Prepare for release.

[youtubedl] / youtube_dl / extractor / bloomberg.py

diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py
index 755d9c9ef2a093289df91409097320908ea06df7..11ace91dd310b62b8071e2f5b4603c54c2f91d52 100644 (file)
--- a/youtube_dl/extractor/bloomberg.py
+++ b/youtube_dl/extractor/bloomberg.py
@@ -1,27 +1,47 @@
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):
 import re
 
 from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):

-    _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
-
-    _TEST = {
-        u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
-        u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4',
-        u'info_dict': {
-            u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies',
-            u'description': u'md5:abc86e5236f9f0e4866c59ad36736686',
-        },
-        u'params': {
-            # Requires ffmpeg (m3u8 manifest)
-            u'skip_download': True,
+    _VALID_URL = r'https?://www\.bloomberg\.com/news/[^/]+/[^/]+/(?P<id>[^/?#]+)'
+
+    _TESTS = [{
+        'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
+        # The md5 checksum changes
+        'info_dict': {
+            'id': 'qurhIVlJSB6hzkVi229d8g',
+            'ext': 'flv',
+            'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
+            'description': 'md5:a8ba0302912d03d246979735c17d2761',

         },
         },

-    }
+    }, {
+        'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        name = mobj.group('name')
+        name = self._match_id(url)

         webpage = self._download_webpage(url, name)
         webpage = self._download_webpage(url, name)

-        ooyala_url = self._og_search_video_url(webpage)
-        return self.url_result(ooyala_url, ie='Ooyala')
+        video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
+        title = re.sub(': Video$', '', self._og_search_title(webpage))
+
+        embed_info = self._download_json(
+            'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
+        formats = []
+        for stream in embed_info['streams']:
+            if stream["muxing_format"] == "TS":
+                formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
+            else:
+                formats.extend(self._extract_f4m_formats(stream['url'], video_id))
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }