Merge d5b0fb3d03 into 10d3af84b8

The query string send to DDG must not be qouted.

The query string was URL-qouted in #4011, but the URL-qouted query string result
in unexpected *URL decoded* and other garbish results as reported in #4019
and #4020.  To test compare the results of a query like::

    !ddg Häuser und Straßen :de
    !ddg Häuser und Straßen :all
    !ddg 房屋和街道 :all
    !ddg 房屋和街道 :zh

Closed:

- [#4019] https://github.com/searxng/searxng/issues/4019
- [#4020] https://github.com/searxng/searxng/issues/4020

Related:

- [#4011] https://github.com/searxng/searxng/pull/4011

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

searx/engines/adobe_stock.py

@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Adobe Stock (images)
+"""
+
+from urllib.parse import urlencode
+from searx.utils import gen_useragent
+
+about = {
+    "website": 'https://stock.adobe.com/',
+    "wikidata_id": 'Q5977430',
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": 'JSON',
+}
+
+categories = ['images']
+paging = True
+
+base_url = 'https://stock.adobe.com'
+
+results_per_page = 10
+adobe_order = "relevance"  # one of 'relevant', 'featured', 'creation' or 'nb_downloads'
+
+
+def request(query, params):
+    args = {
+        'k': query,
+        'limit': results_per_page,
+        'order': adobe_order,
+        'search_page': params['pageno'],
+        'search_type': 'pagination',
+        'filters[content_type:video]': 0,
+        'filters[content_type:audio]': 0,
+    }
+    params['url'] = f"{base_url}/de/Ajax/Search?{urlencode(args)}"
+
+    # headers required to bypass bot-detection
+    params['headers'] = {
+        "User-Agent": gen_useragent(),
+        "Accept-Language": "en-US,en;q=0.5",
+    }
+
+    return params
+
+
+def response(resp):
+    results = []
+
+    json_resp = resp.json()
+
+    for item in json_resp['items'].values():
+        results.append(
+            {
+                'template': 'images.html',
+                'url': item['content_url'],
+                'title': item['title'],
+                'content': '',
+                'img_src': item['content_thumb_extra_large_url'],
+                'thumbnail_src': item['thumbnail_url'],
+                'resolution': f"{item['content_original_width']}x{item['content_original_height']}",
+                'img_format': item['format'],
+                'author': item['author'],
+            }
+        )
+
+    return results

searx/engines/duckduckgo.py

@@ -6,7 +6,7 @@ DuckDuckGo Lite
 
 from typing import TYPE_CHECKING
 import re
-from urllib.parse import urlencode, quote_plus
+from urllib.parse import urlencode
 import json
 import babel
 import lxml.html
@@ -263,7 +263,7 @@ def request(query, params):
 
     params['url'] = url
     params['method'] = 'POST'
-    params['data']['q'] = quote_plus(query)
+    params['data']['q'] = query
 
     # The API is not documented, so we do some reverse engineering and emulate
     # what https://html.duckduckgo.com/html does when you press "next Page" link
@@ -381,7 +381,11 @@ def response(resp):
     zero_click_info_xpath = '//div[@id="zero_click_abstract"]'
     zero_click = extract_text(eval_xpath(doc, zero_click_info_xpath)).strip()
 
-    if zero_click and "Your IP address is" not in zero_click and "Your user agent:" not in zero_click:
+    if zero_click and (
+        "Your IP address is" not in zero_click
+        and "Your user agent:" not in zero_click
+        and "URL Decoded:" not in zero_click
+    ):
         current_query = resp.search_params["data"].get("q")
 
         results.append(

searx/settings.yml

@@ -325,6 +325,13 @@ engines:
     shortcut: 9g
     disabled: true
 
+  - name: adobe stock
+    engine: adobe_stock
+    # available search orders: 'relevant', 'featured', 'creation', 'nb_downloads'
+    # adobe_order: relevance
+    shortcut: as
+    disabled: true
+
   - name: alpine linux packages
     engine: alpinelinux
     disabled: true