[ellentube] Implement code review changes.

youtube_dl/extractor/ellentube.py

@@ -5,14 +5,31 @@ from .common import InfoExtractor
 from ..utils import (
     clean_html,
     int_or_none,
-    urljoin,
 )
 
 
-class EllenTubeBaseIE(InfoExtractor):
+class EllenTubeIE(InfoExtractor):
-    API_URL = 'https://api-prod.ellentube.com/'
+    _VALID_URL = r'''(?x)
+                    (?:
+                        https://api-prod\.ellentube\.com/ellenapi/api/item/
+                        |ellentube:
+                    )
+                    (?P<id>
+                        [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}
+                    )'''
 
-    def _extract_video_from_json(self, data, video_id, display_id=None):
+    _TESTS = [{
+        'url': 'https://api-prod.ellentube.com/ellenapi/api/item/75c64c16-aefd-4558-b4f5-3de09b22e6fc',
+        'match_only': True,
+    }, {
+        'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0',
+        'match_only': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._download_json(
+            'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id, video_id)
         title = data['title']
         description = data.get('description')
         publish_time = int_or_none(data.get('publishTime'))
@@ -31,21 +48,43 @@ class EllenTubeBaseIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'description': description,
-            'display_id': display_id,
             'duration': duration,
             'thumbnail': thumbnail,
             'timestamp': publish_time,
             'formats': formats,
         }
 
-    def _extract_playlist_entries_from_json(self, data, display_id):
-        return [self._extract_video_from_json(elem, elem['id'])
-                for elem in data if elem.get('type') == 'VIDEO']
 
-    def _extract_from_video_id(self, video_id, display_id=None):
+class EllenTubeVideoIE(InfoExtractor):
-        api_data = self._download_json(
+    _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+)\.html'
-            urljoin(self.API_URL, 'ellenapi/api/item/%s' % video_id), video_id)
+
-        return self._extract_video_from_json(api_data, video_id, display_id)
+    _TEST = {
+        'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html',
+        'md5': '2fabc277131bddafdd120e0fc0f974c9',
+        'info_dict': {
+            'id': '0822171c-3829-43bf-b99f-d77358ae75e3',
+            'ext': 'mp4',
+            'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck',
+            'description': 'md5:76e3355e2242a78ad9e3858e5616923f',
+            'duration': 514,
+            'timestamp': 1508505120000,
+            'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111',
+        }
+    }
+
+    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'(?s)<!--\s*CONTENT\s*-->.*data-config.+([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
+            webpage, 'video id')
+        return self.url_result('ellentube:%s' % video_id)
+
+
+class EllenTubePlaylistIE(InfoExtractor):
+    def _extract_videos_from_json(self, data, display_id):
+        return [self.url_result('ellentube:%s' % elem['id'], 'EllenTube')
+                for elem in data if elem.get('type') == 'VIDEO']
 
     def _extract_playlist(self, url, display_id, extract_description=True):
         webpage = self._download_webpage(url, display_id)
@@ -59,40 +98,14 @@ class EllenTubeBaseIE(InfoExtractor):
         api_search = self._search_regex(
             r'"filter"\s*:\s*"(.+?)"', playlist_data, 'playlist api request')
         api_data = self._download_json(
-            urljoin(self.API_URL, 'ellenapi/api/feed/?%s' % api_search), display_id)
+            'https://api-prod.ellentube.com/ellenapi/api/feed/?%s' % api_search,
+            display_id)
         return self.playlist_result(
-            self._extract_playlist_entries_from_json(api_data, display_id),
+            self._extract_videos_from_json(api_data, display_id),
             display_id, playlist_title, playlist_description)
 
 
-class EllenTubeVideoIE(EllenTubeBaseIE):
+class EllenTubeEpisodeIE(EllenTubePlaylistIE):
-    _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+)\.html'
-
-    _TEST = {
-        'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html',
-        'md5': '2fabc277131bddafdd120e0fc0f974c9',
-        'info_dict': {
-            'id': '0822171c-3829-43bf-b99f-d77358ae75e3',
-            'ext': 'mp4',
-            'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck',
-            'description': 'md5:76e3355e2242a78ad9e3858e5616923f',
-            'display_id': 'ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck',
-            'duration': 514,
-            'timestamp': 1508505120000,
-            'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111',
-        }
-    }
-
-    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'(?s)<!--\s*CONTENT\s*-->.*data-config.+([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
-            webpage, 'video id')
-        return self._extract_from_video_id(video_id, display_id)
-
-
-class EllenTubeEpisodeIE(EllenTubeBaseIE):
     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/episode/(?P<id>.+)\.html'
 
     _TEST = {
@@ -110,7 +123,7 @@ class EllenTubeEpisodeIE(EllenTubeBaseIE):
         return self._extract_playlist(url, display_id)
 
 
-class EllenTubeStudioIE(EllenTubeBaseIE):
+class EllenTubeStudioIE(EllenTubePlaylistIE):
     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/studios/(?P<id>.+)\.html'
 
     _TEST = {

youtube_dl/extractor/extractors.py

@@ -309,6 +309,7 @@ from .eighttracks import EightTracksIE
 from .einthusan import EinthusanIE
 from .eitb import EitbIE
 from .ellentube import (
+    EllenTubeIE,
     EllenTubeEpisodeIE,
     EllenTubeStudioIE,
     EllenTubeVideoIE,