Merge tag 'upstream/2015.06.04.1'

[youtubedl] / youtube_dl / extractor / blinkx.py

diff --git a/youtube_dl/extractor/blinkx.py b/youtube_dl/extractor/blinkx.py
index 7d558e262ecea44df6b025f0db716b82d975b314..3b8eabe8f4e42283eaa8a2288413f971fdcd5b35 100644 (file)
--- a/youtube_dl/extractor/blinkx.py
+++ b/youtube_dl/extractor/blinkx.py
@@ -1,40 +1,35 @@
 from __future__ import unicode_literals
 
 import json
 from __future__ import unicode_literals
 
 import json

-import re

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..utils import remove_start
+from ..utils import (
+    remove_start,
+    int_or_none,
+)

 
 
 class BlinkxIE(InfoExtractor):
 
 
 class BlinkxIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
+    _VALID_URL = r'(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'

     IE_NAME = 'blinkx'
 
     _TEST = {
     IE_NAME = 'blinkx'
 
     _TEST = {

-        'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
-        'md5': '2e9a07364af40163a908edbf10bb2492',
+        'url': 'http://www.blinkx.com/ce/Da0Gw3xc5ucpNduzLuDDlv4WC9PuI4fDi1-t6Y3LyfdY2SZS5Urbvn-UPJvrvbo8LTKTc67Wu2rPKSQDJyZeeORCR8bYkhs8lI7eqddznH2ofh5WEEdjYXnoRtj7ByQwt7atMErmXIeYKPsSDuMAAqJDlQZ-3Ff4HJVeH_s3Gh8oQ',
+        'md5': '337cf7a344663ec79bf93a526a2e06c7',

         'info_dict': {
         'info_dict': {

-            'id': '8aQUy7GV',
+            'id': 'Da0Gw3xc',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Police Car Rolls Away',
-            'uploader': 'stupidvideos.com',
-            'upload_date': '20131215',
-            'timestamp': 1387068000,
-            'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!',
-            'duration': 14.886,
-            'thumbnails': [{
-                'width': 100,
-                'height': 76,
-                'resolution': '100x76',
-                'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
-            }],
+            'title': 'No Daily Show for John Oliver; HBO Show Renewed - IGN News',
+            'uploader': 'IGN News',
+            'upload_date': '20150217',
+            'timestamp': 1424215740,
+            'description': 'HBO has renewed Last Week Tonight With John Oliver for two more seasons.',
+            'duration': 47.743333,

         },
     }
 
         },
     }
 

-    def _real_extract(self, rl):
-        m = re.match(self._VALID_URL, rl)
-        video_id = m.group('id')
+    def _real_extract(self, url):
+        video_id = self._match_id(url)

         display_id = video_id[:8]
 
         api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +
         display_id = video_id[:8]
 
         api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +


@@ -52,7 +47,7 @@ class BlinkxIE(InfoExtractor):
                     'height': int(m['h']),
                 })
             elif m['type'] == 'original':
                     'height': int(m['h']),
                 })
             elif m['type'] == 'original':

-                duration = m['d']
+                duration = float(m['d'])

             elif m['type'] == 'youtube':
                 yt_id = m['link']
                 self.to_screen('Youtube video detected: %s' % yt_id)
             elif m['type'] == 'youtube':
                 yt_id = m['link']
                 self.to_screen('Youtube video detected: %s' % yt_id)


@@ -60,18 +55,20 @@ class BlinkxIE(InfoExtractor):
             elif m['type'] in ('flv', 'mp4'):
                 vcodec = remove_start(m['vcodec'], 'ff')
                 acodec = remove_start(m['acodec'], 'ff')
             elif m['type'] in ('flv', 'mp4'):
                 vcodec = remove_start(m['vcodec'], 'ff')
                 acodec = remove_start(m['acodec'], 'ff')

-                tbr = (int(m['vbr']) + int(m['abr'])) // 1000
+                vbr = int_or_none(m.get('vbr') or m.get('vbitrate'), 1000)
+                abr = int_or_none(m.get('abr') or m.get('abitrate'), 1000)
+                tbr = vbr + abr if vbr and abr else None

                 format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
                 formats.append({
                     'format_id': format_id,
                     'url': m['link'],
                     'vcodec': vcodec,
                     'acodec': acodec,
                 format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
                 formats.append({
                     'format_id': format_id,
                     'url': m['link'],
                     'vcodec': vcodec,
                     'acodec': acodec,

-                    'abr': int(m['abr']) // 1000,
-                    'vbr': int(m['vbr']) // 1000,
+                    'abr': abr,
+                    'vbr': vbr,

                     'tbr': tbr,
                     'tbr': tbr,

-                    'width': int(m['w']),
-                    'height': int(m['h']),
+                    'width': int_or_none(m.get('w')),
+                    'height': int_or_none(m.get('h')),

                 })
 
         self._sort_formats(formats)
                 })
 
         self._sort_formats(formats)