[fix] aol: disable http2 to prevent request fingerprinting (#6149)

PodcastIndex.org started using a Proof-of-Work JavaScript
challenge whose results are sent as `X-Pow-*` request headers.
Although it is technically possible to re-implement the
PoW challenge in Python, it's likely impossible to maintain
because

- the actual Proof of Concept logic might change very often

- the whole idea of the Proof of Work challenge is to use
  a "big" amount of resources (about 1s on my PC); so executing the challenge
  would almost block all other work on the SearXNG instance

At first glance, the challenge looks very similar to what
Anubis does, because it also uses SHA256 hashes.

client/simple/src/less/style.less

@@ -7,7 +7,6 @@
 @import "mixins.less";
 @import "toolkit.less";
 @import "autocomplete.less";
-@import "detail.less";
 @import "animations.less";
 @import "embedded.less";
 @import "info.less";
@@ -1165,3 +1164,4 @@ pre code {
 @import "result_types/code.less";
 @import "result_types/paper.less";
 @import "result_types/file.less";
+@import "result_types/image.less";

docs/dev/result_types/main/image.rst

@@ -0,0 +1,7 @@
+.. _result_types.image:
+
+=============
+Image Results
+=============
+
+.. automodule:: searx.result_types.image

docs/dev/result_types/main/mainresult.rst

@@ -1,4 +1,8 @@
 .. _result_types.mainresult:
 
+============
+Main Results
+============
+
 .. autoclass:: searx.result_types._base.MainResult
    :members:

docs/dev/result_types/main_result.rst

@@ -18,13 +18,13 @@ following types have been implemented so far ..
    main/code
    main/paper
    main/file
+   main/image
 
 The :ref:`LegacyResult <LegacyResult>` is used internally for the results that
 have not yet been typed.  The templates can be used as orientation until the
 final typing is complete.
 
 - :ref:`template default` / :py:obj:`Result`
-- :ref:`template images`
 - :ref:`template videos`
 - :ref:`template torrent`
 - :ref:`template map`

docs/dev/templates.rst

@@ -129,53 +129,6 @@ audio_src : uri,
   URL of an embedded ``<audio controls>``.
 
 
-.. _template images:
-
-``images.html``
----------------
-
-The images are displayed as small thumbnails in the main results list.
-
-title :  :py:class:`str`
-  Title of the image.
-
-thumbnail_src : :py:class:`str`
-  URL of a preview of the image.
-
-resolution :py:class:`str`
-  The resolution of the image (e.g. ``1920 x 1080`` pixel)
-
-
-Image labels
-~~~~~~~~~~~~
-
-Clicking on the preview opens a gallery view in which all further metadata for
-the image is displayed.  Addition fields used in the :origin:`images.html
-<searx/templates/simple/result_templates/images.html>`:
-
-img_src : :py:class:`str`
-  URL of the full size image.
-
-content:  :py:class:`str`
-  Description of the image.
-
-author:  :py:class:`str`
-  Name of the author of the image.
-
-img_format : :py:class:`str`
-  The format of the image (e.g. ``png``).
-
-source : :py:class:`str`
-  Source of the image.
-
-filesize: :py:class:`str`
-  Size of bytes in :py:obj:`human readable <searx.humanize_bytes>` notation
-  (e.g. ``MB`` for 1024 \* 1024 Bytes filesize).
-
-url : :py:class:`str`
-  URL of the page from where the images comes from (source).
-
-
 .. _template videos:
 
 ``videos.html``

searx/engines/aol.py

@@ -60,6 +60,8 @@ base_url = "https://search.aol.com"
 time_range_map = {"day": "1d", "week": "1w", "month": "1m", "year": "1y"}
 safesearch_map = {0: "p", 1: "r", 2: "i"}
 
