Imported Upstream version 2015.11.10

[youtubedl] / youtube_dl / extractor / vice.py

diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py
index 6b93afa50f765a0be24265b3154ee8f670f68312..01af7a99574401b38e487b01dd5104e674740bbc 100644 (file)
--- a/youtube_dl/extractor/vice.py
+++ b/youtube_dl/extractor/vice.py
@@ -1,4 +1,4 @@
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from .ooyala import OoyalaIE
@@ -6,33 +6,34 @@ from ..utils import ExtractorError
 
 
 class ViceIE(InfoExtractor):
-    _VALID_URL = r'http://www.vice.com/.*?/(?P<name>.+)'
+    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)+(?P<id>.+)'
 
-    _TEST = {
-        u'url': u'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
-        u'file': u'43cW1mYzpia9IlestBjVpd23Yu3afAfp.mp4',
-        u'info_dict': {
-            u'title': u'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
-        },
-        u'params': {
-            # Requires ffmpeg (m3u8 manifest)
-            u'skip_download': True,
-        },
-    }
+    _TESTS = [
+        {
+            'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
+            'info_dict': {
+                'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
+                'ext': 'mp4',
+                'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
+            },
+            'params': {
+                # Requires ffmpeg (m3u8 manifest)
+                'skip_download': True,
+            },
+        }, {
+            'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
+            'only_matching': True,
+        }
+    ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
-        webpage = self._download_webpage(url, name)
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
         try:
-            ooyala_url = self._og_search_video_url(webpage)
+            embed_code = self._search_regex(
+                r'embedCode=([^&\'"]+)', webpage,
+                'ooyala embed code')
+            ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
         except ExtractorError:
-            try:
-                embed_code = self._search_regex(
-                    r'OO.Player.create\(\'ooyalaplayer\', \'(.+?)\'', webpage,
-                    u'ooyala embed code')
-                ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
-            except ExtractorError:
-                raise ExtractorError(u'The page doesn\'t contain a video', expected=True)
+            raise ExtractorError('The page doesn\'t contain a video', expected=True)
         return self.url_result(ooyala_url, ie='Ooyala')
-