Update app.py

app.py

@@ -1,8 +1,9 @@
 import gradio as gr
+import pandas as pd
+import numpy as np
 import requests
 import re
 import json
-import csv
 import io
 from urllib.parse import urlparse, urljoin
 import time
@@ -215,6 +216,9 @@ CONTACTS_DB = [
 def extract_domain(url):
     """Extract domain from URL"""
     try:
+        if not url or pd.isna(url):
+            return ""
+        url = str(url).strip()
         if not url.startswith(('http://', 'https://')):
             url = 'https://' + url
         parsed = urlparse(url)
@@ -232,188 +236,189 @@ def find_contacts_by_website(website_url):
     if not target_domain:
         return []
     
-    print(f"Searching for domain: {target_domain}")  # Debug info
-    
     matching_contacts = []
     for contact in CONTACTS_DB:
         contact_domain = extract_domain(contact['website'])
-        print(f"Comparing with: {contact_domain}")  # Debug info
         
         # Exact domain match or subdomain match
         if target_domain == contact_domain or target_domain in contact_domain or contact_domain in target_domain:
             matching_contacts.append(contact)
     
-    print(f"Found {len(matching_contacts)} matching contacts")  # Debug info
     return matching_contacts
 
 def simulate_website_scraping(url):
     """Simulate scraping a website and finding contact information"""
     # Add some delay to simulate real scraping
-    time.sleep(random.uniform(0.5, 1))
+    time.sleep(random.uniform(0.1, 0.3))
     
     # Find matching contacts from our database
     contacts = find_contacts_by_website(url)
     
     return contacts
 
-def parse_csv_file(file_content):
-    """Parse CSV file and extract website URLs"""
-    websites = []
+def process_excel_file(excel_file):
+    """Process Excel file and populate contact information"""
+    if excel_file is None:
+        return "Please upload an Excel file", None
+    
     try:
-        # Decode file content
-        content = file_content.decode('utf-8')
+        # Read the Excel file
+        df = pd.read_excel(excel_file.name)
         
-        # Parse CSV
-        csv_reader = csv.DictReader(io.StringIO(content))
+        # Check if column H exists (index 7)
+        if df.shape[1] < 8:
+            return "Excel file must have at least 8 columns (up to column H for websites)", None
         
-        # Look for common website column names (case-insensitive)
-        website_columns = ['website', 'url', 'domain', 'site', 'web', 'homepage']
+        # Ensure we have enough columns for all contact fields
+        required_columns = 23  # Up to column W (index 22)
+        current_columns = df.shape[1]
         
-        # 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}")
+        # Add missing columns if needed
+        if current_columns < required_columns:
+            for i in range(current_columns, required_columns):
+                df[f'Column_{chr(65+i)}'] = ''
         
-        # 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
+        # Define column mappings (0-indexed)
+        website_col = 7  # Column H
+        first_name_col = 8  # Column I
+        last_name_col = 9  # Column J
+        job_title_col = 10  # Column K
+        phone_col = 11  # Column L
+        email_col = 12  # Column M
         
-        if not website_column:
-            print(f"No website column found. Available columns: {all_columns}")
-            return []
+        # Second contact columns
+        first_name_2_col = 18  # Column S
+        last_name_2_col = 19  # Column T
+        job_title_2_col = 20  # Column U
+        phone_2_col = 21  # Column V
+        email_2_col = 22  # Column W
         
-        # Extract websites
-        for row in csv_reader:
-            website_url = row.get(website_column, '').strip()
-            if website_url:
-                websites.append(website_url)
+        total_processed = 0
+        contacts_found = 0
         
-        print(f"Extracted {len(websites)} websites: {websites[:5]}...")  # Show first 5
-        return websites
+        # Process each row
+        for index, row in df.iterrows():
+            website_url = row.iloc[website_col] if pd.notna(row.iloc[website_col]) else ""
+            
+            if website_url:
+                total_processed += 1
+                print(f"Processing row {index + 1}: {website_url}")
+                
+                # Find contacts for this website
+                contacts = simulate_website_scraping(website_url)
+                
+                if contacts:
+                    contacts_found += len(contacts)
+                    
+                    # Fill in first contact
+                    if len(contacts) >= 1:
+                        contact1 = contacts[0]
+                        df.iloc[index, first_name_col] = contact1['first_name']
+                        df.iloc[index, last_name_col] = contact1['last_name']
+                        df.iloc[index, job_title_col] = contact1['job_title']
+                        df.iloc[index, phone_col] = contact1['phone']
+                        df.iloc[index, email_col] = contact1['email']
+                    
+                    # Fill in second contact if available
+                    if len(contacts) >= 2:
+                        contact2 = contacts[1]
+                        df.iloc[index, first_name_2_col] = contact2['first_name']
+                        df.iloc[index, last_name_2_col] = contact2['last_name']
+                        df.iloc[index, job_title_2_col] = contact2['job_title']
+                        df.iloc[index, phone_2_col] = contact2['phone']
+                        df.iloc[index, email_2_col] = contact2['email']
         
