[krasview] Add extractor (Closes #3313)
authorSergey M․ <dstftw@gmail.com>
Wed, 23 Jul 2014 12:29:15 +0000 (19:29 +0700)
committerSergey M․ <dstftw@gmail.com>
Wed, 23 Jul 2014 12:29:15 +0000 (19:29 +0700)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/krasview.py [new file with mode: 0644]

index 8d63d9281d68d496b65d025666fd4d8a2c863b06..80aa2dfbb768c4263c94820add6a856915d42813 100644 (file)
@@ -151,6 +151,7 @@ from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .kontrtube import KontrTubeIE
+from .krasview import KrasViewIE
 from .ku6 import Ku6IE
 from .la7 import LA7IE
 from .lifenews import LifeNewsIE
diff --git a/youtube_dl/extractor/krasview.py b/youtube_dl/extractor/krasview.py
new file mode 100644 (file)
index 0000000..6f3d234
--- /dev/null
@@ -0,0 +1,59 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unescapeHTML,
+)
+
+
+class KrasViewIE(InfoExtractor):
+    IE_DESC = 'Красвью'
+    _VALID_URL = r'https?://krasview\.ru/video/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://krasview.ru/video/512228',
+        'md5': '3b91003cf85fc5db277870c8ebd98eae',
+        'info_dict': {
+            'id': '512228',
+            'ext': 'mp4',
+            'title': 'Снег, лёд, заносы',
+            'description': 'Снято в городе Нягань, в Ханты-Мансийском автономном округе.',
+            'duration': 27,
+            'thumbnail': 're:^https?://.*\.jpg',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        flashvars = json.loads(self._search_regex(
+            r'flashvars\s*:\s*({.+?})\s*}\);', webpage, 'flashvars'))
+
+        video_url = flashvars['url']
+        title = unescapeHTML(flashvars['title'])
+        description = unescapeHTML(flashvars.get('subtitle') or self._og_search_description(webpage, default=None))
+        thumbnail = flashvars['image']
+        duration = int(flashvars['duration'])
+        filesize = int(flashvars['size'])
+        width = int_or_none(self._og_search_property('video:width', webpage, 'video width'))
+        height = int_or_none(self._og_search_property('video:height', webpage, 'video height'))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'filesize': filesize,
+            'width': width,
+            'height': height,
+        }