Update app.py

app.py

@@ -1,65 +1,69 @@
-from flask import Flask, request, jsonify, render_template
+from flask import Flask, request, jsonify
 import requests
 from bs4 import BeautifulSoup
-from urllib.parse import urlparse, parse_qs, unquote
 
 app = Flask(__name__)
 
-def duckduckgo_search(query):
-    url = 'https://duckduckgo.com/html/'
-    params = {'q': query}
-    headers = {'User-Agent': 'Mozilla/5.0'}
+# Example URL, modify based on the search page you're targeting
+url = "https://html.duckduckgo.com/html/"
 
-    response = requests.get(url, params=params, headers=headers)
+# Function to fetch results from a specific page (1st page: page_num=1, 2nd page: page_num=2, etc.)
+def fetch_duckduckgo_results(search_query, page_num=1):
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'
+    }
+    
+    # DuckDuckGo uses 's' parameter for result offset, calculate offset for pages (e.g., 0 for first, 50 for second)
+    offset = (page_num - 1) * 50
+    
+    # Search query parameters (assuming DuckDuckGo), 's' is for pagination
+    params = {'q': search_query, 's': offset}
+    
+    # Send request to DuckDuckGo or relevant HTML page
+    response = requests.get(url, headers=headers, params=params)
+    
+    # Check if request was successful
     if response.status_code != 200:
-        return []
-
+        return {"error": f"Failed to retrieve data: {response.status_code}"}
+    
+    # Parse HTML content
     soup = BeautifulSoup(response.text, 'html.parser')
+    
+    # Find all result blocks
     results = []
-    for result in soup.find_all('div', class_='result'):
-        title_tag = result.find('a', class_='result__a')
-        if not title_tag:
-            continue
-        title = title_tag.get_text()
-        link = title_tag['href']
-        
-        # Decode the actual URL from the DuckDuckGo redirect link
-        parsed_link = urlparse(link)
-        query_params = parse_qs(parsed_link.query)
-        actual_url = unquote(query_params.get('uddg', [''])[0])
-
-        description_tag = result.find('a', class_='result__snippet')
-        description = description_tag.get_text() if description_tag else 'No description available'
+    for result in soup.find_all('div', class_='result__body'):
+        title_tag = result.find('h2', class_='result__title')
+        snippet_tag = result.find('a', class_='result__snippet')
+        icon_tag = result.find('img', class_='result__icon__img')
+        url_tag = result.find('a', class_='result__a')
         
-        # Attempt to fetch the favicon
-        icon = 'No icon available'
-        if actual_url:
-            parsed_actual_url = urlparse(actual_url)
-            favicon_url = f"{parsed_actual_url.scheme}://{parsed_actual_url.netloc}/favicon.ico"
-            favicon_response = requests.get(favicon_url, headers=headers)
-            if favicon_response.status_code == 200:
-                icon = favicon_url
-
-        results.append({
-            'title': title,
-            'link': actual_url,
-            'description': description,
-            'icon': icon
-        })
+        if title_tag and snippet_tag and icon_tag and url_tag:
+            result_data = {
+                'title': title_tag.text.strip(),
+                'description': snippet_tag.text.strip(),
+                'icon_url': "https:" + icon_tag['src'] if icon_tag else None,
+                'url': url_tag['href']
+            }
+            results.append(result_data)
+    
     return results
 
-@app.route('/')
-def index():
-    return render_template('index.html')
-
+# API endpoint for fetching search results
 @app.route('/search', methods=['GET'])
 def search():
-    query = request.args.get('query')
-    if not query:
-        return jsonify({'error': 'No query provided'}), 400
-
-    results = duckduckgo_search(query)
+    # Get query parameters
+    search_query = request.args.get('query', default='', type=str)
+    page_num = request.args.get('page', default=1, type=int)
+    
+    if not search_query:
+        return jsonify({"error": "Search query is required"}), 400
+    
+    # Fetch results from DuckDuckGo
+    results = fetch_duckduckgo_results(search_query, page_num)
+    
+    # Return results as JSON
     return jsonify(results)
 
+# Run the Flask application
 if __name__ == '__main__':
     app.run(host="0.0.0.0", port=7860)