Create main.py

main.py

@@ -0,0 +1,139 @@
+from flask import Flask, request, Response
+import requests
+import logging
+from urllib.parse import urljoin
+from bs4 import BeautifulSoup
+import re
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+app = Flask(__name__)
+
+# Target URL base
+TARGET_BASE_URL = "https://superetka.com"
+
+@app.route('/proxy_image')
+def proxy_image():
+    image_url = request.args.get('url')
+    if not image_url:
+        return 'No URL provided', 400
+    
+    try:
+        # Forward the request to get the image
+        resp = requests.get(image_url, timeout=30)
+        return Response(resp.content, mimetype=resp.headers['Content-Type'])
+    except Exception as e:
+        logger.error(f"Error proxying image: {str(e)}")
+        return str(e), 500
+
+@app.route('/', defaults={'path': ''}, methods=['GET', 'POST', 'PUT', 'DELETE', 'PATCH', 'OPTIONS'])
+@app.route('/<path:path>', methods=['GET', 'POST', 'PUT', 'DELETE', 'PATCH', 'OPTIONS'])
+def proxy(path):
+    # Construct target URL with path and query parameters
+    if path and path.strip():
+        # If path is provided, use it
+        url = f"{TARGET_BASE_URL}/{path}"
+    else:
+        # Default to wap.php if no path is provided
+        url = f"{TARGET_BASE_URL}/etka/wap.php"
+    
+    # If there are query parameters, append them to the URL
+    if request.query_string:
+        url = f"{url}?{request.query_string.decode('utf-8')}"
+    
+    # Log the constructed URL
+    logger.info(f"Constructed URL: {url}")
+    
+    # Log the request
+    logger.info(f"Received request: {request.method} {request.url}")
+    logger.info(f"Forwarding to: {url}")
+    
+    # Get headers from the incoming request
+    headers = {key: value for key, value in request.headers if key.lower() != 'host'}
+    
+    try:
+        # Forward the request to the target server
+        # Don't pass params separately as they're already in the URL
+        resp = requests.request(
+            method=request.method,
+            url=url,
+            headers=headers,
+            data=request.get_data(),
+            cookies=request.cookies,
+            allow_redirects=False,
+            timeout=30
+        )
+        
+        # Log the response
+        logger.info(f"Received response from target: {resp.status_code}")
+        
+        # Check if response is HTML and filter content if needed
+        content_type = resp.headers.get('Content-Type', '')
+        if 'text/html' in content_type:
+            # Parse HTML content
+            html_content = resp.content.decode('utf-8', errors='ignore')
+            soup = BeautifulSoup(html_content, 'html.parser')
+            
+            # Filter out "Полная версия ETKA"
+            for element in soup.find_all(string=re.compile('Полная версия ETKA')):
+                # Replace the text with empty string
+                element.replace_with('')
+            
+            # Filter out README content
+            for element in soup.find_all(string=re.compile('README', re.IGNORECASE)):
+                element.replace_with('')
+                
+            # Redirect part number links to Google search
+            # Look for links that contain part numbers (typically in the second column of the table)
+            part_number_links = soup.select('td:nth-child(2) a')
+            for link in part_number_links:
+                # Get the part number from the link text
+                part_number = link.text.strip()
+                # Check if it matches a part number pattern (alphanumeric with possible spaces)
+                if re.match(r'^[A-Z0-9 ]+$', part_number):
+                    # Create a Google search URL for this part number with avto.pro
+                    google_search_url = f"https://www.google.com/search?q={part_number} avto.pro"
+                    # Update the link's href attribute
+                    link['href'] = google_search_url
+            
+            # Replace images with buttons
+            for img in soup.find_all('img'):
+                # Create button element
+                button = soup.new_tag('button')
+                img_src = img['src']
+                if not img_src.startswith('http'):
+                    img_src = urljoin(TARGET_BASE_URL, img_src)
+                proxy_url = f"/proxy_image?url={img_src}"
+                button['onclick'] = f'window.open("{proxy_url}", "_blank")'
+                button['style'] = 'margin: 5px;'
+                button.string = 'Показать изображение'
+                # Replace image with button
+                img.replace_with(button)
+
+            # Create a Flask response object with filtered content
+            response = Response(
+                soup.encode(),
+                status=resp.status_code
+            )
+        else:
+            # Create a Flask response object with original content
+            response = Response(
+                resp.content,
+                status=resp.status_code
+            )
+        
+        # Copy headers from the target response
+        for key, value in resp.headers.items():
+            if key.lower() not in ('transfer-encoding', 'content-encoding', 'content-length'):
+                response.headers[key] = value
+                
+        return response
+        
+    except requests.RequestException as e:
+        logger.error(f"Error forwarding request: {str(e)}")
+        return Response(f"Error forwarding request: {str(e)}", status=500)
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000, debug=True)