]> jfr.im git - yt-dlp.git/blobdiff - yt_dlp/extractor/americastestkitchen.py
[ie/matchtv] Fix extractor (#10190)
[yt-dlp.git] / yt_dlp / extractor / americastestkitchen.py
index be960c0f93b4950559c761f1bcd1f60dd4792d69..a6337e4825c6e2c1389125ee6610cc532a1067f5 100644 (file)
@@ -1,8 +1,4 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import json
-import re
 
 from .common import InfoExtractor
 from ..utils import (
@@ -15,7 +11,7 @@
 
 
 class AmericasTestKitchenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?:cooks(?:country|illustrated)/)?(?P<resource_type>episode|videos)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
         'md5': 'b861c3e365ac38ad319cfd509c30577f',
@@ -23,15 +19,20 @@ class AmericasTestKitchenIE(InfoExtractor):
             'id': '5b400b9ee338f922cb06450c',
             'title': 'Japanese Suppers',
             'ext': 'mp4',
+            'display_id': 'weeknight-japanese-suppers',
             'description': 'md5:64e606bfee910627efc4b5f050de92b3',
-            'thumbnail': r're:^https?://',
-            'timestamp': 1523318400,
-            'upload_date': '20180410',
-            'release_date': '20180410',
-            'series': "America's Test Kitchen",
-            'season_number': 18,
+            'timestamp': 1523304000,
+            'upload_date': '20180409',
+            'release_date': '20180409',
+            'series': 'America\'s Test Kitchen',
+            'season': 'Season 18',
             'episode': 'Japanese Suppers',
+            'season_number': 18,
             'episode_number': 15,
+            'duration': 1376,
+            'thumbnail': r're:^https?://',
+            'average_rating': 0,
+            'view_count': int,
         },
         'params': {
             'skip_download': True,
@@ -44,15 +45,20 @@ class AmericasTestKitchenIE(InfoExtractor):
             'id': '5fbe8c61bda2010001c6763b',
             'title': 'Simple Chicken Dinner',
             'ext': 'mp4',
+            'display_id': 'atktv_2103_simple-chicken-dinner_full-episode_web-mp4',
             'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
-            'thumbnail': r're:^https?://',
-            'timestamp': 1610755200,
-            'upload_date': '20210116',
-            'release_date': '20210116',
-            'series': "America's Test Kitchen",
-            'season_number': 21,
+            'timestamp': 1610737200,
+            'upload_date': '20210115',
+            'release_date': '20210115',
+            'series': 'America\'s Test Kitchen',
+            'season': 'Season 21',
             'episode': 'Simple Chicken Dinner',
+            'season_number': 21,
             'episode_number': 3,
+            'duration': 1397,
+            'thumbnail': r're:^https?://',
+            'view_count': int,
+            'average_rating': 0,
         },
         'params': {
             'skip_download': True,
@@ -60,6 +66,12 @@ class AmericasTestKitchenIE(InfoExtractor):
     }, {
         'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
         'only_matching': True,
+    }, {
+        'url': 'https://www.americastestkitchen.com/cookscountry/episode/564-when-only-chocolate-will-do',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.americastestkitchen.com/cooksillustrated/videos/4478-beef-wellington',
+        'only_matching': True,
     }, {
         'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
         'only_matching': True,
@@ -69,19 +81,19 @@ class AmericasTestKitchenIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        resource_type, video_id = re.match(self._VALID_URL, url).groups()
+        resource_type, video_id = self._match_valid_url(url).groups()
         is_episode = resource_type == 'episode'
         if is_episode:
             resource_type = 'episodes'
 
         resource = self._download_json(
-            'https://www.americastestkitchen.com/api/v6/%s/%s' % (resource_type, video_id), video_id)
+            f'https://www.americastestkitchen.com/api/v6/{resource_type}/{video_id}', video_id)
         video = resource['video'] if is_episode else resource
         episode = resource if is_episode else resource.get('episode') or {}
 
         return {
             '_type': 'url_transparent',
-            'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
+            'url': 'https://player.zype.com/embed/{}.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ'.format(video['zypeId']),
             'ie_key': 'Zype',
             'description': clean_html(video.get('description')),
             'timestamp': unified_timestamp(video.get('publishDate')),
@@ -94,7 +106,7 @@ def _real_extract(self, url):
 
