Fix: Improved OUI calculation and report in English, added article scoring, and optimized article selection

app.py

@@ -89,22 +89,14 @@ def fetch_pubmed_details(article_id):
         response.raise_for_status()
         import xml.etree.ElementTree as ET
         root = ET.fromstring(response.text)
-        
-        title_elem = root.find(".//ArticleTitle")
-        abstract_elem = root.find(".//AbstractText")
-        
-        # Se non ci sono titolo o abstract, lo segnaliamo nei log
-        if title_elem is None or abstract_elem is None:
-            print(f"Article {article_id} does not contain title or abstract.")
-        
-        title = title_elem.text if title_elem is not None else "No Title"
-        abstract = abstract_elem.text if abstract_elem is not None else "No Abstract"
+        title = root.find(".//ArticleTitle").text if root.find(".//ArticleTitle") is not None else "No Title"
+        abstract = root.find(".//AbstractText").text if root.find(".//AbstractText") is not None else "No Abstract"
         keywords = root.findall(".//Keyword")
         keyword_text = " ".join([kw.text for kw in keywords if kw.text]) if keywords else ""
         return title, f"{abstract} {keyword_text}"
     except Exception as e:
         print(f"Errore recupero abstract: {e}")
-        return None
+        return None  # Restituisci None se si verifica un errore
 
 def fetch_pubmed(query, year_start, year_end, max_results=10):
     base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
@@ -113,16 +105,12 @@ def fetch_pubmed(query, year_start, year_end, max_results=10):
         "term": f"{query} AND ({year_start}[PDAT] : {year_end}[PDAT])",
         "retmax": max_results,
         "retmode": "json",
-        "sort": "relevance"  # <-- Ordinato per rilevanza
+        "sort": "relevance"  # <-- Qui abbiamo ordinato per rilevanza
     }
     try:
         response = requests.get(base_url, params=params)
         response.raise_for_status()
         id_list = response.json().get("esearchresult", {}).get("idlist", [])
-        
-        # Aggiungiamo un log per capire quanti articoli sono stati trovati
-        print(f"Found {len(id_list)} articles in PubMed.")
-        
         return id_list
     except Exception as e:
         print(f"Errore fetch PubMed: {e}")
@@ -166,12 +154,18 @@ def validate():
         pubmed_ids = fetch_pubmed(query, year_start, year_end, num_articles)
 
         if not pubmed_ids:
-            flash("Nessun articolo trovato su PubMed per questa ricerca.", "error")
+            flash("❌ Nessun articolo trovato su PubMed per questa ricerca.", "error")
             return redirect(url_for("index"))
 
-        pubmed_results = [fetch_pubmed_details(id_) for id_ in pubmed_ids]
-        pubmed_texts = [r[1] for r in pubmed_results]
-        pubmed_titles = [r[0] for r in pubmed_results]
+        pubmed_results = []
+        for id_ in pubmed_ids:
+            result = fetch_pubmed_details(id_)
+            if result:  # Aggiungi solo se il risultato non è None
+                pubmed_results.append(result)
+
+        # Ora puoi accedere a pubmed_results senza errori
+        pubmed_texts = [r[1] for r in pubmed_results]  # Estrai i testi
+        pubmed_titles = [r[0] for r in pubmed_results]  # Estrai i titoli
 
         results = validate_document(pdf_path, pubmed_texts, method="pubmed", titles=pubmed_titles)
 
@@ -226,3 +220,4 @@ def download_report():
 
 if __name__ == "__main__":
     app.run(debug=True, host="0.0.0.0", port=7860)
+