-    except Exception as e:
-        print(f"Error parsing CSV: {e}")
-        return []
+        # Create a summary report
+        report = f"""EXCEL CONTACT PROCESSING REPORT
+{'='*50}
 
-def search_csv_websites(csv_file, max_results=10):
-    """Search for contacts from websites listed in CSV file"""
-    if csv_file is None:
-        return "Please upload a CSV file", ""
-    
-    try:
-        # Parse CSV file
-        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.", ""
-        
-        all_contacts = []
-        processed_websites = []
-        
-        # Search each website
-        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)
-                processed_websites.append(website)
-                print(f"Found {len(contacts)} contacts for {website}")
-            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]
-        
-        if not unique_contacts:
-            return f"No contacts found for the {len(websites)} websites in the CSV file. Processed websites: {', '.join(websites[:10])}", ""
+File Processing Summary:
+- Total rows processed: {len(df)}
+- Rows with websites: {total_processed}
+- Total contacts found: {contacts_found}
+- Rows updated with contact info: {sum(1 for _, row in df.iterrows() if pd.notna(row.iloc[first_name_col]) and row.iloc[first_name_col] != '')}
+
+Column Mapping:
+- Column H: Website URLs (source)
+- Column I: Contact First Name
+- Column J: Contact Last Name  
+- Column K: Job Title
+- Column L: Phone Number
+- Column M: Email Address
+- Column S: Second Contact First Name
+- Column T: Second Contact Last Name
+- Column U: Second Contact Job Title
+- Column V: Second Contact Phone
+- Column W: Second Contact Email
+
+Processing Details:
+"""
         
-        # Format results
-        results_text = f"CONTACT DISCOVERY REPORT\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"
-        results_text += f"Unique Contacts Found: {len(unique_contacts)}\n"
-        results_text += f"Processed Websites: {', '.join(processed_websites)}\n"
-        results_text += f"{'='*60}\n\n"
+        # Add details for each processed row
+        for index, row in df.iterrows():
+            website_url = row.iloc[website_col] if pd.notna(row.iloc[website_col]) else ""
+            if website_url:
+                first_name = row.iloc[first_name_col] if pd.notna(row.iloc[first_name_col]) else ""
+                if first_name:
+                    report += f"Row {index + 1}: {website_url} -> Found contact: {first_name}\n"
+                else:
+                    report += f"Row {index + 1}: {website_url} -> No contacts found\n"
         
-        for i, contact in enumerate(unique_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"
-            results_text += f"Email: {contact['email']}\n"
-            results_text += f"Phone: {contact['phone']}\n"
-            results_text += f"Company: {contact['company']}\n"
-            results_text += f"Website: {contact['website']}\n\n"
+        # Save the updated Excel file
+        output_buffer = io.BytesIO()
+        with pd.ExcelWriter(output_buffer, engine='openpyxl') as writer:
+            df.to_excel(writer, index=False, sheet_name='Updated_Contacts')
         
-        # 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"
+        output_buffer.seek(0)
         
-        return results_text, csv_output
+        return report, output_buffer.getvalue()
         
     except Exception as e:
-        return f"Error processing CSV file: {str(e)}", ""
+        return f"Error processing Excel file: {str(e)}\n\nPlease ensure your Excel file:\n- Has websites in column H\n- Is a valid Excel format (.xlsx, .xls)\n- Is not password protected", None
 
