Merge pull request #8611 from remitamine/ffmpegfd

[youtube-dl] / youtube_dl / extractor / aol.py

diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py
index abc668912d0b3b9bbc06b93bfeea7b2d3c09c402..b761b2cc4c5d3d4b70766ed56ff5c3529dd39e6b 100644 (file)
--- a/youtube_dl/extractor/aol.py
+++ b/youtube_dl/extractor/aol.py
@@ -1,16 +1,13 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from .fivemin import FiveMinIE
 
 
 class AolIE(InfoExtractor):
     IE_NAME = 'on.aol.com'
-    _VALID_URL = r'http://on\.aol\.com/video/.*-(?P<id>\d+)($|\?)'
+    _VALID_URL = r'(?:aol-video:|http://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
         'md5': '18ef68f48740e86ae94b98da815eec42',
         'info_dict': {
@@ -19,10 +16,31 @@ class AolIE(InfoExtractor):
             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
         },
         'add_ie': ['FiveMin'],
-    }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result('5min:%s' % video_id)
+
+
+class AolFeaturesIE(InfoExtractor):
+    IE_NAME = 'features.aol.com'
+    _VALID_URL = r'http://features\.aol\.com/video/(?P<id>[^/?#]+)'
+
+    _TESTS = [{
+        'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
+        'md5': '7db483bb0c09c85e241f84a34238cc75',
+        'info_dict': {
+            'id': '519507715',
+            'ext': 'mp4',
+            'title': 'What To Watch - February 17, 2016',
+        },
+        'add_ie': ['FiveMin'],
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        self.to_screen('Downloading 5min.com video %s' % video_id)
-        return FiveMinIE._build_result(video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        return self.url_result(self._search_regex(
+            r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
+            webpage, '5min embed url'), 'FiveMin')