From b3ef06c0f50de9e5b7e2098447e8f0838b962090 Mon Sep 17 00:00:00 2001
From: TheresNoTime <sam@theresnotime.co.uk>
Date: Thu, 23 Mar 2023 17:01:31 +0000
Subject: [PATCH] Add DuckDuckGo search engine, add `extra_deps`

---
 earwigbot/wiki/copyvios/search.py | 22 ++++++++++++++++++++--
 setup.py                          |  1 +
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/earwigbot/wiki/copyvios/search.py b/earwigbot/wiki/copyvios/search.py
index dedffd8..c98ad91 100644
--- a/earwigbot/wiki/copyvios/search.py
+++ b/earwigbot/wiki/copyvios/search.py
@@ -27,13 +27,14 @@ from socket import error
 from io import StringIO
 from urllib.parse import quote, urlencode
 from urllib.error import URLError
+from duckduckgo_search import ddg
 
 from earwigbot import importer
 from earwigbot.exceptions import SearchQueryError
 
 lxml = importer.new("lxml")
 
-__all__ = ["BingSearchEngine", "GoogleSearchEngine", "YandexSearchEngine", "SEARCH_ENGINES"]
+__all__ = ["BingSearchEngine", "GoogleSearchEngine", "YandexSearchEngine", "DDGSearchEngine", "SEARCH_ENGINES"]
 
 class _BaseSearchEngine:
     """Base class for a simple search engine interface."""
@@ -203,9 +204,26 @@ class YandexSearchEngine(_BaseSearchEngine):
         except lxml.etree.Error as exc:
             raise SearchQueryError("Yandex XML parse error: " + str(exc))
 
+class DDGSearchEngine(_BaseSearchEngine):
+    """A search engine interface with DuckDuckGo"""
+    name = "DDG"
+
+    def search(self, query):
+        """Do a DuckDuckGo web search for *query*.
+
+        Returns a list of URLs ranked by relevance (as determined by DuckDuckGo).
+        """
+        result = ddg(query, safesearch='Off', time='y', max_results=200)
+
+        try:
+            return [item["href"] for item in result]
+        except KeyError:
+            return []
+
 
 SEARCH_ENGINES = {
     "Bing": BingSearchEngine,
     "Google": GoogleSearchEngine,
-    "Yandex": YandexSearchEngine
+    "Yandex": YandexSearchEngine,
+    "DDG": DDGSearchEngine
 }
diff --git a/setup.py b/setup.py
index a928353..2145f30 100644
--- a/setup.py
+++ b/setup.py
@@ -46,6 +46,7 @@ extra_deps = {
         "nltk >= 3.6.1",  # Parsing sentences to split article content
         "pdfminer >= 20191125",  # Extracting text from PDF files
         "tldextract >= 3.1.0",  # Getting domains for the multithreaded workers
+        "duckduckgo-search == 2.8.5", # DuckDuckGo search engine
     ],
     "time": [
         "pytz >= 2021.1",  # Handling timezones for the !time IRC command