added an IE and test for break.com

diff --git a/test/tests.json b/test/tests.json
index c2c6421fd7a12145053737de1258c49556383bb1..30ab11fd83a19197ab889c50e87d04fe883d8982 100644 (file)
--- a/test/tests.json
+++ b/test/tests.json
@@ -640,5 +640,14 @@
         "uploader": "videoseconds",
         "title": "Instagram photo by @videoseconds (Videos)"
     }
+  },
+  {
+    "name": "Break",
+    "url": "http://www.break.com/video/when-girls-act-like-guys-2468056",
+    "file": "2468056.mp4",
+    "md5": "a3513fb1547fba4fb6cfac1bffc6c46b",
+    "info_dict": {
+        "title": "When Girls Act Like D-Bags"
+    }
   }
 ]

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 4aec8c6879e79ccc13cf5e9bcfbf9abc17c4d1d1..11176dd6a6217138bb659b5a5d4430d443fab5d0 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -4575,6 +4575,29 @@ class StatigrIE(InfoExtractor):
             'uploader' : uploader
         }]
 
+class BreakIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
+        video_id = mobj.group(1).split("-")[-1]
+        webpage = self._download_webpage(url, video_id)
+        video_url = re.search(r"videoPath: '(.+?)',",webpage).group(1)
+        key = re.search(r"icon: '(.+?)',",webpage).group(1)
+        final_url = str(video_url)+"?"+str(key)
+        thumbnail_url = re.search(r"thumbnailURL: '(.+?)'",webpage).group(1)
+        title = re.search(r"sVidTitle: '(.+)',",webpage).group(1)
+        ext = video_url.split('.')[-1]
+        return [{
+            'id':        video_id,
+            'url':       final_url,
+            'ext':       ext,
+            'title':     title,
+            'thumbnail': thumbnail_url,
+        }]
+
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
     The order does matter; the first extractor matched is the one handling the URL.
@@ -4642,6 +4665,7 @@ def gen_extractors():
         Vbox7IE(),
         GametrailersIE(),
         StatigrIE(),
+        BreakIE(),
         GenericIE()
     ]