aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/zdf.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-06-23 20:24:07 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2013-06-23 20:24:07 +0200
commitd5822b96b00fce48e04a14953c4cb25cef1cdbaf (patch)
tree600e8a81e4b95e2316bd2f36e81618d1ef91adeb /youtube_dl/extractor/zdf.py
parentb3d14cbfa7d593a74cf1423ec58265abff6758a3 (diff)
Move ARD, Arte, ZDF into their own files
Diffstat (limited to 'youtube_dl/extractor/zdf.py')
-rw-r--r--youtube_dl/extractor/zdf.py65
1 files changed, 65 insertions, 0 deletions
diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py
new file mode 100644
index 000000000..418509cb9
--- /dev/null
+++ b/youtube_dl/extractor/zdf.py
@@ -0,0 +1,65 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ unescapeHTML,
+)
+
+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' and mms url
+ # s['media_type'] == 'hstreaming' -> use 'Quicktime' and 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
+ }]