[Viddler] Add support for generic embeds

youtube_dl/extractor/britishcouncil.py

@@ -1,30 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .viddler import ViddlerBaseIE
-
-
-class BritishCouncilIE(ViddlerBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:learnenglish\.)?britishcouncil.org/(?P<id>.*)'
-    _TEST = {
-        'url': 'https://learnenglish.britishcouncil.org/episode-01-they-meet',
-        'md5': '796e9c4fa07017e3da79d5e99ef36fe8',
-        'info_dict': {
-            'id': '34d5e84c',
-            'ext': 'mp4',
-            'title': 'StartingOut.s01e01',
-            'upload_date': '20160927',
-            'uploader': 'BCLearnenglish',
-            'timestamp': 1474975664,
-            'view_count': int,
-            'comment_count': int,
-        }
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        video_id = self._html_search_regex(
-            r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
-            webpage, 'video ID', group='id', default=None)
-        return self._extract_viddler_info(url, video_id, None)

youtube_dl/extractor/extractors.py

@@ -132,7 +132,6 @@ from .brightcove import (
     BrightcoveLegacyIE,
     BrightcoveNewIE,
 )
-from .britishcouncil import BritishCouncilIE
 from .businessinsider import BusinessInsiderIE
 from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE

youtube_dl/extractor/generic.py

@@ -119,6 +119,7 @@ from .expressen import ExpressenIE
 from .zype import ZypeIE
 from .odnoklassniki import OdnoklassnikiIE
 from .kinja import KinjaEmbedIE
+from .viddler import ViddlerIE
 
 
 class GenericIE(InfoExtractor):
@@ -1098,6 +1099,20 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Viddler'],
         },
+        {
+            'url': 'https://learnenglish.britishcouncil.org/episode-01-they-meet',
+            'md5': '796e9c4fa07017e3da79d5e99ef36fe8',
+            'info_dict': {
+                'id': '34d5e84c',
+                'ext': 'mp4',
+                'title': 'StartingOut.s01e01',
+                'upload_date': '20160927',
+                'uploader': 'BCLearnenglish',
+                'timestamp': 1474975664,
+                'view_count': int,
+                'comment_count': int,
+            },
+        },
         # Libsyn embed
         {
             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
@@ -2580,6 +2595,12 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
+        mobj = re.search(
+            r'<div class="viddler-auto-embed" data-video-id=([\'"])(?P<id>[^\'"]+)\1',
+            webpage)
+        if mobj is not None:
+            return ViddlerIE._build_url_result(mobj.group('id'))
+
         # Look for NYTimes player
         mobj = re.search(
             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',

youtube_dl/extractor/viddler.py

@@ -9,70 +9,7 @@ from ..utils import (
 )
 
 
-class ViddlerBaseIE(InfoExtractor):
+class ViddlerIE(InfoExtractor):
-    def _extract_viddler_info(self, url, video_id, secret):
-        query = {
-            'video_id': video_id,
-            'key': 'v0vhrt7bg2xq1vyxhkct',
-        }
-        if secret:
-            query['secret'] = secret
-
-        data = self._download_json(
-            'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json',
-            video_id, headers={'Referer': url}, query=query)['video']
-
-        formats = []
-        for filed in data['files']:
-            if filed.get('status', 'ready') != 'ready':
-                continue
-            format_id = filed.get('profile_id') or filed['profile_name']
-            f = {
-                'format_id': format_id,
-                'format_note': filed['profile_name'],
-                'url': self._proto_relative_url(filed['url']),
-                'width': int_or_none(filed.get('width')),
-                'height': int_or_none(filed.get('height')),
-                'filesize': int_or_none(filed.get('size')),
-                'ext': filed.get('ext'),
-                'source_preference': -1,
-            }
-            formats.append(f)
-
-            if filed.get('cdn_url'):
-                f = f.copy()
-                f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
-                f['format_id'] = format_id + '-cdn'
-                f['source_preference'] = 1
-                formats.append(f)
-
-            if filed.get('html5_video_source'):
-                f = f.copy()
-                f['url'] = self._proto_relative_url(filed['html5_video_source'])
-                f['format_id'] = format_id + '-html5'
-                f['source_preference'] = 0
-                formats.append(f)
-        self._sort_formats(formats)
-
-        categories = [
-            t.get('text') for t in data.get('tags', []) if 'text' in t]
-
-        return {
-            'id': video_id,
-            'title': data['title'],
-            'formats': formats,
-            'description': data.get('description'),
-            'timestamp': int_or_none(data.get('upload_time')),
-            'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
-            'uploader': data.get('author'),
-            'duration': float_or_none(data.get('length')),
-            'view_count': int_or_none(data.get('view_count')),
-            'comment_count': int_or_none(data.get('comment_count')),
-            'categories': categories,
-        }
-
-
-class ViddlerIE(ViddlerBaseIE):
     _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)(?:.+?\bsecret=(\d+))?'
     _TESTS = [{
         'url': 'http://www.viddler.com/v/43903784',
@@ -137,6 +74,74 @@ class ViddlerIE(ViddlerBaseIE):
         },
     }]
 
+    @staticmethod
+    def _url_for_id(id):
+        return 'http://www.viddler.com/v/%s' % id
+
+    @classmethod
+    def _build_url_result(cls, id):
+        return cls.url_result(cls._url_for_id(id),
+                              ie=cls.ie_key())
+
     def _real_extract(self, url):
         video_id, secret = re.match(self._VALID_URL, url).groups()
-        return self._extract_viddler_info(url, video_id, secret)
+
+        query = {
+            'video_id': video_id,
+            'key': 'v0vhrt7bg2xq1vyxhkct',
+        }
+        if secret:
+            query['secret'] = secret
+
+        data = self._download_json(
+            'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json',
+            video_id, headers={'Referer': url}, query=query)['video']
+
+        formats = []
+        for filed in data['files']:
+            if filed.get('status', 'ready') != 'ready':
+                continue
+            format_id = filed.get('profile_id') or filed['profile_name']
+            f = {
+                'format_id': format_id,
+                'format_note': filed['profile_name'],
+                'url': self._proto_relative_url(filed['url']),
+                'width': int_or_none(filed.get('width')),
+                'height': int_or_none(filed.get('height')),
+                'filesize': int_or_none(filed.get('size')),
+                'ext': filed.get('ext'),
+                'source_preference': -1,
+            }
+            formats.append(f)
+
+            if filed.get('cdn_url'):
+                f = f.copy()
+                f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
+                f['format_id'] = format_id + '-cdn'
+                f['source_preference'] = 1
+                formats.append(f)
+
+            if filed.get('html5_video_source'):
+                f = f.copy()
+                f['url'] = self._proto_relative_url(filed['html5_video_source'])
+                f['format_id'] = format_id + '-html5'
+                f['source_preference'] = 0
+                formats.append(f)
+        self._sort_formats(formats)
+
+        categories = [
+            t.get('text') for t in data.get('tags', []) if 'text' in t]
+
+        return {
+            'id': video_id,
+            'title': data['title'],
+            'formats': formats,
+            'description': data.get('description'),
+            'timestamp': int_or_none(data.get('upload_time')),
+            'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
+            'uploader': data.get('author'),
+            'duration': float_or_none(data.get('length')),
+            'view_count': int_or_none(data.get('view_count')),
+            'comment_count': int_or_none(data.get('comment_count')),
+            'categories': categories,
+        }