Update ✨Entity Linking Application✨.py

✨Entity Linking Application✨.py

@@ -55,11 +55,14 @@ async def combination_method(name, session):
         x = itertools_combinations(new_name, 2)
         for i in x:
             new_word = (i[0] + " " + i[1])
-            url = f"https://en.wikipedia.org/w/api.php?action=query&list=search&srsearch={new_word}&srlimit=5&srprop=&srenablerewrites=True&srinfo=suggestion&format=json"
-            json_suggestion = await fetch_json(url, session)
-            results = json_suggestion.get('query', {}).get('search')
-            for i in results:
-                data.add(i.get('title'))
+            url = f"https://www.google.com/search?q={new_word} site:en.wikipedia.org inurl:/wiki/ -inurl:? -inurl:Category: -inurl:File: -inurl:Special: -inurl:Help:&num=5"
+            html = requests.get(url, headers=headers)
+            soup = BeautifulSoup(html.text, "html.parser")
+            elements_with_href = soup.find_all(href=True)
+            href_links = [element['href'] for element in elements_with_href]
+            for link in href_links:
+                if link.startswith('https://en.wikipedia.org/wiki/'):
+                    data.add(link.split("/")[-1])
     return data
 
 async def single_method(name, session):
@@ -67,11 +70,14 @@ async def single_method(name, session):
         data = set()
         new_name = name.replace("-", " ").replace("/", " ").split()
         for i in new_name:
-            url = f"https://en.wikipedia.org/w/api.php?action=query&list=search&srsearch={i}&srlimit=10&srprop=&srenablerewrites=True&srinfo=suggestion&format=json"
-            json_suggestion = await fetch_json(url, session)
-            results = json_suggestion.get('query', {}).get('search')
-            for i in results:
-                data.add(i.get('title'))
+            url = f"https://www.google.com/search?q={i} site:en.wikipedia.org inurl:/wiki/ -inurl:? -inurl:Category: -inurl:File: -inurl:Special: -inurl:Help:&num=5"
+            html = requests.get(url, headers=headers)
+            soup = BeautifulSoup(html.text, "html.parser")
+            elements_with_href = soup.find_all(href=True)
+            href_links = [element['href'] for element in elements_with_href]
+            for link in href_links:
+                if link.startswith('https://en.wikipedia.org/wiki/'):
+                    data.add(link.split("/")[-1])
     return data
 
 async def mains(name, single, combi):