search-duckduck

usr/bin/search-duckduck

@@ -1,32 +1,32 @@
 #!/usr/bin/env python
+
 import sys
 import subprocess
 
-# Vérifie et installe bs4 si nécessaire
-try:
-    from bs4 import BeautifulSoup
-except ImportError:
-    print("bs4 non trouvé, installation en cours...")
-    subprocess.check_call([sys.executable, "-m", "pip", "install", "beautifulsoup4"])
-    from bs4 import BeautifulSoup
+# Vérifie et installe les dépendances si nécessaire
+def ensure_package(pkg):
+    try:
+        __import__(pkg)
+    except ImportError:
+        print(f"{pkg} non trouvé, installation...")
+        subprocess.check_call([sys.executable, "-m", "pip", "install", pkg])
 
+ensure_package("bs4")
+ensure_package("requests")
+
+from bs4 import BeautifulSoup
 import requests
 import argparse
 
 
 def recherche_duckduckgo(query, n=5):
     url = "https://html.duckduckgo.com/html/"
-    params = {"q": query}
+    headers = {"User-Agent": "Mozilla/5.0"}
 
-    headers = {
-        "User-Agent": "Mozilla/5.0"
-    }
-
-    response = requests.post(url, data=params, headers=headers)
+    response = requests.post(url, data={"q": query}, headers=headers)
     soup = BeautifulSoup(response.text, "html.parser")
 
     results = []
-
     for result in soup.find_all("a", class_="result__a", limit=n):
         title = result.get_text()
         link = result.get("href")
@@ -35,18 +35,38 @@ def recherche_duckduckgo(query, n=5):
     return results
 
 
+def extract_text(url, max_chars=300):
+    try:
+        headers = {"User-Agent": "Mozilla/5.0"}
+        response = requests.get(url, headers=headers, timeout=5)
+
+        soup = BeautifulSoup(response.text, "html.parser")
+
+        # Récupère le texte brut
+        text = soup.get_text(separator=" ", strip=True)
+
+        return text[:max_chars] + "..."
+
+    except Exception as e:
+        return f"[Erreur lors de l'accès au site: {e}]"
+
+
 def main():
-    parser = argparse.ArgumentParser(description="Recherche DuckDuckGo simple")
+    parser = argparse.ArgumentParser(description="Recherche + extraction de texte")
     parser.add_argument("query", type=str, help="Terme de recherche")
-    parser.add_argument("-n", "--number", type=int, default=5, help="Nombre de résultats")
+    parser.add_argument("-n", "--number", type=int, default=3, help="Nombre de résultats")
+    parser.add_argument("--chars", type=int, default=300, help="Nombre de caractères à extraire")
 
     args = parser.parse_args()
 
     results = recherche_duckduckgo(args.query, args.number)
 
     for i, (title, link) in enumerate(results, 1):
-        print(f"{i}. {title}")
-        print(f"   {link}\n")
+        print(f"\n{i}. {title}")
+        print(f"URL: {link}")
+
+        snippet = extract_text(link, args.chars)
+        print(f"Extrait: {snippet}")
 
 
 if __name__ == "__main__":