[vice] Re-add extractor (fixes #4120)
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Thu, 6 Nov 2014 20:44:07 +0000 (21:44 +0100)
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Thu, 6 Nov 2014 20:44:07 +0000 (21:44 +0100)
The generic extraction no longer works.

youtube_dl/extractor/__init__.py
youtube_dl/extractor/vice.py [new file with mode: 0644]

index 3f85c99cdd1a0795327eaa5b52191637912a9225..3c1807f1583c78322b5f5600d3ba4f4b71a1a752 100644 (file)
@@ -421,6 +421,7 @@ from .vesti import VestiIE
 from .vevo import VevoIE
 from .vgtv import VGTVIE
 from .vh1 import VH1IE
+from .vice import ViceIE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py
new file mode 100644 (file)
index 0000000..f11ca82
--- /dev/null
@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+import re
+
+from .common import InfoExtractor
+from .ooyala import OoyalaIE
+from ..utils import ExtractorError
+
+
+class ViceIE(InfoExtractor):
+    _VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)'
+
+    _TEST = {
+        '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,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        name = mobj.group('name')
+        webpage = self._download_webpage(url, name)
+        try:
+            embed_code = self._search_regex(
+                r'embedCode=([^&\'"]+)', webpage,
+                'ooyala embed code')
+            ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
+            print(ooyala_url)
+        except ExtractorError:
+            raise ExtractorError('The page doesn\'t contain a video', expected=True)
+        return self.url_result(ooyala_url, ie='Ooyala')
+