[feat] duckduckgo: support for videos and news

searx/engines/duckduckgo.py

@@ -66,8 +66,10 @@ def cache_vqd(query, value):
     The vqd value depends on the query string and is needed for the follow up
     pages or the images loaded by a XMLHttpRequest:
 
-    - DuckDuckGo Web: `https://links.duckduckgo.com/d.js?q=...&vqd=...`
-    - DuckDuckGo Images: `https://duckduckgo.com/i.js??q=...&vqd=...`
+    - DuckDuckGo Web: ``https://links.duckduckgo.com/d.js?q=...&vqd=...``
+    - DuckDuckGo Images: ``https://duckduckgo.com/i.js??q=...&vqd=...``
+    - DuckDuckGo Videos: ``https://duckduckgo.com/v.js??q=...&vqd=...``
+    - DuckDuckGo News: ``https://duckduckgo.com/news.js??q=...&vqd=...``
 
     """
     c = redisdb.client()

searx/engines/duckduckgo_extra.py

@@ -1,9 +1,10 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """
-DuckDuckGo Images
-~~~~~~~~~~~~~~~~~
+DuckDuckGo Extra (images, videos, news)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
+from datetime import datetime
 from typing import TYPE_CHECKING
 from urllib.parse import urlencode
 
@@ -32,6 +33,9 @@ about = {
 
 # engine dependent config
 categories = ['images', 'web']
+ddg_category = 'images'
+"""The category must be any of ``images``, ``videos`` and ``news``
+"""
 paging = True
 safesearch = True
 send_accept_language_header = True
@@ -39,6 +43,8 @@ send_accept_language_header = True
 safesearch_cookies = {0: '-2', 1: None, 2: '1'}
 safesearch_args = {0: '1', 1: None, 2: '1'}
 
+search_path_map = {'images': 'i', 'videos': 'v', 'news': 'news'}
+
 
 def request(query, params):
 
@@ -69,28 +75,61 @@ def request(query, params):
         args['p'] = safe_search  # "-1", "1"
 
     logger.debug("cookies: %s", params['cookies'])
-    args = urlencode(args)
-    params['url'] = 'https://duckduckgo.com/i.js?{args}'.format(args=args)
+
+    params['url'] = f'https://duckduckgo.com/{search_path_map[ddg_category]}.js?{urlencode(args)}'
 
     return params
 
 
+def _image_result(result):
+    return {
+        'template': 'images.html',
+        'url': result['url'],
+        'title': result['title'],
+        'content': '',
+        'thumbnail_src': result['thumbnail'],
+        'img_src': result['image'],
+        'img_format': '%s x %s' % (result['width'], result['height']),
+        'source': result['source'],
+    }
+
+
+def _video_result(result):
+    return {
+        'template': 'videos.html',
+        'url': result['content'],
+        'title': result['title'],
+        'content': result['description'],
+        'thumbnail': result['images'].get('small') or result['images'].get('medium'),
+        'iframe_src': result['embed_url'],
+        'source': result['provider'],
+        'length': result['duration'],
+        'metadata': result.get('uploader'),
+    }
+
+
+def _news_result(result):
+    return {
+        'url': result['url'],
+        'title': result['title'],
+        'content': result['excerpt'],
+        'source': result['source'],
+        'publishedDate': datetime.utcfromtimestamp(result['date']),
+    }
+
+
 def response(resp):
     results = []
     res_json = resp.json()
 
     for result in res_json['results']:
-        results.append(
-            {
-                'template': 'images.html',
-                'title': result['title'],
-                'content': '',
-                'thumbnail_src': result['thumbnail'],
-                'img_src': result['image'],
-                'url': result['url'],
-                'img_format': '%s x %s' % (result['width'], result['height']),
-                'source': result['source'],
-            }
-        )
+        if ddg_category == 'images':
+            results.append(_image_result(result))
+        elif ddg_category == 'videos':
+            results.append(_video_result(result))
+        elif ddg_category == 'news':
+            results.append(_news_result(result))
+        else:
+            raise ValueError(f"Invalid duckduckgo category: {ddg_category}")
 
     return results