Add extractor for thescene.com (closes #8929)

1 files changed, 48 insertions, 0 deletions

diff --git a/youtube_dl/extractor/thescene.py b/youtube_dl/extractor/thescene.py
new file mode 100644
index 000000000..08d666eaf
--- /dev/null
+++ b/youtube_dl/extractor/thescene.py
@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..compat import compat_urllib_parse
+from ..utils import qualities
+
+
+class TheSceneIE(InfoExtractor):
+    _VALID_URL = r'https://thescene\.com/watch/[^/]+/(?P<id>[^/#?]+)'
+
+    _TEST = {
+        'url': 'https://thescene.com/watch/vogue/narciso-rodriguez-spring-2013-ready-to-wear',
+        'info_dict': {
+            'id': '520e8faac2b4c00e3c6e5f43',
+            'ext': 'mp4',
+            'title': 'Narciso Rodriguez: Spring 2013 Ready-to-Wear',
+            'display_id': 'narciso-rodriguez-spring-2013-ready-to-wear',
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        player_url = compat_urllib_parse.urljoin(
+            url,
+            self._html_search_regex(
+                r'id=\'js-player-script\'[^>]+src=\'(.+?)\'', webpage, 'player url'))
+
+        self.to_screen(player_url)
+        player = self._download_webpage(player_url, player_url)
+        info = self._parse_json(self._search_regex(r'(?m)var\s+video\s+=\s+({.+?});$', player, 'info json'), display_id)
+
+        qualities_order = qualities(['low', 'high'])
+        formats = [{
+            'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']),
+            'url': f['src'],
+            'quality': qualities_order(f['quality']),
+        } for f in info['sources'][0]]
+        self._sort_formats(formats)
+
+        return {
+            'id': info['id'],
+            'title': info['title'],
+            'formats': formats,
+            'thumbnail': info.get('poster_frame'),
+            'display_id': display_id,
+        }