Prepare for upload.

[youtubedl] / youtube_dl / extractor / discovery.py

diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py
index d3e6675283cddcb8f6a6dfffbfbd1e1ea3da11bc..55853f76f91e97db19423c6cf8c1b8b56e006447 100644 (file)
--- a/youtube_dl/extractor/discovery.py
+++ b/youtube_dl/extractor/discovery.py
@@ -2,44 +2,96 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

+    parse_duration,

     parse_iso8601,
     parse_iso8601,

-    int_or_none,

 )
 )

+from ..compat import compat_str

 
 
 class DiscoveryIE(InfoExtractor):
 
 
 class DiscoveryIE(InfoExtractor):

-    _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
-    _TEST = {
+    _VALID_URL = r'''(?x)https?://(?:www\.)?(?:
+            discovery|
+            investigationdiscovery|
+            discoverylife|
+            animalplanet|
+            ahctv|
+            destinationamerica|
+            sciencechannel|
+            tlc|
+            velocity
+        )\.com/(?:[^/]+/)*(?P<id>[^./?#]+)'''
+    _TESTS = [{

         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',

-        'md5': '3c69d77d9b0d82bfd5e5932a60f26504',

         'info_dict': {
         'info_dict': {

-            'id': 'mission-impossible-outtakes',
-            'ext': 'flv',
+            'id': '20769',
+            'ext': 'mp4',

             'title': 'Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                             ' each other -- to the point of confusing Jamie\'s dog -- and '
                             'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
                             ' back.'),
             'duration': 156,
             'title': 'Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                             ' each other -- to the point of confusing Jamie\'s dog -- and '
                             'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
                             ' back.'),
             'duration': 156,

-            'timestamp': 1303099200,
-            'upload_date': '20110418',
+            'timestamp': 1302032462,
+            'upload_date': '20110405',
+            'uploader_id': '103207',

         },
         },

-    }
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        }
+    }, {
+        'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mythbusters-the-simpsons',
+        'info_dict': {
+            'id': 'mythbusters-the-simpsons',
+            'title': 'MythBusters: The Simpsons',
+        },
+        'playlist_mincount': 10,
+    }, {
+        'url': 'http://www.animalplanet.com/longfin-eels-maneaters/',
+        'info_dict': {
+            'id': '78326',
+            'ext': 'mp4',
+            'title': 'Longfin Eels: Maneaters?',
+            'description': 'Jeremy Wade tests whether or not New Zealand\'s longfin eels are man-eaters by covering himself in fish guts and getting in the water with them.',
+            'upload_date': '20140725',
+            'timestamp': 1406246400,
+            'duration': 116,
+            'uploader_id': '103207',
+        },
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        }
+    }]

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

-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        info = self._parse_json(self._search_regex(
-            r'(?s)<script type="application/ld\+json">(.*?)</script>',
-            webpage, 'video info'), video_id)
-
-        return {
-            'id': video_id,
-            'title': info['name'],
-            'url': info['contentURL'],
-            'description': info.get('description'),
-            'thumbnail': info.get('thumbnailUrl'),
-            'timestamp': parse_iso8601(info.get('uploadDate')),
-            'duration': int_or_none(info.get('duration')),
-        }
+        display_id = self._match_id(url)
+        info = self._download_json(url + '?flat=1', display_id)
+
+        video_title = info.get('playlist_title') or info.get('video_title')
+
+        entries = []
+
+        for idx, video_info in enumerate(info['playlist']):
+            subtitles = {}
+            caption_url = video_info.get('captionsUrl')
+            if caption_url:
+                subtitles = {
+                    'en': [{
+                        'url': caption_url,
+                    }]
+                }
+
+            entries.append({
+                '_type': 'url_transparent',
+                'url': 'http://players.brightcove.net/103207/default_default/index.html?videoId=ref:%s' % video_info['referenceId'],
+                'id': compat_str(video_info['id']),
+                'title': video_info['title'],
+                'description': video_info.get('description'),
+                'duration': parse_duration(video_info.get('video_length')),
+                'webpage_url': video_info.get('href') or video_info.get('url'),
+                'thumbnail': video_info.get('thumbnailURL'),
+                'alt_title': video_info.get('secondary_title'),
+                'timestamp': parse_iso8601(video_info.get('publishedDate')),
+                'subtitles': subtitles,
+            })
+
+        return self.playlist_result(entries, display_id, video_title)