youtube-dl

commit: 416c3ca7f53dab76b9e5ec46a0c0335698252c2d
parent 162bcc68dc73706699b559fffdd8bed3db6643b9
Author: Remita Amine <remitamine@gmail.com>
Date:   Fri, 25 Oct 2019 19:27:28 +0100

[odnoklassniki] add support for Schemeless embed extraction

Diffstat:
M
youtube_dl/extractor/generic.py
7
++++---
M
youtube_dl/extractor/odnoklassniki.py
9
+++++++++

2 files changed, 13 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -118,6 +118,7 @@ from .foxnews import FoxNewsIE
 from .viqeo import ViqeoIE
 from .expressen import ExpressenIE
 from .zype import ZypeIE
+from .odnoklassniki import OdnoklassnikiIE
 
 
 class GenericIE(InfoExtractor):
@@ -2627,9 +2628,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'VK')
 
         # Look for embedded Odnoklassniki player
-        mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
-        if mobj is not None:
-            return self.url_result(mobj.group('url'), 'Odnoklassniki')
+        odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
+        if odnoklassniki_url:
+            return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
 
         # Look for embedded ivi player
         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_etree_fromstring,
@@ -121,6 +123,13 @@ class OdnoklassnikiIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
     def _real_extract(self, url):
         start_time = int_or_none(compat_parse_qs(
             compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0])