Update app.py

app.py

@@ -257,41 +257,47 @@ def simulate_website_scraping(url):
     return contacts
 
 def parse_csv_file(file_content):
-    """Parse CSV file and extract website URLs"""
+    """Parse CSV file and extract website URLs from column H"""
     websites = []
     try:
         # Decode file content
         content = file_content.decode('utf-8')
         
         # Parse CSV
-        csv_reader = csv.DictReader(io.StringIO(content))
+        csv_reader = csv.reader(io.StringIO(content))
         
-        # Look for common website column names (case-insensitive)
-        website_columns = ['website', 'url', 'domain', 'site', 'web', 'homepage']
-        
-        # Get all column names and print for debugging
-        all_columns = list(csv_reader.fieldnames) if csv_reader.fieldnames else []
-        print(f"CSV columns found: {all_columns}")
+        # Get the first row to determine column count
+        first_row = next(csv_reader, None)
+        if not first_row:
+            print("CSV file is empty")
+            return []
         
-        # Find the website column (case-insensitive)
-        website_column = None
-        for col_name in all_columns:
-            if col_name and col_name.lower().strip() in website_columns:
-                website_column = col_name
-                print(f"Using website column: '{website_column}'")
-                break
+        # Reset reader
+        csv_reader = csv.reader(io.StringIO(content))
         
-        if not website_column:
-            print(f"No website column found. Available columns: {all_columns}")
-            return []
+        # Skip header row if it exists (you can modify this logic if needed)
+        header_row = next(csv_reader, None)
+        print(f"Header row: {header_row}")
         
-        # Extract websites
+        row_count = 0
+        # Process each row
         for row in csv_reader:
-            website_url = row.get(website_column, '').strip()
-            if website_url:
-                websites.append(website_url)
+            row_count += 1
+            print(f"Processing row {row_count}: {row}")
+            
+            # Check if row has at least 8 columns (column H is index 7)
+            if len(row) >= 8:
+                website_url = row[7].strip()  # Column H (index 7)
+                if website_url:
+                    websites.append(website_url)
+                    print(f"Found website in row {row_count}: {website_url}")
+                else:
+                    print(f"Empty website in row {row_count}, column H")
+            else:
+                print(f"Row {row_count} has only {len(row)} columns, skipping (need at least 8 for column H)")
         
-        print(f"Extracted {len(websites)} websites: {websites[:5]}...")  # Show first 5
+        print(f"Total rows processed: {row_count}")
+        print(f"Extracted {len(websites)} websites from column H: {websites[:5]}...")  # Show first 5
         return websites
         
     except Exception as e:
@@ -299,7 +305,7 @@ def parse_csv_file(file_content):
         return []
 
 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 (column H)"""
     if csv_file is None:
         return "Please upload a CSV file", ""
     
@@ -308,7 +314,7 @@ def search_csv_websites(csv_file, max_results=10):
         websites = parse_csv_file(csv_file)
         
         if not websites:
-            return "No websites found in CSV file. Please ensure your CSV has a column named 'website', 'url', or 'domain'. Check the console for debugging info about your CSV columns.", ""
+            return "No websites found in column H of the CSV file. Please ensure your CSV has data in column H (the 8th column). Check the console for debugging info about your CSV structure.", ""
         
         all_contacts = []
         processed_websites = []
@@ -336,10 +342,11 @@ def search_csv_websites(csv_file, max_results=10):
         unique_contacts = unique_contacts[:max_results]
         
         if not unique_contacts:
-            return f"No contacts found for the {len(websites)} websites in the CSV file. Processed websites: {', '.join(websites[:10])}", ""
+            return f"No contacts found for the {len(websites)} websites from column H in the CSV file. Websites processed: {', '.join(websites[:10])}", ""
         
         # Format results
         results_text = f"CONTACT DISCOVERY REPORT\n"
+        results_text += f"CSV Column Used: H (8th column)\n"
         results_text += f"Websites Processed: {len(processed_websites)}\n"
         results_text += f"Total Websites in CSV: {len(websites)}\n"
         results_text += f"Websites with Contacts: {len(processed_websites)}\n"
@@ -609,9 +616,10 @@ with gr.Blocks(css=custom_css, title="Contact Discovery Platform", theme=gr.them
                     gr.HTML("""
                     <div style="background: #f8fafc; padding: 15px; border-radius: 8px; border-left: 4px solid #1e40af; margin: 10px 0;">
                         <strong>CSV Format Requirements:</strong><br>
-                        • Include a column named 'website', 'url', or 'domain'<br>
+                        • Website URLs should be in <strong>Column H (8th column)</strong><br>
                         • One website per row<br>
-                        • Example: techflowsolutions.com, greenleafconsult.com
+                        • Example: techflowsolutions.com, greenleafconsult.com<br>
+                        • The system will automatically read from column H regardless of headers
                     </div>
                     """)
                     
@@ -723,4 +731,4 @@ with gr.Blocks(css=custom_css, title="Contact Discovery Platform", theme=gr.them
     """)
 
 if __name__ == "__main__":
-    app.launch()
+    app.launch()