From 5c402923f8082272192d3e44f1214c9ffd7f0539 Mon Sep 17 00:00:00 2001
From: Bnyro <bnyro@tutanota.com>
Date: Fri, 8 Sep 2023 18:11:06 +0200
Subject: [PATCH] [feat] engine: implementation of internet archive scholar

---
 searx/engines/internet_archive_scholar.py | 72 +++++++++++++++++++++++
 searx/settings.yml                        |  5 ++
 2 files changed, 77 insertions(+)
 create mode 100644 searx/engines/internet_archive_scholar.py

diff --git a/searx/engines/internet_archive_scholar.py b/searx/engines/internet_archive_scholar.py
new file mode 100644
index 000000000..fdbc10026
--- /dev/null
+++ b/searx/engines/internet_archive_scholar.py
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# lint: pylint
+"""Internet Archive scholar(science)
+"""
+
+from datetime import datetime
+from urllib.parse import urlencode
+from searx.utils import html_to_text
+
+about = {
+    "website": "https://scholar.archive.org/",
+    "wikidata_id": "Q115667709",
+    "official_api_documentation": "https://scholar.archive.org/api/redoc",
+    "use_official_api": True,
+    "require_api_key": False,
+    "results": "JSON",
+}
+categories = ['science', 'scientific publications']
+paging = True
+
+base_url = "https://scholar.archive.org"
+results_per_page = 15
+
+
+def request(query, params):
+    args = {
+        "q": query,
+        "limit": results_per_page,
+        "offset": (params["pageno"] - 1) * results_per_page,
+    }
+    params["url"] = f"{base_url}/search?{urlencode(args)}"
+    params["headers"]["Accept"] = "application/json"
+    return params
+
+
+def response(resp):
+    results = []
+
+    json = resp.json()
+
+    for result in json["results"]:
+        publishedDate, content, doi = None, '', None
+
+        if result['biblio'].get('release_date'):
+            publishedDate = datetime.strptime(result['biblio']['release_date'], "%Y-%m-%d")
+
+        if len(result['abstracts']) > 0:
+            content = result['abstracts'][0].get('body')
+        elif len(result['_highlights']) > 0:
+            content = result['_highlights'][0]
+
+        if len(result['releases']) > 0:
+            doi = result['releases'][0].get('doi')
+
+        results.append(
+            {
+                'template': 'paper.html',
+                'url': result['fulltext']['access_url'],
+                'title': result['biblio']['title'],
+                'content': html_to_text(content),
+                'publisher': result['biblio'].get('publisher'),
+                'doi': doi,
+                'journal': result['biblio'].get('container_name'),
+                'authors': result['biblio'].get('contrib_names'),
+                'tags': result['tags'],
+                'publishedDate': publishedDate,
+                'issns': result['biblio'].get('issns'),
+                'pdf_url': result['fulltext'].get('access_url'),
+            }
+        )
+
+    return results
diff --git a/searx/settings.yml b/searx/settings.yml
index 77a6a72f9..bd2cc1bfb 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -1348,6 +1348,11 @@ engines:
     api_site: 'askubuntu'
     categories: [it, q&a]
 
+  - name: internetarchivescholar
+    engine: internet_archive_scholar
+    shortcut: ias
+    timeout: 5.0
+
   - name: superuser
     engine: stackexchange
     shortcut: su