youtube-dl

commit 9dcd6fd3aae77571116ee8b823b6b9224d0ef2ad
parent 98763ee354ffc13a57f28dbd006729affacb6d30
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Fri,  7 Oct 2016 19:22:30 +0800

[generic,commonprotocols] Move mms suuport from GenericIE

And use _generic_* helpers in those extractors

Diffstat:
M
ChangeLog
 | 
2
+-
M
youtube_dl/extractor/commonprotocols.py
 | 
36
++++++++++++++++++++++++++++++------
M
youtube_dl/extractor/generic.py
 | 
24
++----------------------

3 files changed, 33 insertions(+), 29 deletions(-)
diff --git a/ChangeLog b/ChangeLog
@@ -1,7 +1,7 @@
 version <unreleased>
 
 Extractors
-+ [generic] Support direct MMS links (#10838)
++ [commonprotocols] Support direct MMS links (#10838)
 
 
 version 2016.10.02
diff --git a/youtube_dl/extractor/commonprotocols.py b/youtube_dl/extractor/commonprotocols.py
@@ -1,13 +1,9 @@
 from __future__ import unicode_literals
 
-import os
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_unquote,
     compat_urlparse,
 )
-from ..utils import url_basename
 
 
 class RtmpIE(InfoExtractor):
@@ -23,8 +19,8 @@ class RtmpIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
-        title = compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
         return {
             'id': video_id,
             'title': title,
@@ -34,3 +30,31 @@ class RtmpIE(InfoExtractor):
                 'format_id': compat_urlparse.urlparse(url).scheme,
             }],
         }
+
+
+class MmsIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?i)mms://.+'
+
+    _TEST = {
+        # Direct MMS link
+        'url': 'mms://kentro.kaist.ac.kr/200907/MilesReid(0709).wmv',
+        'info_dict': {
+            'id': 'MilesReid(0709)',
+            'ext': 'wmv',
+            'title': 'MilesReid(0709)',
+        },
+        'params': {
+            'skip_download': True,  # rtsp downloads, requiring mplayer or mpv
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+        }
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -27,7 +27,6 @@ from ..utils import (
     unified_strdate,
     unsmuggle_url,
     UnsupportedError,
-    url_basename,
     xpath_text,
 )
 from .brightcove import (
@@ -1412,18 +1411,6 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 3,
         },
-        {
-            # Direct MMS link
-            'url': 'mms://kentro.kaist.ac.kr/200907/MilesReid(0709).wmv',
-            'info_dict': {
-                'id': 'MilesReid(0709)',
-                'ext': 'wmv',
-                'title': 'MilesReid(0709)',
-            },
-            'params': {
-                'skip_download': True,  # rtsp downloads, requiring mplayer or mpv
-            },
-        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -1561,14 +1548,7 @@ class GenericIE(InfoExtractor):
             force_videoid = smuggled_data['force_videoid']
             video_id = force_videoid
         else:
-            video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
-
-        if parsed_url.scheme == 'mms':
-            return {
-                'id': video_id,
-                'title': video_id,
-                'url': url,
-            }
+            video_id = self._generic_id(url)
 
         self.to_screen('%s: Requesting header' % video_id)
 
@@ -1597,7 +1577,7 @@ class GenericIE(InfoExtractor):
 
         info_dict = {
             'id': video_id,
-            'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+            'title': self._generic_title(url),
             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
         }