From 73364e158ec88a56383bd3b56023e4fb768d0b9b Mon Sep 17 00:00:00 2001
From: Bnyro <bnyro@tutanota.com>
Date: Sat, 5 Aug 2023 19:46:04 +0200
Subject: [PATCH] [feat] engine: brave - support for images

---
 requirements.txt       |  1 +
 searx/engines/brave.py | 65 ++++++++++++++++++++++++++++++++++++++++++
 searx/settings.yml     |  6 ++++
 3 files changed, 72 insertions(+)
 create mode 100644 searx/engines/brave.py

diff --git a/requirements.txt b/requirements.txt
index c8371795a..4d0b8da8e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -17,3 +17,4 @@ markdown-it-py==3.0.0
 typing_extensions==4.7.1
 fasttext-predict==0.9.2.1
 pytomlpp==1.0.13
+chompjs==1.2.2
\ No newline at end of file
diff --git a/searx/engines/brave.py b/searx/engines/brave.py
new file mode 100644
index 000000000..e2acf64f4
--- /dev/null
+++ b/searx/engines/brave.py
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""
+ Brave (General, news, videos, images)
+"""
+
+from urllib.parse import urlencode
+from lxml import html
+from searx.utils import extract_text, eval_xpath, eval_xpath_list
+import chompjs, json
+import re
+
+about = {
+    "website": 'https://search.brave.com/',
+    "wikidata_id": 'Q22906900',
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": 'HTML',
+}
+base_url = "https://search.brave.com/"
+paging = False
+categories = ['images', 'videos', 'news'] # images, videos, news
+
+def request(query, params):
+    args = {
+        'q': query,
+        'spellcheck': 1,
+    }
+    params["url"] = f"{base_url}{categories[0]}?{urlencode(args)}"
+
+def get_image_results(text):
+    results = []
+
+    datastr = ""
+    for line in text.split("\n"):
+        if "const data = " in line:
+            datastr = line.replace("const data = ", "").strip()[:-1]
+            break
+
+    json_data = chompjs.parse_js_object(datastr)
+
+    for result in json_data[1]["data"]["body"]["response"]["results"]:
+        results.append(
+            {
+                'template': 'images.html',
+                'url': result['url'],
+                'thumbnail_src': result['thumbnail']['src'],
+                'img_src': result['properties']['url'],
+                'content': result['description'],
+                'title': result['title'],
+                'source': result['source'],
+                'img_format': result['properties']['format'],
+            }
+        )
+
+    return results
+
+def response(resp):
+    dom = html.fromstring(resp.text)
+
+    match categories[0]:
+        case 'images':
+            return get_image_results(resp.text)
+        case _:
+            return []
\ No newline at end of file
diff --git a/searx/settings.yml b/searx/settings.yml
index aa8e61ae8..d41b1edfd 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -1843,6 +1843,12 @@ engines:
       require_api_key: false
       results: HTML
 
+  - name: brave.images
+    shortcut: braveimg
+    engine: brave
+    categories: images
+    disabled: false
+
   - name: petalsearch
     shortcut: pts
     engine: xpath