From 7adb9090e5dbc25b0d120772beca01dc4eb0791e Mon Sep 17 00:00:00 2001
From: Paolo Basso <12545838+paolobasso99@users.noreply.github.com>
Date: Sun, 25 Jun 2023 17:24:28 +0200
Subject: [mod] engine: Anna's Archive - add language support

---
 searx/engines/annas-archive.py | 63 --------------------------------------
 searx/engines/annas_archive.py | 68 ++++++++++++++++++++++++++++++++++++++++++
 searx/settings.yml             |  4 +--
 3 files changed, 70 insertions(+), 65 deletions(-)
 delete mode 100644 searx/engines/annas-archive.py
 create mode 100644 searx/engines/annas_archive.py

diff --git a/searx/engines/annas-archive.py b/searx/engines/annas-archive.py
deleted file mode 100644
index 56d1ca77a..000000000
--- a/searx/engines/annas-archive.py
+++ /dev/null
@@ -1,63 +0,0 @@
-# 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/engines/annas_archive.py b/searx/engines/annas_archive.py
new file mode 100644
index 000000000..1d5aa41ee
--- /dev/null
+++ b/searx/engines/annas_archive.py
@@ -0,0 +1,68 @@
+# 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}&lang={lang}"
+    lang: str = ""
+    if params["language"] != "all":
+        lang = params["language"]
+
+    params["url"] = search_url.format(search_query=quote(query), lang=lang)
+    print(params)
+    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 561ec41a9..8877fba54 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -298,8 +298,8 @@ engines:
     disabled: true
 
   - name: anna's archive
-    engine: annas-archive
-    paging: False
+    engine: annas_archive
+    paging: false
     categories: files
     disabled: true
     shortcut: aa
-- 
cgit v1.2.3-54-g00ecf