 
 class AmericasTestKitchenSeasonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|(?P<cooks>cooks(?:country|illustrated)))\.com(?:(?:/(?P<show2>cooks(?:country|illustrated)))?(?:/?$|(?<!ated)(?<!ated\.com)/episodes/browse/season_(?P<season>\d+)))'
     _TESTS = [{
         # ATK Season
         'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
@@ -105,55 +117,99 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
         'playlist_count': 13,
     }, {
         # Cooks Country Season
-        'url': 'https://www.cookscountry.com/episodes/browse/season_12',
+        'url': 'https://www.americastestkitchen.com/cookscountry/episodes/browse/season_12',
         'info_dict': {
             'id': 'season_12',
             'title': 'Season 12',
         },
         'playlist_count': 13,
+    }, {
+        # America's Test Kitchen Series
+        'url': 'https://www.americastestkitchen.com/',
+        'info_dict': {
+            'id': 'americastestkitchen',
+            'title': 'America\'s Test Kitchen',
+        },
+        'playlist_count': 558,
+    }, {
+        # Cooks Country Series
+        'url': 'https://www.americastestkitchen.com/cookscountry',
+        'info_dict': {
+            'id': 'cookscountry',
+            'title': 'Cook\'s Country',
+        },
+        'playlist_count': 199,
+    }, {
+        'url': 'https://www.americastestkitchen.com/cookscountry/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cookscountry.com/episodes/browse/season_12',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cookscountry.com',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.americastestkitchen.com/cooksillustrated/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cooksillustrated.com',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        show_name, season_number = re.match(self._VALID_URL, url).groups()
-        season_number = int(season_number)
+        season_number, show1, show = self._match_valid_url(url).group('season', 'show', 'show2')
+        show_path = ('/' + show) if show else ''
+        show = show or show1
+        season_number = int_or_none(season_number)
+
+        slug, title = {
+            'americastestkitchen': ('atk', 'America\'s Test Kitchen'),
+            'cookscountry': ('cco', 'Cook\'s Country'),
+            'cooksillustrated': ('cio', 'Cook\'s Illustrated'),
+        }[show]
 
-        slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
+        facet_filters = [
+            'search_document_klass:episode',
+            'search_show_slug:' + slug,
+        ]
 
-        season = 'Season %d' % season_number
+        if season_number:
+            playlist_id = f'season_{season_number}'
+            playlist_title = f'Season {season_number}'
+            facet_filters.append('search_season_list:' + playlist_title)
+        else:
+            playlist_id = show
+            playlist_title = title
 
         season_search = self._download_json(
-            'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
-            season, headers={
-                'Origin': 'https://www.%s.com' % show_name,
+            f'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_{slug}_season_desc_production',
+            playlist_id, headers={
+                'Origin': 'https://www.americastestkitchen.com',
                 'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
                 'X-Algolia-Application-Id': 'Y1FNZXUI30',
             }, query={
-                'facetFilters': json.dumps([
-                    'search_season_list:' + season,
-                    'search_document_klass:episode',
-                    'search_show_slug:' + slug,
-                ]),
-                'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
+                'facetFilters': json.dumps(facet_filters),
+                'attributesToRetrieve': f'description,search_{slug}_episode_number,search_document_date,search_url,title,search_atk_episode_season',
                 'attributesToHighlight': '',
                 'hitsPerPage': 1000,
             })
 
         def entries():
             for episode in (season_search.get('hits') or []):
-                search_url = episode.get('search_url')
+                search_url = episode.get('search_url')  # always formatted like '/episode/123-title-of-episode'
                 if not search_url:
                     continue
                 yield {
                     '_type': 'url',
-                    'url': 'https://www.%s.com%s' % (show_name, search_url),
+                    'url': f'https://www.americastestkitchen.com{show_path or ""}{search_url}',
                     'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
                     'title': episode.get('title'),
                     'description': episode.get('description'),
                     'timestamp': unified_timestamp(episode.get('search_document_date')),
                     'season_number': season_number,
-                    'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
+                    'episode_number': int_or_none(episode.get(f'search_{slug}_episode_number')),
                     'ie_key': AmericasTestKitchenIE.ie_key(),
                 }
 
         return self.playlist_result(
-            entries(), 'season_%d' % season_number, season)
+            entries(), playlist_id, playlist_title)