Update app.py

app.py

@@ -4,10 +4,11 @@ import requests
 from bs4 import BeautifulSoup
 import uvicorn
 import urllib.parse
-from duckduckgo_search import DDGS  # <- Nueva importación para imágenes
+from duckduckgo_search import DDGS
 
-app = FastAPI(title="Glimpse Scraping API", description="API de Scraping directo e Imágenes para buscadores")
+app = FastAPI(title="Glimpse Scraping API", description="API de Scraping directo e Imágenes")
 
+# Configuración CORS para evitar bloqueos del navegador
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -16,13 +17,12 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-# User-Agent de un navegador real para evitar bloqueos en texto
 HEADERS = {
     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
     "Accept-Language": "es-ES,es;q=0.9,en;q=0.8"
 }
 
-# --- FUNCIONES DE SCRAPING DE TEXTO (WEB) ---
+# --- FUNCIONES DE SCRAPING WEB ---
 
 def scrape_duckduckgo(query: str):
     url = f"https://html.duckduckgo.com/html/?q={urllib.parse.quote(query)}"
@@ -34,11 +34,9 @@ def scrape_duckduckgo(query: str):
     for result in soup.select('.result__body'):
         title_tag = result.select_one('.result__title a')
         snippet_tag = result.select_one('.result__snippet')
-        
         if title_tag:
             raw_url = title_tag.get('href', '')
             clean_url = urllib.parse.unquote(raw_url.replace('//duckduckgo.com/l/?uddg=', '').split('&')[0])
-            
             results.append({
                 "title": title_tag.text.strip(),
                 "url": clean_url if clean_url.startswith('http') else raw_url,
@@ -51,12 +49,10 @@ def scrape_mojeek(query: str):
     resp = requests.get(url, headers=HEADERS, timeout=10)
     resp.raise_for_status()
     soup = BeautifulSoup(resp.text, 'lxml')
-    
     results = []
     for li in soup.select('ul.results-standard > li'):
         a_tag = li.select_one('a.ob')
         p_tag = li.select_one('p.s')
-        
         if a_tag:
             results.append({
                 "title": a_tag.text.strip(),
@@ -70,12 +66,10 @@ def scrape_qwant(query: str):
     resp = requests.get(url, headers=HEADERS, timeout=10)
     resp.raise_for_status()
     soup = BeautifulSoup(resp.text, 'lxml')
-    
     results = []
     for article in soup.select('article.result'):
         title_tag = article.select_one('h2 a')
         snippet_tag = article.select_one('.result-snippet')
-        
         if title_tag:
             results.append({
                 "title": title_tag.text.strip(),
@@ -89,13 +83,11 @@ def scrape_brave(query: str):
     resp = requests.get(url, headers=HEADERS, timeout=10)
     resp.raise_for_status()
     soup = BeautifulSoup(resp.text, 'lxml')
-    
     results = []
     for snippet in soup.select('.snippet'):
         title_tag = snippet.select_one('.heading')
         link_tag = snippet.select_one('a')
         desc_tag = snippet.select_one('.snippet-content, .snippet-description')
-        
         if title_tag and link_tag:
             results.append({
                 "title": title_tag.text.strip(),
@@ -104,66 +96,67 @@ def scrape_brave(query: str):
             })
     return results
 
-# --- ENDPOINTS DE LA API ---
+# --- ENDPOINTS ---
 
 @app.get("/")
 def read_root():
-    return {"status": "Glimpse API is running! Endpoints: /search, /images"}
+    return {"status": "Glimpse API is running!", "endpoints": ["/search", "/images"]}
 
 @app.get("/search")
 def search(
     q: str = Query(..., description="Término de búsqueda"), 
-    engine: str = Query("duckduckgo", description="duckduckgo, mojeek, qwant, brave")
+    engine: str = Query("duckduckgo", description="Motor de búsqueda")
 ):
     engine = engine.lower()
     results = []
-
     try:
-        if engine == "duckduckgo":
-            results = scrape_duckduckgo(q)
-        elif engine == "mojeek":
+        if engine == "mojeek":
             results = scrape_mojeek(q)
         elif engine in ["qwant", "tapnav"]:
             results = scrape_qwant(q)
         elif engine == "brave":
             results = scrape_brave(q)
-        elif engine == "startpage":
-            results = scrape_duckduckgo(q)
         else:
-            results = scrape_duckduckgo(q)
-            
-    except requests.exceptions.HTTPError as e:
-        if e.response.status_code == 403:
-            raise HTTPException(status_code=403, detail=f"El motor {engine} nos bloqueó.")
-        raise HTTPException(status_code=500, detail=str(e))
+            results = scrape_duckduckgo(q) # Duckduckgo o Startpage (como fallback)
     except Exception as e:
-        raise HTTPException(status_code=500, detail=f"Error al procesar el HTML de {engine}: {str(e)}")
-
+        raise HTTPException(status_code=500, detail=f"Error en {engine}: {str(e)}")
     return {"results": results}
 
-# --- NUEVO ENDPOINT PARA IMÁGENES ---
-
 @app.get("/images")
 def search_images(
     q: str = Query(..., description="Término de búsqueda para imágenes"),
-    max_results: int = Query(30, description="Cantidad máxima de imágenes a devolver")
+    max_results: int = Query(40, description="Cantidad máxima de imágenes")
 ):
     try:
         results = []
         with DDGS() as ddgs:
-            # duckduckgo-search tiene una función nativa robusta para esto
-            ddg_images = list(ddgs.images(q, max_results=max_results))
+            # Forzamos los parámetros correctos para la librería
+            ddg_images = list(ddgs.images(keywords=q, max_results=max_results))
+            
             for img in ddg_images:
-                results.append({
-                    "title": img.get("title", ""),
-                    "image_url": img.get("image", ""),       # URL de la imagen en alta resolución
-                    "thumbnail_url": img.get("thumbnail", ""), # URL de la miniatura (carga rápida)
-                    "source_url": img.get("url", ""),        # URL de la página web donde está la imagen
-                    "source_name": img.get("source", "")     # Nombre del sitio web
-                })
+                # Extraemos de forma segura, garantizando compatibilidad con el JS actual
+                img_url = img.get("image", "") or img.get("url", "")
+                thumb_url = img.get("thumbnail", "") or img_url
+                source_link = img.get("url", "")
+                
+                if img_url: # Solo añadimos la imagen si el enlace existe
+                    results.append({
+                        # Variables que necesita tu JS actual:
+                        "title": img.get("title", "Imagen"),
+                        "image_url": img_url,
+                        "thumbnail_url": thumb_url,
+                        "source_url": source_link,
+                        "source_name": img.get("source", ""),
+                        
+                        # Variables de compatibilidad clásica por si acaso:
+                        "url": img_url,
+                        "content": f"Fuente: {img.get('source', '')}"
+                    })
+                    
         return {"results": results}
     except Exception as e:
-        raise HTTPException(status_code=500, detail=f"Error al buscar imágenes: {str(e)}")
+        print(f"Error interno buscando imágenes: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Fallo al obtener imágenes: {str(e)}")
 
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=7860)