Merge tag 'upstream/2015.05.15'

[youtubedl] / youtube_dl / extractor / funnyordie.py

diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py
index 6e6b6666003d0837bffd6c25ddd12fe1ce892e50..dd87257c465983dcda30a6faf5dbd7bc0950560c 100644 (file)
--- a/youtube_dl/extractor/funnyordie.py
+++ b/youtube_dl/extractor/funnyordie.py
@@ -8,7 +8,7 @@ from ..utils import ExtractorError
 
 
 class FunnyOrDieIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
+    _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|articles|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
     _TESTS = [{
         'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
         'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9',
@@ -21,14 +21,16 @@ class FunnyOrDieIE(InfoExtractor):
         },
     }, {
         'url': 'http://www.funnyordie.com/embed/e402820827',
-        'md5': 'ff4d83318f89776ed0250634cfaa8d36',
         'info_dict': {
             'id': 'e402820827',
             'ext': 'mp4',
             'title': 'Please Use This Song (Jon Lajoie)',
-            'description': 'md5:2ed27d364f5a805a6dba199faaf6681d',
+            'description': 'Please use this to sell something.  www.jonlajoie.com',
             'thumbnail': 're:^http:.*\.jpg$',
         },
+    }, {
+        'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -37,7 +39,7 @@ class FunnyOrDieIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        links = re.findall(r'<source src="([^"]+/v)\d+\.([^"]+)" type=\'video', webpage)
+        links = re.findall(r'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video', webpage)
         if not links:
             raise ExtractorError('No media links available for %s' % video_id)
 
@@ -48,7 +50,6 @@ class FunnyOrDieIE(InfoExtractor):
         bitrates.sort()
 
         formats = []
-
         for bitrate in bitrates:
             for link in links:
                 formats.append({
@@ -57,6 +58,13 @@ class FunnyOrDieIE(InfoExtractor):
                     'vbr': bitrate,
                 })
 
+        subtitles = {}
+        for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage):
+            subtitles[src_lang] = [{
+                'ext': src.split('/')[-1],
+                'url': 'http://www.funnyordie.com%s' % src,
+            }]
+
         post_json = self._search_regex(
             r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
         post = json.loads(post_json)
@@ -67,4 +75,5 @@ class FunnyOrDieIE(InfoExtractor):
             'description': post.get('description'),
             'thumbnail': post.get('picture'),
             'formats': formats,
+            'subtitles': subtitles,
         }