Update app.py

app.py

@@ -370,8 +370,42 @@ def parse_csv_file(file_obj):
         debug_info.append(f"Error parsing CSV: {e}")
         return [], debug_info
 
+def rank_contact_by_title(job_title):
+    """Rank contacts by job title priority (lower number = higher priority)"""
+    title_lower = job_title.lower()
+    
+    # Define ranking hierarchy
+    if 'president' in title_lower:
+        return 1
+    elif 'ceo' in title_lower or 'chief executive' in title_lower:
+        return 2
+    elif 'cfo' in title_lower or 'chief financial' in title_lower:
+        return 3
+    elif 'coo' in title_lower or 'chief operating' in title_lower:
+        return 4
+    elif 'vice president' in title_lower or 'vp' in title_lower or 'v.p.' in title_lower:
+        return 5
+    elif 'controller' in title_lower:
+        return 6
+    elif 'general manager' in title_lower or 'gm' in title_lower:
+        return 7
+    else:
+        return 100  # All other positions get lower priority
+
+def get_best_contact_for_website(website_url):
+    """Get the highest-ranked contact for a specific website"""
+    contacts = simulate_website_scraping(website_url)
+    if not contacts:
+        return None
+    
+    # Sort contacts by job title ranking
+    contacts_with_rank = [(contact, rank_contact_by_title(contact['job_title'])) for contact in contacts]
+    contacts_with_rank.sort(key=lambda x: x[1])  # Sort by rank (lower number = higher priority)
+    
+    return contacts_with_rank[0][0]  # Return the highest-ranked contact
+
 def search_csv_websites(csv_file, max_results=10):
-    """Search for contacts from websites listed in CSV file"""
+    """Search for contacts from websites listed in CSV file and populate the CSV"""
     if csv_file is None:
         return "Please upload a CSV file", ""
     
@@ -391,45 +425,78 @@ def search_csv_websites(csv_file, max_results=10):
             error_msg += "4. Verify the CSV file is not corrupted\n"
             return error_msg, ""
         
+        # Read the original CSV file to preserve all data
+        with open(csv_file.name, 'r', encoding='utf-8') as f:
+            content = f.read()
+        
+        csv_reader = csv.reader(io.StringIO(content))
+        original_rows = list(csv_reader)
+        
+        # Process websites and find contacts
         all_contacts = []
         processed_websites = []
+        contacts_by_website = {}
         
-        # Search each website
+        # Create a mapping of websites to their row indices
+        website_to_row = {}
+        for row_idx, row in enumerate(original_rows):
+            if len(row) > 7:  # Column H exists
+                website_url = row[7].strip()
+                if website_url and is_valid_url(website_url):
+                    website_to_row[website_url] = row_idx
+        
+        # Search each website and get the best contact
         for website in websites[:20]:  # Limit to first 20 websites
             print(f"Processing website: {website}")
-            contacts = simulate_website_scraping(website)
-            if contacts:
-                all_contacts.extend(contacts)
+            best_contact = get_best_contact_for_website(website)
+            
+            if best_contact:
+                contacts_by_website[website] = best_contact
+                all_contacts.append(best_contact)
                 processed_websites.append(website)
-                print(f"Found {len(contacts)} contacts for {website}")
+                print(f"Found best contact for {website}: {best_contact['first_name']} {best_contact['last_name']} - {best_contact['job_title']}")
             else:
                 print(f"No contacts found for {website}")
         
