Merge tag 'upstream/2016.08.17'

[youtubedl] / youtube_dl / extractor / ellentv.py

diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py
index 02c6a4615c4436fecda86fb152a131f084640612..74bbc5c51c576880465e76453604891b6b5f48ca 100644 (file)
--- a/youtube_dl/extractor/ellentv.py
+++ b/youtube_dl/extractor/ellentv.py
@@ -6,40 +6,64 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,

+    NO_DEFAULT,

 )
 
 
 class EllenTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
 )
 
 
 class EllenTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',

-        'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
+        'md5': '4294cf98bc165f218aaa0b89e0fd8042',

         'info_dict': {
             'id': '0_ipq1gsai',
         'info_dict': {
             'id': '0_ipq1gsai',

-            'ext': 'mp4',
+            'ext': 'mov',

             'title': 'Fast Fingers of Fate',
             'title': 'Fast Fingers of Fate',

-            'description': 'md5:587e79fbbd0d73b148bc596d99ce48e6',
+            'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a',

             'timestamp': 1428035648,
             'upload_date': '20150403',
             'uploader_id': 'batchUser',
             'timestamp': 1428035648,
             'upload_date': '20150403',
             'uploader_id': 'batchUser',

-        }
-    }
+        },
+    }, {
+        # not available via http://widgets.ellentube.com/
+        'url': 'http://www.ellentv.com/videos/1-szkgu2m2/',
+        'info_dict': {
+            'id': '1_szkgu2m2',
+            'ext': 'flv',
+            'title': "Ellen's Amazingly Talented Audience",
+            'description': 'md5:86ff1e376ff0d717d7171590e273f0a5',
+            'timestamp': 1255140900,
+            'upload_date': '20091010',
+            'uploader_id': 'ellenkaltura@gmail.com',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

-        webpage = self._download_webpage(
-            'http://widgets.ellentube.com/videos/%s' % video_id,
-            video_id)
+        URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url)
+
+        for num, url_ in enumerate(URLS, 1):
+            webpage = self._download_webpage(
+                url_, video_id, fatal=num == len(URLS))
+
+            default = NO_DEFAULT if num == len(URLS) else None
+
+            partner_id = self._search_regex(
+                r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id',
+                default=default)

 
 

-        partner_id = self._search_regex(
-            r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
+            kaltura_id = self._search_regex(
+                [r'id="kaltura_player_([^"]+)"',
+                 r"_wb_entry_id\s*:\s*'([^']+)",
+                 r'data-kaltura-entry-id="([^"]+)'],
+                webpage, 'kaltura id', default=default)

 
 

-        kaltura_id = self._search_regex(
-            [r'id="kaltura_player_([^"]+)"',
-             r"_wb_entry_id\s*:\s*'([^']+)",
-             r'data-kaltura-entry-id="([^"]+)'],
-            webpage, 'kaltura id')
+            if partner_id and kaltura_id:
+                break

 
         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
 
 
         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
 


@@ -72,7 +96,7 @@ class EllenTVClipsIE(InfoExtractor):
     def _extract_playlist(self, webpage):
         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
         try:
     def _extract_playlist(self, webpage):
         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
         try:

-            return json.loads("[{" + json_string + "}]")
+            return json.loads('[{' + json_string + '}]')

         except ValueError as ve:
             raise ExtractorError('Failed to download JSON', cause=ve)
 
         except ValueError as ve:
             raise ExtractorError('Failed to download JSON', cause=ve)