-def search_website_contacts(website_url, max_results=10):
-    """Main function to search for contacts on a website"""
-    if not website_url:
-        return "Please enter a website URL", ""
-    
-    # Clean up URL
-    if not website_url.startswith(('http://', 'https://')):
-        website_url = 'https://' + website_url
-    
+def download_sample_excel():
+    """Create a sample Excel file for download"""
     try:
-        # Simulate finding contacts
-        contacts = simulate_website_scraping(website_url)
+        # Create sample data
+        sample_data = {
+            'A': ['Company 1', 'Company 2', 'Company 3', 'Company 4', 'Company 5'],
+            'B': ['Industry 1', 'Industry 2', 'Industry 3', 'Industry 4', 'Industry 5'],
+            'C': ['City 1', 'City 2', 'City 3', 'City 4', 'City 5'],
+            'D': ['State 1', 'State 2', 'State 3', 'State 4', 'State 5'],
+            'E': ['Country 1', 'Country 2', 'Country 3', 'Country 4', 'Country 5'],
+            'F': ['Notes 1', 'Notes 2', 'Notes 3', 'Notes 4', 'Notes 5'],
+            'G': ['Status 1', 'Status 2', 'Status 3', 'Status 4', 'Status 5'],
+            'H': ['techflowsolutions.com', 'greenleafconsult.com', 'blueskymarketing.net', 'quantumdynamics.org', 'stellarlogistics.biz'],
+            'I': ['', '', '', '', ''],  # Contact First Name
+            'J': ['', '', '', '', ''],  # Contact Last Name
+            'K': ['', '', '', '', ''],  # Job Title
+            'L': ['', '', '', '', ''],  # Phone
+            'M': ['', '', '', '', ''],  # Email
+            'N': ['', '', '', '', ''],
+            'O': ['', '', '', '', ''],
+            'P': ['', '', '', '', ''],
+            'Q': ['', '', '', '', ''],
+            'R': ['', '', '', '', ''],
+            'S': ['', '', '', '', ''],  # Second Contact First Name
+            'T': ['', '', '', '', ''],  # Second Contact Last Name
+            'U': ['', '', '', '', ''],  # Second Contact Job Title
+            'V': ['', '', '', '', ''],  # Second Contact Phone
+            'W': ['', '', '', '', ''],  # Second Contact Email
+        }
         
-        if not contacts:
-            return f"No contacts found on {website_url}. \n\nThis website is not in our contact database. Try one of the sample websites listed below, or the website might not have publicly available contact information.", ""
+        df = pd.DataFrame(sample_data)
         
-        # Limit results
-        contacts = contacts[:max_results]
+        # Save to buffer
+        output_buffer = io.BytesIO()
+        with pd.ExcelWriter(output_buffer, engine='openpyxl') as writer:
+            df.to_excel(writer, index=False, sheet_name='Sample_Template')
         
-        # Format results
-        results_text = f"CONTACT INTELLIGENCE REPORT\n"
-        results_text += f"Website: {website_url}\n"
-        results_text += f"Contacts Found: {len(contacts)}\n"
-        results_text += f"{'='*60}\n\n"
-        
-        for i, contact in enumerate(contacts, 1):
-            results_text += f"CONTACT #{i}\n"
-            results_text += f"First Name: {contact['first_name']}\n"
-            results_text += f"Last Name: {contact['last_name']}\n"
-            results_text += f"Position: {contact['job_title']}\n"
-            results_text += f"Email: {contact['email']}\n"
-            results_text += f"Phone: {contact['phone']}\n"
-            results_text += f"Company: {contact['company']}\n\n"
-        
-        # Create a simple table format for the second output
-        table_text = "First Name,Last Name,Job Title,Email,Phone,Company\n"
-        for contact in contacts:
-            table_text += f"{contact['first_name']},{contact['last_name']},{contact['job_title']},{contact['email']},{contact['phone']},{contact['company']}\n"
-        
-        return results_text, table_text
+        output_buffer.seek(0)
+        return output_buffer.getvalue()
         
     except Exception as e:
-        return f"Error searching website: {str(e)}", ""
-
-def get_all_available_websites():
-    """Get list of all available websites from the database"""
-    websites = list(set([contact['website'] for contact in CONTACTS_DB]))
-    return "\n".join(sorted(websites))
+        print(f"Error creating sample Excel: {e}")
+        return None
 
 # Custom CSS
 custom_css = """
@@ -445,28 +450,22 @@ custom_css = """
     opacity: 0.9;
 }
 
-.corporate-card {
-    background: white;
-    border: 1px solid #d1d5db;
-    border-radius: 12px;
-    padding: 25px;
-    margin: 15px 0;
-    box-shadow: 0 4px 15px rgba(0,0,0,0.1);
-    border-left: 5px solid #1e40af;
+.section-header {
+    background: linear-gradient(135deg, #64748b 0%, #475569 100%);
+    color: white;
+    padding: 15px 20px;
+    border-radius: 10px;
+    margin: 20px 0 15px 0;
+    font-weight: 600;
 }
 
