youtube-dl

commit 825e0984e27f0c626c4d072066e0c9cae9069704
parent d1cade5adeae95654f164fd30a57efd316b888ee
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Sun, 23 Jun 2013 22:59:51 +0200

[break] adapt to new paths

Diffstat:
M
test/tests.json
 | 
9
+++++++++
M
youtube_dl/extractor/__init__.py
 | 
2
++
A
youtube_dl/extractor/breakcom.py
 | 
25
+++++++++++++++++++++++++

3 files changed, 36 insertions(+), 0 deletions(-)
diff --git a/test/tests.json b/test/tests.json
@@ -640,5 +640,14 @@
         "uploader_id": "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/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -3,6 +3,7 @@ from .ard import ARDIE
 from .arte import ArteTvIE
 from .bandcamp import BandcampIE
 from .bliptv import BlipTVIE, BlipTVUserIE
+from .breakcom import BreakIE
 from .comedycentral import ComedyCentralIE
 from .collegehumor import CollegeHumorIE
 from .dailymotion import DailymotionIE
@@ -123,6 +124,7 @@ def gen_extractors():
         Vbox7IE(),
         GametrailersIE(),
         StatigramIE(),
+        BreakIE(),
         GenericIE()
     ]
 
diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py
@@ -0,0 +1,25 @@
+import re
+
+from .common import InfoExtractor
+
+
+class BreakIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, 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,
+        }]