From e5637fe7b98d7fb06cbbe0e0f24deb12a33187ba Mon Sep 17 00:00:00 2001
From: Paolo Basso <12545838+paolobasso99@users.noreply.github.com>
Date: Sun, 25 Jun 2023 17:12:17 +0200
Subject: [PATCH] [feat] engine: implementation of Anna's Archive

Anna's Archive [1] is a free non-profit online shadow library metasearch engine
providing access to a variety of book resources (also via IPFS), created by a
team of anonymous archivists [2].

[1] https://annas-archive.org/
[2] https://annas-software.org/AnnaArchivist/annas-archive
---
 searx/engines/annas-archive.py | 63 ++++++++++++++++++++++++++++++++++
 searx/settings.yml             |  7 ++++
 2 files changed, 70 insertions(+)
 create mode 100644 searx/engines/annas-archive.py

diff --git a/searx/engines/annas-archive.py b/searx/engines/annas-archive.py
new file mode 100644
index 000000000..56d1ca77a
--- /dev/null
+++ b/searx/engines/annas-archive.py
@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# lint: pylint
+"""Anna's Archive
+
+"""
+from typing import List, Dict, Any, Optional
+from urllib.parse import quote
+from lxml import html
+
+from searx.utils import extract_text, eval_xpath
+
+# about
+about: Dict[str, Any] = {
+    "website": "https://annas-archive.org/",
+    "wikidata_id": "Q115288326",
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "HTML",
+}
+
+# engine dependent config
+categories: List[str] = ["files"]
+paging: bool = False
+
+# search-url
+base_url: str = "https://annas-archive.org"
+
+# xpath queries
+xpath_results: str = '//main//a[starts-with(@href,"/md5")]'
+xpath_url: str = ".//@href"
+xpath_title: str = ".//h3/text()[1]"
+xpath_authors: str = './/div[contains(@class, "italic")]'
+xpath_publisher: str = './/div[contains(@class, "text-sm")]'
+xpath_file_info: str = './/div[contains(@class, "text-xs")]'
+
+
+def request(query, params: Dict[str, Any]) -> Dict[str, Any]:
+    search_url: str = base_url + "/search?q={search_query}"
+    params["url"] = search_url.format(search_query=quote(query))
+    return params
+
+
+def response(resp) -> List[Dict[str, Optional[str]]]:
+    results: List[Dict[str, Optional[str]]] = []
+    dom = html.fromstring(resp.text)
+
+    for item in dom.xpath(xpath_results):
+        result: Dict[str, Optional[str]] = {}
+
+        result["url"] = base_url + item.xpath(xpath_url)[0]
+
+        result["title"] = extract_text(eval_xpath(item, xpath_title))
+
+        result["content"] = "{publisher}. {authors}. {file_info}".format(
+            authors=extract_text(eval_xpath(item, xpath_authors)),
+            publisher=extract_text(eval_xpath(item, xpath_publisher)),
+            file_info=extract_text(eval_xpath(item, xpath_file_info)),
+        )
+
+        results.append(result)
+
+    return results
diff --git a/searx/settings.yml b/searx/settings.yml
index b6bb0a0e3..561ec41a9 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -297,6 +297,13 @@ engines:
     shortcut: 9g
     disabled: true
 
+  - name: anna's archive
+    engine: annas-archive
+    paging: False
+    categories: files
+    disabled: true
+    shortcut: aa
+
   - name: apk mirror
     engine: apkmirror
     timeout: 4.0