[ellentube] Fix issues, improve and simplify (closes #14570)

youtube_dl/extractor/ellentube.py

@@ -4,137 +4,130 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
+    extract_attributes,
+    float_or_none,
     int_or_none,
+    try_get,
 )
 
 
-class EllenTubeIE(InfoExtractor):
-    _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}
-                    )'''
-
-    _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,
-    }]
+class EllenTubeBaseIE(InfoExtractor):
+    def _extract_data_config(self, webpage, video_id):
+        details = self._search_regex(
+            r'(<[^>]+\bdata-component=(["\'])[Dd]etails.+?></div>)', webpage,
+            'details')
+        return self._parse_json(
+            extract_attributes(details)['data-config'], video_id)
 
-    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)
+    def _extract_video(self, data, video_id):
         title = data['title']
-        description = data.get('description')
-        publish_time = int_or_none(data.get('publishTime'))
-        thumbnail = data.get('thumbnail')
 
         formats = []
         duration = None
         for entry in data.get('media'):
             if entry.get('id') == 'm3u8':
                 formats = self._extract_m3u8_formats(
-                    entry.get('url'), video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
+                    entry['url'], video_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls')
                 duration = int_or_none(entry.get('duration'))
                 break
         self._sort_formats(formats)
+
+        def get_insight(kind):
+            return int_or_none(try_get(
+                data, lambda x: x['insight']['%ss' % kind]))
+
         return {
+            'extractor_key': EllenTubeIE.ie_key(),
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': data.get('description'),
             'duration': duration,
-            'thumbnail': thumbnail,
-            'timestamp': publish_time,
+            'thumbnail': data.get('thumbnail'),
+            'timestamp': float_or_none(data.get('publishTime'), scale=1000),
+            'view_count': get_insight('view'),
+            'like_count': get_insight('like'),
             'formats': formats,
         }
 
 
-class EllenTubeVideoIE(InfoExtractor):
-    _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',
+class EllenTubeIE(EllenTubeBaseIE):
+    _VALID_URL = r'''(?x)
+                        (?:
+                            ellentube:|
+                            https://api-prod\.ellentube\.com/ellenapi/api/item/
+                        )
+                        (?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})
+                    '''
+    _TESTS = [{
+        'url': 'https://api-prod.ellentube.com/ellenapi/api/item/0822171c-3829-43bf-b99f-d77358ae75e3',
         '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',
+            'thumbnail': r're:^https?://.+?',
             'duration': 514,
-            'timestamp': 1508505120000,
-            'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111',
+            'timestamp': 1508505120,
+            'upload_date': '20171020',
+            'view_count': int,
+            'like_count': int,
         }
-    }
+    }, {
+        'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0',
+        'only_matching': True,
+    }]
 
     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, 'EllenTube')
+        video_id = self._match_id(url)
+        data = self._download_json(
+            'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id,
+            video_id)
+        return self._extract_video(data, 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']
+class EllenTubeVideoIE(EllenTubeBaseIE):
+    _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',
+        'only_matching': True,
+    }
 
-    def _extract_playlist(self, url, display_id, extract_description=True):
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        playlist_data = self._html_search_regex(
-            r'<div\s+data-component\s*=\s*"Details"(.+)</div>', webpage, 'playlist data')
-        playlist_title = self._search_regex(
-            r'"title"\s*:\s*"(.+?)"', playlist_data, 'playlist title')
-        playlist_description = clean_html(self._search_regex(
-            r'"description"\s*:\s*"(.+?)"', playlist_data, 'playlist description',
-            fatal=False)) if extract_description else None
-        api_search = self._search_regex(
-            r'"filter"\s*:\s*"(.+?)"', playlist_data, 'playlist api request')
-        api_data = self._download_json(
-            'https://api-prod.ellentube.com/ellenapi/api/feed/?%s' % api_search,
-            display_id)
-        return self.playlist_result(
-            self._extract_videos_from_json(api_data, display_id),
-            display_id, playlist_title, playlist_description)
+        video_id = self._extract_data_config(webpage, display_id)['id']
+        return self.url_result(
+            'ellentube:%s' % video_id, ie=EllenTubeIE.ie_key(),
+            video_id=video_id)
 
 
-class EllenTubeEpisodeIE(EllenTubePlaylistIE):
-    _VALID_URL = r'https?://(?:www\.)?ellentube\.com/episode/(?P<id>.+)\.html'
-
-    _TEST = {
+class EllenTubePlaylistIE(EllenTubeBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?ellentube\.com/(?:episode|studios)/(?P<id>.+?)\.html'
+    _TESTS = [{
         'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html',
         'info_dict': {
             'id': 'dax-shepard-jordan-fisher-haim',
-            'title': 'Dax Shepard, \'DWTS\' Team Jordan Fisher & Lindsay Arnold, HAIM',
-            'description': 'md5:aed85d42892f6126e71ec5ed2aea2a0d'
+            'title': "Dax Shepard, 'DWTS' Team Jordan Fisher & Lindsay Arnold, HAIM",
+            'description': 'md5:bfc982194dabb3f4e325e43aa6b2e21c',
         },
         'playlist_count': 6,
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        return self._extract_playlist(url, display_id)
-
-
-class EllenTubeStudioIE(EllenTubePlaylistIE):
-    _VALID_URL = r'https?://(?:www\.)?ellentube\.com/studios/(?P<id>.+)\.html'
-
-    _TEST = {
+    }, {
         'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html',
-        'info_dict': {
-            'id': 'macey-goes-rving0',
-            'title': 'Macey Goes RVing',
-        },
-        'playlist_mincount': 3,
-    }
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        return self._extract_playlist(url, display_id, False)
+        webpage = self._download_webpage(url, display_id)
+        data = self._extract_data_config(webpage, display_id)['data']
+        feed = self._download_json(
+            'https://api-prod.ellentube.com/ellenapi/api/feed/?%s'
+            % data['filter'], display_id)
+        entries = [
+            self._extract_video(elem, elem['id'])
+            for elem in feed if elem.get('type') == 'VIDEO' and elem.get('id')]
+        return self.playlist_result(
+            entries, display_id, data.get('title'),
+            clean_html(data.get('description')))

youtube_dl/extractor/extractors.py

@@ -313,9 +313,8 @@ from .einthusan import EinthusanIE
 from .eitb import EitbIE
 from .ellentube import (
     EllenTubeIE,
-    EllenTubeEpisodeIE,
-    EllenTubeStudioIE,
     EllenTubeVideoIE,
+    EllenTubePlaylistIE,
 )
 from .elpais import ElPaisIE
 from .embedly import EmbedlyIE