Merge branch 'master' of https://github.com/linhua55/youtube-dl into linhua55-master

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 5d41b6319a1ef857a95d51af3b0a378ab6260e12..ec748ed9f4c7b81f4e49270a9857ba429a2cd108 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -48,6 +48,7 @@ from .vimeo import VimeoIE
 from .dailymotion import DailymotionCloudIE
 from .onionstudios import OnionStudiosIE
 from .snagfilms import SnagFilmsEmbedIE
+from .screenwavemedia import ScreenwaveMediaIE
 
 
 class GenericIE(InfoExtractor):
@@ -1001,6 +1002,16 @@ class GenericIE(InfoExtractor):
                 'description': 'New experience with Acrobat DC',
                 'duration': 248.667,
             },
+        },
+        # ScreenwaveMedia embed
+        {
+            'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
+            'md5': '24ace5baba0d35d55c6810b51f34e9e0',
+            'info_dict': {
+                'id': 'cinemasnob-55d26273809dd',
+                'ext': 'mp4',
+                'title': 'cinemasnob',
+            },
         }
     ]
 
@@ -1719,13 +1730,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(snagfilms_url)
 
         # Look for ScreenwaveMedia embeds
-        mobj = re.search(
-            r'<script[^>]+src=[\'"](http://player\d?\.screenwavemedia\.com/player\.php\?id=[A-Za-z0-9-]+)[\'"]',
-            webpage)
+        mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
         if mobj is not None:
-            return self.url_result(
-                unescapeHTML(mobj.group(1)),
-                'ScreenwaveMedia')
+            return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
 
         # Look for AdobeTVVideo embeds
         mobj = re.search(
@@ -1790,7 +1797,7 @@ class GenericIE(InfoExtractor):
                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
         if not found:
             # HTML5 video
-            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
+            found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
             found = re.search(