From 3ab826de225a19133ca08137f5a52aafdd384c5e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?L=C3=A9on=20Tiek=C3=B6tter?= <leon@tiekoetter.com>
Date: Fri, 7 Jan 2022 01:30:52 +0100
Subject: [PATCH] Drop microsoft academic engine

Microsoft academic was discontinued on 2021-12-31.

Source: https://www.microsoft.com/en-us/research/project/academic/articles/microsoft-academic-to-expand-horizons-with-community-driven-approach/
---
 searx/engines/microsoft_academic.py | 77 -----------------------------
 searx/settings.yml                  |  6 ---
 2 files changed, 83 deletions(-)
 delete mode 100644 searx/engines/microsoft_academic.py

diff --git a/searx/engines/microsoft_academic.py b/searx/engines/microsoft_academic.py
deleted file mode 100644
index a869daf2f..000000000
--- a/searx/engines/microsoft_academic.py
+++ /dev/null
@@ -1,77 +0,0 @@
-# SPDX-License-Identifier: AGPL-3.0-or-later
-"""
- Microsoft Academic (Science)
-"""
-
-from json import dumps, loads
-from searx.utils import html_to_text
-
-# about
-about = {
-    "website": 'https://academic.microsoft.com',
-    "wikidata_id": 'Q28136779',
-    "official_api_documentation": 'http://ma-graph.org/',
-    "use_official_api": False,
-    "require_api_key": False,
-    "results": 'JSON',
-}
-
-categories = ['images']
-paging = True
-search_url = 'https://academic.microsoft.com/api/search'
-_paper_url = 'https://academic.microsoft.com/paper/{id}/reference'
-
-
-def request(query, params):
-    params['url'] = search_url
-    params['method'] = 'POST'
-    params['headers']['content-type'] = 'application/json; charset=utf-8'
-    params['data'] = dumps(
-        {
-            'query': query,
-            'queryExpression': '',
-            'filters': [],
-            'orderBy': 0,
-            'skip': (params['pageno'] - 1) * 10,
-            'sortAscending': True,
-            'take': 10,
-            'includeCitationContexts': False,
-            'profileId': '',
-        }
-    )
-
-    return params
-
-
-def response(resp):
-    results = []
-    response_data = loads(resp.text)
-    if not response_data:
-        return results
-
-    for result in response_data.get('pr', {}):
-        if 'dn' not in result['paper']:
-            continue
-
-        title = result['paper']['dn']
-        content = _get_content(result['paper'])
-        url = _paper_url.format(id=result['paper']['id'])
-        results.append(
-            {
-                'url': url,
-                'title': html_to_text(title),
-                'content': html_to_text(content),
-            }
-        )
-
-    return results
-
-
-def _get_content(result):
-    if 'd' in result:
-        content = result['d']
-        if len(content) > 300:
-            return content[:300] + '...'
-        return content
-
-    return ''
diff --git a/searx/settings.yml b/searx/settings.yml
index f1d6fa1b1..e41daf6f1 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -872,12 +872,6 @@ engines:
   #   base_url: http://localhost:7700
   #   index: my-index
 
-  - name: microsoft academic
-    engine: microsoft_academic
-    categories: science
-    shortcut: ma
-    timeout: 6.0
-
   - name: mixcloud
     engine: mixcloud
     shortcut: mc