+enable_http2 = False
+
 
 def init(_):
     if search_type not in ("search", "image", "video"):

searx/engines/flaticon.py

@@ -54,16 +54,13 @@ def response(resp: "SXNG_Response"):
     result: dict[str, str]  # TBH: dict[str, t.Any]
     for result in resp.json()["items"]:
         res.add(
-            res.types.LegacyResult(
+            res.types.Image(
-                {
+                title=result["name"],
-                    "template": "images.html",
+                content=", ".join([tag["tag"] for tag in result["tags"]]),  # pyright: ignore[reportArgumentType]
-                    "url": _fix_url(result["slug"]),
+                url=_fix_url(result["slug"]),
-                    "thumbnail_src": _fix_url(result["png"]),
+                thumbnail_src=_fix_url(result["png"]),
-                    "img_src": _fix_url(result["png512"]),
+                img_src=_fix_url(result["png512"]),
-                    "title": result["name"],
+                author=result["team_name"],
-                    "content": ", ".join([tag["tag"] for tag in result["tags"]]),  # pyright: ignore[reportArgumentType]
-                    "author": result["team_name"],
-                }
             )
         )
 

searx/engines/json_engine.py

@@ -29,7 +29,7 @@ Time Range:
 
 Safe-Search:
 
-- :py:obj:`safe_search_support`
+- :py:obj:`safesearch`
 - :py:obj:`safe_search_map`
 
 Response:
@@ -103,7 +103,7 @@ Replacements are:
 
 ``{safe_search}``:
   Safe-search :py:obj:`URL parameter <safe_search_map>` if engine
-  :py:obj:`supports safe-search <safe_search_support>`.  The ``{safe_search}``
+  :py:obj:`supports safe-search <safesearch>`.  The ``{safe_search}``
   replacement is taken from the :py:obj:`safes_search_map`.  Filter results::
 
       0: none, 1: moderate, 2:strict
@@ -236,7 +236,7 @@ time_range_map = {
       year: 365
 '''
 
-safe_search_support = False
+safesearch = False
 '''Engine supports safe-search.'''
 
 safe_search_map = {0: '&filter=none', 1: '&filter=moderate', 2: '&filter=strict'}
@@ -286,7 +286,6 @@ def do_query(data, q):  # pylint: disable=invalid-name
     qkey = q[0]
 
     for key, value in iterate(data):
-
         if len(q) == 1:
             if key == qkey:
                 ret.append(value)

searx/engines/podcastindex.py

@@ -1,41 +0,0 @@
-# SPDX-License-Identifier: AGPL-3.0-or-later
-"""Podcast Index"""
-
-from urllib.parse import quote_plus
-from datetime import datetime
-
-about = {
-    'website': 'https://podcastindex.org',
-    'official_api_documentation': None,  # requires an account
-    'use_official_api': False,
-    'require_api_key': False,
-    'results': 'JSON',
-}
-categories = []
-
-base_url = "https://podcastindex.org"
-
-
-def request(query, params):
-    params['url'] = f"{base_url}/api/search/byterm?q={quote_plus(query)}"
-    return params
-
-
-def response(resp):
-    results = []
-
-    json = resp.json()
-
-    for result in json['feeds']:
-        results.append(
-            {
-                'url': result['link'],
-                'title': result['title'],
-                'content': result['description'],
-                'thumbnail': result['image'],
-                'publishedDate': datetime.fromtimestamp(result['newestItemPubdate']),
-                'metadata': f"{result['author']}, {result['episodeCount']} episodes",
-            }
-        )
-
-    return results

searx/engines/xpath.py

@@ -31,7 +31,7 @@ Time Range:
 
 Safe-Search:
 
-- :py:obj:`safe_search_support`
+- :py:obj:`safesearch`
 - :py:obj:`safe_search_map`
 
 Response:
@@ -100,7 +100,7 @@ Replacements are:
 
