summary refs log tree commit diff
diff options
context:
space:
mode:
authorRemita Amine <remitamine@gmail.com>2020-12-06 23:37:16 +0100
committerRemita Amine <remitamine@gmail.com>2020-12-06 23:41:18 +0100
commit17b01228f84713df850912b554675bbfcbc62fb3 (patch)
tree31884155abfdea3795c70b7660edefd917cef96c
parent4f1ecca58d19be96b17893edb44308004c2b47fa (diff)
downloadyoutube-dl-17b01228f84713df850912b554675bbfcbc62fb3.tar.gz
youtube-dl-17b01228f84713df850912b554675bbfcbc62fb3.tar.xz
youtube-dl-17b01228f84713df850912b554675bbfcbc62fb3.zip
[americastestkitchen] Fix Extraction and add support for Cook's Country and Cook's Illustrated
closes #17234
closes #27322
-rw-r--r--youtube_dl/extractor/americastestkitchen.py68
1 files changed, 26 insertions, 42 deletions
diff --git a/youtube_dl/extractor/americastestkitchen.py b/youtube_dl/extractor/americastestkitchen.py
index 9c9d77ae1..e20f00fc3 100644
--- a/youtube_dl/extractor/americastestkitchen.py
+++ b/youtube_dl/extractor/americastestkitchen.py
@@ -1,33 +1,33 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
-    int_or_none,
-    js_to_json,
     try_get,
     unified_strdate,
 )
 
 
 class AmericasTestKitchenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
         'md5': 'b861c3e365ac38ad319cfd509c30577f',
         'info_dict': {
             'id': '5b400b9ee338f922cb06450c',
-            'title': 'Weeknight Japanese Suppers',
+            'title': 'Japanese Suppers',
             'ext': 'mp4',
-            'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8',
+            'description': 'md5:64e606bfee910627efc4b5f050de92b3',
             'thumbnail': r're:^https?://',
             'timestamp': 1523664000,
             'upload_date': '20180414',
-            'release_date': '20180414',
+            'release_date': '20180410',
             'series': "America's Test Kitchen",
             'season_number': 18,
-            'episode': 'Weeknight Japanese Suppers',
+            'episode': 'Japanese Suppers',
             'episode_number': 15,
         },
         'params': {
@@ -36,47 +36,31 @@ class AmericasTestKitchenIE(InfoExtractor):
     }, {
         'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
         'only_matching': True,
+    }, {
+        'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cooksillustrated.com/videos/4478-beef-wellington',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
+        resource_type, video_id = re.match(self._VALID_URL, url).groups()
+        is_episode = resource_type == 'episode'
+        if is_episode:
+            resource_type = 'episodes'
 
-        video_data = self._parse_json(
-            self._search_regex(
-                r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
-                webpage, 'initial context'),
-            video_id, js_to_json)
-
-        ep_data = try_get(
-            video_data,
-            (lambda x: x['episodeDetail']['content']['data'],
-             lambda x: x['videoDetail']['content']['data']), dict)
-        ep_meta = ep_data.get('full_video', {})
-
-        zype_id = ep_data.get('zype_id') or ep_meta['zype_id']
-
-        title = ep_data.get('title') or ep_meta.get('title')
-        description = clean_html(ep_meta.get('episode_description') or ep_data.get(
-            'description') or ep_meta.get('description'))
-        thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url'])
-        release_date = unified_strdate(ep_data.get('aired_at'))
-
-        season_number = int_or_none(ep_meta.get('season_number'))
-        episode = ep_meta.get('title')
-        episode_number = int_or_none(ep_meta.get('episode_number'))
+        resource = self._download_json(
+            'https://www.americastestkitchen.com/api/v6/%s/%s' % (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' % zype_id,
+            'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
             'ie_key': 'Zype',
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'release_date': release_date,
-            'series': "America's Test Kitchen",
-            'season_number': season_number,
-            'episode': episode,
-            'episode_number': episode_number,
+            'description': clean_html(video.get('description')),
+            'release_date': unified_strdate(video.get('publishDate')),
+            'series': try_get(episode, lambda x: x['show']['title']),
+            'episode': episode.get('title'),
         }