From aeced6724935a8dbe85230a9155cf12edf74058f Mon Sep 17 00:00:00 2001
From: Bnyro <bnyro@tutanota.com>
Date: Thu, 18 Jun 2026 22:23:12 +0200
Subject: [PATCH] [feat] engines: add findfiles.net file search engine

FindFiles.net is a specialized file search engine designed to help you search
files online with precision. Unlike traditional search engines that mainly index
web pages, FindFiles focuses on finding real files on the internet - including
PDFs, documents, archives, videos, datasets, and more. [1]

[1] https://findfiles.net
---
 searx/engines/findfiles.py | 118 +++++++++++++++++++++++++++++++++++++
 searx/settings.yml         |  28 +++++++++
 2 files changed, 146 insertions(+)
 create mode 100644 searx/engines/findfiles.py

diff --git a/searx/engines/findfiles.py b/searx/engines/findfiles.py
new file mode 100644
index 000000000..2ce7d8e1c
--- /dev/null
+++ b/searx/engines/findfiles.py
@@ -0,0 +1,118 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""FindFiles.net_ is a Germany-based file search engine.
+
+FindFiles.net_ is a specialized file search engine designed to help you search
+files online with precision. Unlike traditional search engines that mainly index
+web pages, FindFiles focuses on finding real files on the internet - including
+PDFs, documents, archives, videos, datasets, and more.
+
+.. _FindFiles.net: https://findfiles.net
+"""
+
+from os.path import basename
+from urllib.parse import urlencode
+import typing as t
+
+from lxml import html
+
+from searx.result_types import EngineResults
+from searx.utils import extract_text, eval_xpath, eval_xpath_list
+
+if t.TYPE_CHECKING:
+    from extended_types import SXNG_Response
+    from search.processors import OnlineParams
+
+about = {
+    "website": "https://findfiles.net",
+    "wikidata_id": None,
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "HTML",
+}
+
+base_url = "https://findfiles.net"
+categories = ["files"]
+paging = True
+safeserach = True
+
+safesearch_map = {
+    0: "contentguard.off",
+    1: "contentguard.moderate",
+    2: "contentguard.strict",
+}
+
+FindFilesCategory = t.Literal[
+    "all",
+    "document",
+    "text",
+    "image",
+    "audio",
+    "video",
+]
+FINDFILES_CATEGORIES = t.get_args(FindFilesCategory)
+
+findfiles_categ: FindFilesCategory = "all"
+"""Category to search in."""
+
+
+def setup(_: dict[str, t.Any]) -> bool:
+    if findfiles_categ not in FINDFILES_CATEGORIES:
+        raise ValueError("invalid category: %s" % findfiles_categ)
+    return True
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    args = {
+        "query": query,
+        "contentguard": safesearch_map[params["safesearch"]],
+        "page": params["pageno"],
+    }
+    # the language in the path doesn't change anything about the results, it
+    # only changes the UI
+    params["url"] = f"{base_url}/en/serp/{findfiles_categ}/?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    res = EngineResults()
+
+    dom = html.fromstring(resp.text)
+    if findfiles_categ == "image":
+        for result in eval_xpath_list(
+            dom, "//div[contains(@class, 'image-mosaic')]/div[contains(@class, 'image-item')]"
+        ):
+            res.add(
+                res.types.Image(
+                    url=extract_text(eval_xpath(result, ".//div[contains(@class, 'caption')]/a/@href")) or "",
+                    title=extract_text(eval_xpath(result, ".//div[contains(@class, 'caption')]/a")) or "",
+                    thumbnail_src=extract_text(eval_xpath(result, ".//img/@src")) or "",
+                )
+            )
+    elif findfiles_categ == "video":
+        for result in eval_xpath_list(
+            dom, "//div[contains(@class, 'video-mosaic')]/div[contains(@class, 'video-item')]"
+        ):
+            video_src = extract_text(eval_xpath(result, ".//video/@src")) or ""
+            res.add(
+                res.types.LegacyResult(
+                    template="videos.html",
+                    url=video_src,
+                    title=extract_text(eval_xpath(result, ".//div[contains(@class, 'caption')]/span")) or "",
+                    iframe_src=video_src or "",
+                )
+            )
+    else:
+        for result in eval_xpath_list(dom, "//ol/li[contains(@class, 'result-item')]/article"):
+            filename = basename(extract_text(eval_xpath(result, ".//h3")) or "")
+            res.add(
+                res.types.File(
+                    url=extract_text(eval_xpath(result, ".//h3/a/@href")) or "",
+                    title=filename,
+                    content=" ".join(extract_text(el) or "" for el in eval_xpath_list(result, "./div/span")),
+                    filename=filename,
+                    size=extract_text(eval_xpath(result, "(.//span[@id])[1]")) or "",
+                    embedded=extract_text(eval_xpath(result, ".//audio/@src")) or "",
+                )
+            )
+
+    return res
diff --git a/searx/settings.yml b/searx/settings.yml
index 29cb8e903..1bf37724a 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -977,6 +977,34 @@ engines:
     shortcut: fd
     disabled: true
 
+  - name: findfiles
+    engine: findfiles
+    findfiles_categ: all
+    categories: files
+    shortcut: fif
+    disabled: true
+
+  - name: findfiles images
+    engine: findfiles
+    findfiles_categ: image
+    categories: images
+    shortcut: fifi
+    disabled: true
+
+  - name: findfiles videos
+    engine: findfiles
+    findfiles_categ: video
+    categories: videos
+    shortcut: fifv
+    disabled: true
+
+  - name: findfiles music
+    engine: findfiles
+    findfiles_categ: audio
+    categories: music
+    shortcut: fifm
+    disabled: true
+
   - name: findthatmeme
     engine: findthatmeme
     shortcut: ftm