-.tips-section {
+.info-box {
     background: linear-gradient(135deg, #f1f5f9 0%, #e2e8f0 100%);
     border: 2px solid #cbd5e1;
     border-radius: 15px;
     padding: 20px;
     margin: 10px 0;
-}
-
-.tips-section h3 {
-    color: #1e40af;
-    margin-top: 0;
-    font-weight: 600;
+    border-left: 5px solid #1e40af;
 }
 
 .primary-btn {
@@ -480,41 +479,6 @@ custom_css = """
     transition: all 0.3s ease;
 }
 
-.primary-btn:hover {
-    background: linear-gradient(135deg, #1e3a8a 0%, #2563eb 100%);
-    transform: translateY(-2px);
-    box-shadow: 0 6px 20px rgba(30, 64, 175, 0.4);
-}
-
-.secondary-btn {
-    background: white;
-    color: #374151;
-    border: 2px solid #d1d5db;
-    border-radius: 6px;
-    padding: 8px 16px;
-    font-weight: 500;
-    transition: all 0.3s ease;
-}
-
-.secondary-btn:hover {
-    border-color: #1e40af;
-    color: #1e40af;
-    background: #f8fafc;
-}
-
-.custom-input {
-    border: 2px solid #d1d5db;
-    border-radius: 8px;
-    padding: 12px;
-    font-size: 16px;
-    transition: border-color 0.3s ease;
-}
-
-.custom-input:focus {
-    border-color: #3b82f6;
-    box-shadow: 0 0 0 3px rgba(59, 130, 246, 0.1);
-}
-
 .results-container {
     background: white;
     border: 1px solid #e5e7eb;
@@ -523,202 +487,149 @@ custom_css = """
     margin: 15px 0;
     box-shadow: 0 2px 10px rgba(0,0,0,0.05);
 }
-
-.section-header {
-    background: linear-gradient(135deg, #64748b 0%, #475569 100%);
-    color: white;
-    padding: 15px 20px;
-    border-radius: 10px;
-    margin: 20px 0 15px 0;
-    font-weight: 600;
-}
 """
 
 # Create Gradio interface
-with gr.Blocks(css=custom_css, title="Contact Discovery Platform", theme=gr.themes.Base()) as app:
+with gr.Blocks(css=custom_css, title="Excel Contact Discovery Platform", theme=gr.themes.Base()) as app:
     gr.HTML("""
     <div class="main-header">
-        <h1>Contact Discovery Platform</h1>
-        <p>Professional Contact Discovery & Lead Generation Tool</p>
-        <p style="font-size: 0.95em; opacity: 0.8;">Advanced website analysis for contact intelligence gathering</p>
+        <h1>Excel Contact Discovery Platform</h1>
+        <p>Automated Contact Discovery for Excel Spreadsheets</p>
+        <p style="font-size: 0.95em; opacity: 0.8;">Upload your Excel file and automatically populate contact information</p>
     </div>
     """)
     
-    with gr.Tabs():
-        # Single Website Search Tab
-        with gr.TabItem("Single Website Search"):
-            with gr.Row():
-                with gr.Column(scale=2):
-                    gr.HTML('<div class="section-header">Search Parameters</div>')
-                    
-                    website_input = gr.Textbox(
-                        label="Target Website URL",
-                        placeholder="Enter company website (e.g., techflowsolutions.com)",
-                        value="",
-                        elem_classes=["custom-input"]
-                    )
-                    
-                    with gr.Row():
-                        max_results = gr.Slider(
-                            minimum=1,
-                            maximum=20,
-                            value=8,
-                            step=1,
-                            label="Maximum Results",
-                            elem_classes=["custom-input"]
-                        )
-                        
-                        search_btn = gr.Button(
-                            "Execute Search", 
-                            variant="primary", 
-                            size="lg",
-                            elem_classes=["primary-btn"]
-                        )
-            
-            gr.HTML('<div class="section-header">Search Results</div>')
-            
-            with gr.Row():
-                results_display = gr.Textbox(
-                    label="Contact Intelligence Report",
-                    lines=18,
-                    max_lines=35,
-                    show_copy_button=True,
-                    elem_classes=["results-container"]
-                )
-                
-                csv_output = gr.Textbox(
-                    label="Export Data (CSV Format)",
-                    lines=18,
-                    max_lines=35,
-                    show_copy_button=True,
-                    elem_classes=["results-container"]
-                )
+    with gr.Tab("Excel Processing"):
+        gr.HTML('<div class="section-header">Excel File Upload</div>')
         
