youtube-dl

commit 17f8deeb481a7aa3079d7e11da2c255f893b9e8c
parent b8a03b66601f6af9e6b4009cba634dac6e0d30e6
Author: Sergey M․ <dstftw@gmail.com>
Date:   Wed, 25 Jan 2017 23:27:22 +0700

[extractor/generic] Add support for openload embeds (closes #11536, closes #11812)

Diffstat:
M
youtube_dl/extractor/generic.py
 | 
7
+++++++
M
youtube_dl/extractor/openload.py
 | 
8
++++++++

2 files changed, 15 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -80,6 +80,7 @@ from .piksel import PikselIE
 from .videa import VideaIE
 from .twentymin import TwentyMinutenIE
 from .ustream import UstreamIE
+from .openload import OpenloadIE
 
 
 class GenericIE(InfoExtractor):
@@ -2431,6 +2432,12 @@ class GenericIE(InfoExtractor):
             return _playlist_from_matches(
                 twentymin_urls, ie=TwentyMinutenIE.ie_key())
 
+        # Look for Openload embeds
+        openload_urls = OpenloadIE._extract_urls(webpage)
+        if openload_urls:
+            return _playlist_from_matches(
+                openload_urls, ie=OpenloadIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')
diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_chr
 from ..utils import (
@@ -56,6 +58,12 @@ class OpenloadIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
+            webpage)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)