Update app.py

app.py

@@ -3,10 +3,11 @@ import numpy as np
 import cv2
 from PIL import Image
 import requests
+from datetime import datetime
 import io
 import os
 from urllib.parse import urljoin
-import re
+from bs4 import BeautifulSoup
 
 # Default parameters
 low_int = 10
@@ -28,9 +29,18 @@ def fetch_sdo_images(max_images, ident="0745", size="1024by960", tool="ccor1"):
         if response.status_code != 200:
             return None, f"Failed to access directory {base_url}: Status {response.status_code}", 0
         
+        # Parse HTML with BeautifulSoup
+        soup = BeautifulSoup(response.text, 'html.parser')
+        links = soup.find_all('a')
+        
         # Extract image filenames matching the pattern {DATE}_{IDENT}_{TOOL}_{SIZE}.jpg
-        pattern = rf"\d{{8}}_\d{{6}}_{re.escape(ident)}_{re.escape(tool)}_{re.escape(size)}\.jpg"
-        image_files = re.findall(pattern, response.text)
+        image_files = []
+        for link in links:
+            href = link.get('href')
+            if href and href.endswith(f"_{ident}_{tool}_{size}.jpg"):
+                # Check if the filename starts with a valid timestamp (YYYYMMDD_HHMMSS)
+                if len(href) >= 15 and href[:8].isdigit() and href[9:15].isdigit():
+                    image_files.append(href)
         
         # Sort images by timestamp (most recent first)
         image_files = sorted(image_files, key=lambda x: x[:15], reverse=True)