fix: add image link to the discovery queue

src/core/link_manager.py

@@ -54,6 +54,40 @@ def extract_links(self, soup, current_url, depth, should_crawl_callback):
                         self.all_discovered_urls.add(clean_url)
                         self.discovered_urls.append((clean_url, depth))
 
+        """Extract images from HTML and add to discovery queue"""
+        imgs = soup.find_all('img', src=True)
+        for img in imgs:
+            src = img.get('src', '').strip()
+            if not src or src.startswith('data:'):
+                continue
+
+            try:
+                absolute_url = urljoin(current_url, src)
+                parsed = urlparse(absolute_url)
+
+                if parsed.scheme not in ('http', 'https'):
+                    continue
+
+                clean_url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}"
+                if parsed.query:
+                    clean_url += f"?{parsed.query}"
+
+                with self.urls_lock:
+                    if clean_url not in self.source_pages:
+                        self.source_pages[clean_url] = []
+                    if current_url not in self.source_pages[clean_url]:
+                        self.source_pages[clean_url].append(current_url)
+
+                    if (clean_url not in self.visited_urls and
+                        clean_url not in self.all_discovered_urls and
+                        clean_url != current_url):
+
+                        if should_crawl_callback(clean_url):
+                            self.all_discovered_urls.add(clean_url)
+                            self.discovered_urls.append((clean_url, depth))
+            except Exception:
+                continue
+
     def collect_all_links(self, soup, source_url, crawl_results):
         """Collect all links for the Links tab display"""
         links = soup.find_all('a', href=True)

src/crawler.py

@@ -163,7 +163,8 @@ def _get_default_config(self):
             'accept_language': 'en-US,en;q=0.9',
             'respect_robots': True,
             'allow_cookies': True,
-            'include_extensions': ['html', 'htm', 'php', 'asp', 'aspx', 'jsp'],
+            'include_extensions': ['html', 'htm', 'php', 'asp', 'aspx', 'jsp',
+                                    'jpg', 'jpeg', 'png', 'gif', 'webp', 'svg', 'ico', 'avif', 'bmp'],
             'exclude_extensions': ['pdf', 'doc', 'docx', 'zip', 'exe', 'dmg'],
             'include_patterns': [],
             'exclude_patterns': [],

src/settings_manager.py

@@ -91,7 +91,7 @@ def _get_default_settings(self):
             'googleApiKey': '',
 
             # Filter settings
-            'includeExtensions': 'html,htm,php,asp,aspx,jsp',
+            'includeExtensions': 'html,htm,php,asp,aspx,jsp,jpg,jpeg,png,gif,webp,svg,ico,avif,bmp',
             'excludeExtensions': 'pdf,doc,docx,zip,exe,dmg',
             'includePatterns': '',
             'excludePatterns': '',

web/static/js/settings.js

@@ -20,7 +20,7 @@ let defaultSettings = {
     googleApiKey: '',
 
     // Filter settings
-    includeExtensions: 'html,htm,php,asp,aspx,jsp',
+    includeExtensions: 'html,htm,php,asp,aspx,jsp,jpg,jpeg,png,gif,webp,svg,ico,avif,bmp',
     excludeExtensions: 'pdf,doc,docx,zip,exe,dmg',
     includePatterns: '',
     excludePatterns: '',

web/templates/index.html

@@ -635,7 +635,7 @@ <h3>Content Filters</h3>
 
                     <div class="setting-group">
                         <label for="includeExtensions">Include File Extensions</label>
-                        <input type="text" id="includeExtensions" value="html,htm,php,asp,aspx,jsp">
+                        <input type="text" id="includeExtensions" value="html,htm,php,asp,aspx,jsp,jpg,jpeg,png,gif,webp,svg,ico,avif,bmp">
                         <span class="setting-help">Comma-separated list of extensions to crawl</span>
                     </div>