youtube-dl

commit 99d79b8692ae8981aff91cf5b1475516b60eb765
parent b9e7bc55da1c1275737b356efadc06435b8bfa2c
Author: remitamine <remitamine@gmail.com>
Date:   Fri, 13 May 2016 05:21:45 +0100

[ustudio] add support ustudio app/embed urls

Diffstat:
M
youtube_dl/extractor/ustudio.py
 | 
66
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----

1 file changed, 62 insertions(+), 4 deletions(-)
diff --git a/youtube_dl/extractor/ustudio.py b/youtube_dl/extractor/ustudio.py
@@ -6,10 +6,12 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     unified_strdate,
+    unescapeHTML,
 )
 
 
 class UstudioIE(InfoExtractor):
+    IE_NAME = 'ustudio'
     _VALID_URL = r'https?://(?:(?:www|v1)\.)?ustudio\.com/video/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
     _TEST = {
         'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge',
@@ -27,9 +29,7 @@ class UstudioIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
 
         config = self._download_xml(
             'http://v1.ustudio.com/embed/%s/ustudio/config.xml' % video_id,
@@ -37,7 +37,7 @@ class UstudioIE(InfoExtractor):
 
         def extract(kind):
             return [{
-                'url': item.attrib['url'],
+                'url': unescapeHTML(item.attrib['url']),
                 'width': int_or_none(item.get('width')),
                 'height': int_or_none(item.get('height')),
             } for item in config.findall('./qualities/quality/%s' % kind) if item.get('url')]
@@ -65,3 +65,61 @@ class UstudioIE(InfoExtractor):
             'uploader': uploader,
             'formats': formats,
         }
+
+
+class UstudioEmbedIE(InfoExtractor):
+    IE_NAME = 'ustudio:embed'
+    _VALID_URL = r'https?://(?:(?:app|embed)\.)?ustudio\.com/embed/(?P<uid>[^/]+)/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://app.ustudio.com/embed/DeN7VdYRDKhP/Uw7G1kMCe65T',
+        'md5': '47c0be52a09b23a7f40de9469cec58f4',
+        'info_dict': {
+            'id': 'Uw7G1kMCe65T',
+            'ext': 'mp4',
+            'title': '5 Things IT Should Know About Video',
+            'description': 'md5:93d32650884b500115e158c5677d25ad',
+            'uploader_id': 'DeN7VdYRDKhP',
+        }
+    }
+
+    def _real_extract(self, url):
+        uploader_id, video_id = re.match(self._VALID_URL, url).groups()
+        video_data = self._download_json(
+            'http://app.ustudio.com/embed/%s/%s/config.json' % (uploader_id, video_id),
+            video_id)['videos'][0]
+        title = video_data['name']
+
+        formats = []
+        for ext, qualities in video_data.get('transcodes', {}).items():
+            for quality in qualities:
+                quality_url = quality.get('url')
+                if not quality_url:
+                    continue
+                height = int_or_none(quality.get('height'))
+                formats.append({
+                    'format_id': '%s-%dp' % (ext, height) if height else ext,
+                    'url': quality_url,
+                    'width': int_or_none(quality.get('width')),
+                    'height': height,
+                })
+        self._sort_formats(formats)
+
+        thumbnails = []
+        for image in video_data.get('images', []):
+            image_url = image.get('url')
+            if not image_url:
+                continue
+            thumbnails.append({
+                'url': image_url,
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'duration': int_or_none(video_data.get('duration')),
+            'uploader_id': uploader_id,
+            'tags': video_data.get('keywords'),
+            'thumbnails': thumbnails,
+            'formats': formats,
+        }