit v1.2.3