Use duckduckgo_search package

app.py

@@ -205,47 +205,34 @@ def _get_runtime_specs():
 
 
 # ---------------------------------------------------------------------------
-# Web search (DuckDuckGo HTML scraping, no API key required)
+# Web search (DuckDuckGo, no API key required)
 # ---------------------------------------------------------------------------
 
-import re as _re
-
-
-def _search_web(query, max_results=10):
-    """Search the web via DuckDuckGo HTML endpoint."""
-    url = f"https://html.duckduckgo.com/html/?{urllib.parse.urlencode({'q': query})}"
-    req = urllib.request.Request(url, headers={
-        "User-Agent": "Mozilla/5.0 (compatible; RespiteAPI/1.0)",
-    })
-    resp = urllib.request.urlopen(req, timeout=10)
-    html = resp.read().decode("utf-8", errors="replace")
-
-    results = []
-    # Extract search results from DuckDuckGo HTML
-    for match in _re.finditer(
-        r'<a[^>]+class="result__a"[^>]*href="([^"]+)"[^>]*>(.+?)</a>.*?'
-        r'<a[^>]+class="result__snippet"[^>]*>(.*?)</a>',
-        html, _re.DOTALL,
-    ):
-        if len(results) >= max_results:
-            break
-        raw_url = match.group(1)
-        title = _re.sub(r'<[^>]+>', '', match.group(2)).strip()
-        snippet = _re.sub(r'<[^>]+>', '', match.group(3)).strip()
-        # DuckDuckGo wraps URLs in a redirect; extract the real URL
-        ud_match = _re.search(r'uddg=([^"&]+)', raw_url)
-        real_url = urllib.parse.unquote(ud_match.group(1)) if ud_match else raw_url
-        results.append({
-            "title": title,
-            "url": real_url,
-            "content": snippet,
-        })
-
-    return {
-        "query": query,
-        "results": results,
-        "total_results": len(results),
-    }
+try:
+    from duckduckgo_search import DDGS
+
+    def _search_web(query, max_results=10):
+        """Search the web via DuckDuckGo."""
+        with DDGS() as ddgs:
+            hits = list(ddgs.text(query, max_results=max_results))
+        results = []
+        for r in hits:
+            results.append({
+                "title": r.get("title", ""),
+                "url": r.get("href", ""),
+                "content": r.get("body", ""),
+            })
+        return {
+            "query": query,
+            "results": results,
+            "total_results": len(results),
+        }
+
+except ImportError:
+    _log("Warning: duckduckgo_search not installed, search disabled")
+
+    def _search_web(query, max_results=10):
+        raise RuntimeError("Search not available: duckduckgo_search not installed")
 
 
 # ---------------------------------------------------------------------------