youtube-dl

commit 20108c6b9045f819580bf2d6ca687718bd7b0510
parent 9195ef745aba88a08e351af6405a87b5f355c026
Author: Sergey M․ <dstftw@gmail.com>
Date:   Thu, 25 Feb 2016 21:30:19 +0600

[ustudio] Improve (Closes #8574)

Diffstat:
M
youtube_dl/extractor/ustudio.py
 | 
97
+++++++++++++++++++++++++++++++++++++++++++------------------------------------

1 file changed, 53 insertions(+), 44 deletions(-)
diff --git a/youtube_dl/extractor/ustudio.py b/youtube_dl/extractor/ustudio.py
@@ -1,58 +1,67 @@
-# coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+)
 
 
 class UstudioIE(InfoExtractor):
-    IE_NAME = 'uStudio'
-    _VALID_URL = r'http://(?:www\.|v1\.)?ustudio.com/video/(?P<id>[\w\d]+)/.+'
-    _TESTS = [
-        {
-            'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge',
-            'md5': '58bbfca62125378742df01fc2abbdef6',
-            'info_dict': {
-                'id': 'Uxu2my9bgSph',
-                'ext': 'mp4',
-                'title': 'San Francisco: Golden Gate Bridge',
-                'thumbnail': 're:^https?://.*\.jpg$',
-                'description': 'md5:23925500697f2c6d4830e387ba51a9be',
-                'uploader': 'Tony Farley',
-            }
-        },
-    ]
+    _VALID_URL = r'https?://(?:(?:www|v1)\.)?ustudio\.com/video/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
+    _TEST = {
+        'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge',
+        'md5': '58bbfca62125378742df01fc2abbdef6',
+        'info_dict': {
+            'id': 'Uxu2my9bgSph',
+            'display_id': 'san_francisco_golden_gate_bridge',
+            'ext': 'mp4',
+            'title': 'San Francisco: Golden Gate Bridge',
+            'description': 'md5:23925500697f2c6d4830e387ba51a9be',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20111107',
+            'uploader': 'Tony Farley',
+        }
+    }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        doc = self._download_xml(
-            'http://v1.ustudio.com/embed/{0}/ustudio/config.xml'.format(
-                video_id),
-            video_id,
-            note='Downloading video info',
-            errnote='Failed to download video info')
-
-        formats = [
-            {
-                'url': quality.attrib['url'],
-                'width': int_or_none(quality.attrib.get('width')),
-                'height': int_or_none(quality.attrib.get('height')),
-            } for quality in doc.findall('./qualities/quality/video')
-        ]
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        config = self._download_xml(
+            'http://v1.ustudio.com/embed/%s/ustudio/config.xml' % video_id,
+            display_id)
+
+        def extract(kind):
+            return [{
+                'url': 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')]
+
+        formats = extract('video')
         self._sort_formats(formats)
 
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._og_search_title(webpage)
+        upload_date = unified_strdate(self._search_regex(
+            r'(?s)Uploaded by\s*.+?\s*on\s*<span>([^<]+)</span>',
+            webpage, 'upload date', fatal=False))
+        uploader = self._search_regex(
+            r'Uploaded by\s*<a[^>]*>([^<]+)<',
+            webpage, 'uploader', fatal=False)
+
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'formats': formats,
+            'display_id': display_id,
+            'title': title,
             'description': self._og_search_description(webpage),
-            'uploader': self._html_search_regex(
-                r'<a href=".*/user/.+">(.+)</a> on',
-                webpage,
-                'uploader',
-                fatal=False),
+            'thumbnails': extract('image'),
+            'upload_date': upload_date,
+            'uploader': uploader,
+            'formats': formats,
         }