[sport5] Add new extractor

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 1f1fc0eb269d5c34821692193da1c93849ff8276..c3a4d3c9aa6b0534143c81d182c8f921956de8c3 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -340,6 +340,7 @@ from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .sportdeutschland import SportDeutschlandIE
+from .sport5 import Sport5IE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE

diff --git a/youtube_dl/extractor/sport5.py b/youtube_dl/extractor/sport5.py
new file mode 100644 (file)
index 0000000..9a4e39a
--- /dev/null
+++ b/youtube_dl/extractor/sport5.py
@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from youtube_dl.utils import compat_str, compat_urlretrieve
+
+
+
+class Sport5IE(InfoExtractor):
+    _VALID_URL = r'http://.*sport5\.co\.il'
+    _TESTS = [{
+            'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
+            'info_dict': {
+                'id': 's5-Y59xx1-GUh2',
+                'ext': 'mp4',
+                'title': 'md5:4a2a5eba7e7dc88fdc446cbca8a41c79',
+            }
+        }, {
+            'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE',
+            'info_dict': {
+                'id': 's5-SiXxx1-hKh2',
+                'ext': 'mp4',
+                'title': 'md5:5cb1c6bfc0f16086e59f6683013f8e02',
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        webpage = self._download_webpage(url, '')
+
+        media_id = self._html_search_regex('clipId=(s5-\w+-\w+)', webpage, 'media id')
+
+        xml = self._download_xml(
+            'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % media_id,
+            media_id, 'Downloading media XML')
+
+        title = xml.find('./Title').text
+        duration = xml.find('./Duration').text
+        description = xml.find('./Description').text
+        thumbnail = xml.find('./PosterLinks/PosterIMG').text
+        player_url = xml.find('./PlaybackLinks/PlayerUrl').text
+        file_els = xml.findall('./PlaybackLinks/FileURL')
+
+        formats = []
+
+        for file_el in file_els:
+            bitrate = file_el.attrib.get('bitrate')
+            width = int(file_el.attrib.get('width'))
+            height = int(file_el.attrib.get('height'))
+            formats.append({
+                'url': compat_str(file_el.text),
+                'ext': 'mp4',
+                'height': height,
+                'width': width
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': media_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+            'player_url': player_url,
+        }
\ No newline at end of file