Merge remote-tracking branch 'Oteng/master'

diff --git a/AUTHORS b/AUTHORS
index 9b548cf25fe9365d1867995bce1639cbf5153ed7..a63c97ae01d700095c3fed0a6c697f8410aee5bd 100644 (file)
--- a/AUTHORS
+++ b/AUTHORS
@@ -99,3 +99,4 @@ Max Reimann
 Cédric Luthi
 Thijs Vermeir
 Joel Leclerc
+Christopher Krooss

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 0c872938489f81aa5291ec5ce4f2ab56aa22c479..8e47bd60dce440f383720fde04e31679d6554cd5 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -325,6 +325,7 @@ from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .quickvid import QuickVidIE
 from .radiode import RadioDeIE
+from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 2d871f8b41a6334152ae4677e275fb650717b14e..7a5bf939237ff45731fd3befca5ad0b7dfc0df1f 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -926,7 +926,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded TED player
         mobj = re.search(
-                r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'TED')
 

diff --git a/youtube_dl/extractor/radiobremen.py b/youtube_dl/extractor/radiobremen.py
new file mode 100644 (file)
index 0000000..0d70631
--- /dev/null
+++ b/youtube_dl/extractor/radiobremen.py
@@ -0,0 +1,63 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class RadioBremenIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?radiobremen\.de/mediathek/(?:index\.html)?\?id=(?P<id>[0-9]+)'
+    IE_NAME = 'radiobremen'
+
+    _TEST = {
+        'url': 'http://www.radiobremen.de/mediathek/index.html?id=114720',
+        'info_dict': {
+            'id': '114720',
+            'ext': 'mp4',
+            'duration': 1685,
+            'width': 512,
+            'title': 'buten un binnen vom 22. Dezember',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'description': 'Unter anderem mit diesen Themen: 45 Flüchtlinge sind in Worpswede angekommen +++ Freies Internet für alle: Bremer arbeiten an einem flächendeckenden W-Lan-Netzwerk +++ Aktivisten kämpfen für das Unibad +++ So war das Wetter 2014 +++',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        meta_url = "http://www.radiobremen.de/apps/php/mediathek/metadaten.php?id=%s" % video_id
+        meta_doc = self._download_webpage(
+            meta_url, video_id, 'Downloading metadata')
+        title = self._html_search_regex(
+            r"<h1.*>(?P<title>.+)</h1>", meta_doc, "title")
+        description = self._html_search_regex(
+            r"<p>(?P<description>.*)</p>", meta_doc, "description", fatal=False)
+        duration = parse_duration(self._html_search_regex(
+            r"L&auml;nge:</td>\s+<td>(?P<duration>[0-9]+:[0-9]+)</td>",
+            meta_doc, "duration", fatal=False))
+
+        page_doc = self._download_webpage(
+            url, video_id, 'Downloading video information')
+        mobj = re.search(
+            r"ardformatplayerclassic\(\'playerbereich\',\'(?P<width>[0-9]+)\',\'.*\',\'(?P<video_id>[0-9]+)\',\'(?P<secret>[0-9]+)\',\'(?P<thumbnail>.+)\',\'\'\)",
+            page_doc)
+        video_url = (
+            "http://dl-ondemand.radiobremen.de/mediabase/%s/%s_%s_%s.mp4" %
+            (video_id, video_id, mobj.group("secret"), mobj.group('width')))
+
+        formats = [{
+            'url': video_url,
+            'ext': 'mp4',
+            'width': int(mobj.group("width")),
+        }]
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+            'thumbnail': mobj.group('thumbnail'),
+        }