[makerschannel] Add new extractor(closes #8839)
authorremitamine <remitamine@gmail.com>
Sat, 12 Mar 2016 21:51:36 +0000 (22:51 +0100)
committerremitamine <remitamine@gmail.com>
Sat, 12 Mar 2016 21:52:53 +0000 (22:52 +0100)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/makerschannel.py [new file with mode: 0644]

index ba9c8b7a5f9cd1a1f6fa5dc33b666bcb0a21b5a0..dc5ecea309fa8fbf6bc9d1b10a7ed2582d093ae5 100644 (file)
@@ -389,6 +389,7 @@ from .lynda import (
 from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
+from .makerschannel import MakersChannelIE
 from .makertv import MakerTVIE
 from .malemotion import MalemotionIE
 from .matchtv import MatchTVIE
diff --git a/youtube_dl/extractor/makerschannel.py b/youtube_dl/extractor/makerschannel.py
new file mode 100644 (file)
index 0000000..f5d00e6
--- /dev/null
@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class MakersChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?makerschannel\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://makerschannel.com/en/zoomin/community-highlights?video_id=849',
+        'md5': '624a512c6969236b5967bf9286345ad1',
+        'info_dict': {
+            'id': '849',
+            'ext': 'mp4',
+            'title': 'Landing a bus on a plane is an epic win',
+            'uploader': 'ZoomIn',
+            'description': 'md5:cd9cca2ea7b69b78be81d07020c97139',
+        }
+    }
+
+    def _real_extract(self, url):
+        id_type, url_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, url_id)
+        video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data')
+
+        def extract_data_val(attr, fatal=False):
+            return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal)
+        minoto_id = self._search_regex(r'/id/([a-zA-Z0-9]+)', extract_data_val('video-src', True), 'minoto id')
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'minoto:%s' % minoto_id,
+            'id': extract_data_val('video-id', True),
+            'title': extract_data_val('title', True),
+            'description': extract_data_val('description'),
+            'thumbnail': extract_data_val('image'),
+            'uploader': extract_data_val('channel'),
+        }