-        # Remove duplicates based on email
-        unique_contacts = []
-        seen_emails = set()
-        for contact in all_contacts:
-            if contact['email'] not in seen_emails:
-                unique_contacts.append(contact)
-                seen_emails.add(contact['email'])
-        
-        # Limit results
-        unique_contacts = unique_contacts[:max_results]
+        # Create updated CSV with contact information
+        updated_rows = []
+        for row_idx, row in enumerate(original_rows):
+            # Make a copy of the row and ensure it has enough columns
+            new_row = row[:]
+            
+            # Extend row to have at least 13 columns (A-M)
+            while len(new_row) < 13:
+                new_row.append("")
+            
+            # Check if this row has a website we found contacts for
+            if len(row) > 7:
+                website_url = row[7].strip()
+                if website_url in contacts_by_website:
+                    contact = contacts_by_website[website_url]
+                    
+                    # Populate contact information in specified columns
+                    new_row[8] = contact['first_name']     # Column I (index 8)
+                    new_row[9] = contact['last_name']      # Column J (index 9)
+                    new_row[10] = contact['job_title']     # Column K (index 10)
+                    new_row[11] = contact['phone']         # Column L (index 11)
+                    new_row[12] = contact['email']         # Column M (index 12)
+            
+            updated_rows.append(new_row)
         
-        if not unique_contacts:
+        if not all_contacts:
             result_msg = f"No contacts found for the {len(websites)} websites from the CSV file.\n\n"
             result_msg += "DEBUG INFORMATION:\n" + debug_text + "\n\n"
             result_msg += f"Websites processed: {', '.join(websites[:10])}\n"
             result_msg += "This might be because the websites are not in our sample database."
             return result_msg, ""
         
-        # Format results
+        # Format results text
         results_text = f"CONTACT DISCOVERY REPORT\n"
         results_text += f"CSV Processing Details:\n"
         results_text += f"Total Websites in CSV: {len(websites)}\n"
         results_text += f"Websites Processed: {len(processed_websites)}\n"
         results_text += f"Websites with Contacts: {len(processed_websites)}\n"
-        results_text += f"Unique Contacts Found: {len(unique_contacts)}\n"
+        results_text += f"Contacts Found: {len(all_contacts)}\n"
         results_text += f"Processed Websites: {', '.join(processed_websites)}\n"
         results_text += f"{'='*60}\n\n"
         
@@ -437,7 +504,17 @@ def search_csv_websites(csv_file, max_results=10):
         results_text += "DEBUG INFORMATION:\n" + debug_text + "\n\n"
         results_text += f"{'='*60}\n\n"
         
-        for i, contact in enumerate(unique_contacts, 1):
+        # Show contact rankings
+        results_text += "CONTACT RANKINGS (by job title priority):\n"
+        for i, contact in enumerate(all_contacts, 1):
+            rank = rank_contact_by_title(contact['job_title'])
+            results_text += f"{i}. {contact['first_name']} {contact['last_name']} - {contact['job_title']} "
+            results_text += f"(Priority Rank: {rank}) - {contact['company']}\n"
+        
+        results_text += f"\n{'='*60}\n\n"
+        
+        # Show detailed contact information
+        for i, contact in enumerate(all_contacts, 1):
             results_text += f"CONTACT #{i}\n"
             results_text += f"Name: {contact['first_name']} {contact['last_name']}\n"
             results_text += f"Position: {contact['job_title']}\n"
@@ -446,12 +523,17 @@ def search_csv_websites(csv_file, max_results=10):
             results_text += f"Company: {contact['company']}\n"
             results_text += f"Website: {contact['website']}\n\n"
         
-        # Create CSV output
-        csv_output = "First Name,Last Name,Job Title,Email,Phone,Company,Website\n"
-        for contact in unique_contacts:
-            csv_output += f"{contact['first_name']},{contact['last_name']},{contact['job_title']},{contact['email']},{contact['phone']},{contact['company']},{contact['website']}\n"
+        # Create CSV output with updated data
+        csv_output = io.StringIO()
+        csv_writer = csv.writer(csv_output)
+        
+        for row in updated_rows:
+            csv_writer.writerow(row)
+        
+        csv_content = csv_output.getvalue()
+        csv_output.close()
         
-        return results_text, csv_output
+        return results_text, csv_content
         
     except Exception as e:
         return f"Error processing CSV file: {str(e)}", ""