 ``{safe_search}``:
   Safe-search :py:obj:`URL parameter <safe_search_map>` if engine
-  :py:obj:`supports safe-search <safe_search_support>`.  The ``{safe_search}``
+  :py:obj:`supports safe-search <safesearch>`.  The ``{safe_search}``
   replacement is taken from the :py:obj:`safes_search_map`.  Filter results::
 
       0: none, 1: moderate, 2:strict
@@ -205,7 +205,7 @@ time_range_map = {
       year: 365
 '''
 
-safe_search_support = False
+safesearch = False
 '''Engine supports safe-search.'''
 
 safe_search_map = {0: '&filter=none', 1: '&filter=moderate', 2: '&filter=strict'}
@@ -280,7 +280,6 @@ def response(resp) -> EngineResults:  # pylint: disable=too-many-branches
 
     if results_xpath:
         for result in eval_xpath_list(dom, results_xpath):
-
             url = extract_url(eval_xpath_list(result, url_xpath, min_len=1), search_url)
             title = extract_text(eval_xpath_list(result, title_xpath, min_len=1))
             content = extract_text(eval_xpath_list(result, content_xpath))

searx/result_types/__init__.py

@@ -35,6 +35,7 @@ from .keyvalue import KeyValue
 from .code import Code
 from .paper import Paper
 from .file import File
+from .image import Image
 
 
 class ResultList(list[Result | LegacyResult], abc.ABC):
@@ -50,6 +51,7 @@ class ResultList(list[Result | LegacyResult], abc.ABC):
         Code = Code
         Paper = Paper
         File = File
+        Image = Image
         MainResult = MainResult
         Result = Result
         Translations = Translations

searx/result_types/image.py

@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Typification of the *image* results.  Results of this type are rendered in
+the :origin:`images.html <searx/templates/simple/result_templates/images.html>`
+template.
+
+.. autoclass:: Image
+   :members:
+   :show-inheritance:
+
+"""
+
+__all__ = ["Image"]
+
+import typing as t
+
+
+from ._base import MainResult
+
+
+@t.final
+class Image(MainResult, kw_only=True):
+    """Result type suitable for displaying images.
+
+    The images are displayed as small thumbnails in the main results list.
+    Clicking on the preview opens a gallery view in which all further metadata
+    for the image is displayed."""
+
+    template: str = "images.html"
+
+    thumbnail_src: str = ""
+    """URL of a preview of the image."""
+
+    resolution: str = ""
+    """The resolution of the image (e.g. ``1920 x 1080`` pixel)"""
+
+    img_format: str = ""
+    """The format of the image (e.g. ``png``)."""
+
+    source: str = ""
+    """Source of the image."""
+
+    filesize: str = ""
+    """Size of bytes in :py:obj:`human readable <searx.humanize_bytes>` notation
+    (e.g. ``1MB`` for ``1024*1024`` Bytes filesize)."""

searx/settings.yml

@@ -1697,10 +1697,6 @@ engines:
       # image proxy of https://pixiv.perennialte.ch
       # - https://pximg.perennialte.ch
 
-  - name: podcastindex
-    engine: podcastindex
-    shortcut: podcast
-
   # Required dependency: psychopg2
   #  - name: postgresql
   #    engine: postgresql
@@ -1798,6 +1794,7 @@ engines:
     engine: qwant
     shortcut: qw
     categories: [general, web]
+    disabled: true
 
   - name: qwant news
     qwant_categ: news
@@ -1805,6 +1802,7 @@ engines:
     shortcut: qwn
     categories: news
     network: qwant
+    disabled: true
 
   - name: qwant images
     qwant_categ: images
@@ -1812,6 +1810,7 @@ engines:
     shortcut: qwi
     categories: [images, web]
     network: qwant
+    disabled: true
 
   - name: qwant videos
     qwant_categ: videos
@@ -1819,6 +1818,7 @@ engines:
     shortcut: qwv
     categories: [videos, web]
     network: qwant
+    disabled: true
 
   # - name: library
   #   engine: recoll