-        # CSV Upload Tab
-        with gr.TabItem("CSV Bulk Search"):
-            with gr.Row():
-                with gr.Column(scale=2):
-                    gr.HTML('<div class="section-header">CSV Upload</div>')
-                    
-                    csv_file = gr.File(
-                        label="Upload CSV File",
-                        file_types=[".csv"],
-                        elem_classes=["custom-input"]
-                    )
-                    
-                    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>
-                        • One website per row<br>
-                        • Example: techflowsolutions.com, greenleafconsult.com
-                    </div>
-                    """)
-                    
-                    with gr.Row():
-                        csv_max_results = gr.Slider(
-                            minimum=1,
-                            maximum=50,
-                            value=20,
-                            step=1,
-                            label="Maximum Results",
-                            elem_classes=["custom-input"]
-                        )
-                        
-                        csv_search_btn = gr.Button(
-                            "Process CSV", 
-                            variant="primary", 
-                            size="lg",
-                            elem_classes=["primary-btn"]
-                        )
-            
-            gr.HTML('<div class="section-header">CSV Results</div>')
-            
-            with gr.Row():
-                csv_results_display = gr.Textbox(
-                    label="CSV Processing Report",
-                    lines=18,
-                    max_lines=35,
-                    show_copy_button=True,
-                    elem_classes=["results-container"]
+        with gr.Row():
+            with gr.Column(scale=2):
+                excel_file = gr.File(
+                    label="Upload Excel File (.xlsx, .xls)",
+                    file_types=[".xlsx", ".xls"],
+                    elem_classes=["custom-input"]
                 )
                 
-                csv_export_output = gr.Textbox(
-                    label="Export Data (CSV Format)",
-                    lines=18,
-                    max_lines=35,
-                    show_copy_button=True,
-                    elem_classes=["results-container"]
+                process_btn = gr.Button(
+                    "Process Excel File", 
+                    variant="primary", 
+                    size="lg",
+                    elem_classes=["primary-btn"]
                 )
-    
-    # Sample websites section
-    with gr.Accordion("Sample Websites Database", open=False):
-        gr.HTML('<div style="background: #f8fafc; padding: 15px; border-radius: 8px; border-left: 4px solid #1e40af;">')
-        sample_websites = gr.Textbox(
-            label="Available Websites in Database",
-            value=get_all_available_websites(),
-            lines=8,
-            interactive=False,
-            elem_classes=["custom-input"]
+        
+        gr.HTML("""
+        <div class="info-box">
+            <h3>Excel File Requirements:</h3>
+            <ul>
+                <li><strong>Column H:</strong> Must contain website URLs (e.g., techflowsolutions.com)</li>
+                <li><strong>Contact Info will be populated in:</strong></li>
+                <ul>
+                    <li>Column I: Contact First Name</li>
+                    <li>Column J: Contact Last Name</li>
+                    <li>Column K: Job Title</li>
+                    <li>Column L: Phone Number</li>
+                    <li>Column M: Email Address</li>
+                </ul>
+                <li><strong>Second Contact (if found) will be populated in:</strong></li>
+                <ul>
+                    <li>Column S: Second Contact First Name</li>
+                    <li>Column T: Second Contact Last Name</li>
+                    <li>Column U: Second Contact Job Title</li>
+                    <li>Column V: Second Contact Phone</li>
+                    <li>Column W: Second Contact Email</li>
+                </ul>
+            </ul>
+        </div>
+        """)
+        
+        gr.HTML('<div class="section-header">Processing Results</div>')
+        
+        processing_report = gr.Textbox(
+            label="Processing Report",
+            lines=20,
+            max_lines=30,
+            show_copy_button=True,
+            elem_classes=["results-container"]
+        )
+        
+        download_file = gr.File(
+            label="Download Updated Excel File",
+            elem_classes=["results-container"]
         )
-        gr.HTML('</div>')
-    
-    # Quick search buttons
-    gr.HTML('<div class="section-header">Quick Access Sample Websites</div>')
     
-    with gr.Row():
-        quick_btn1 = gr.Button("TechFlow Solutions", size="sm", elem_classes=["secondary-btn"])
-        quick_btn2 = gr.Button("GreenLeaf Consulting", size="sm", elem_classes=["secondary-btn"])
-        quick_btn3 = gr.Button("BlueSky Marketing", size="sm", elem_classes=["secondary-btn"])
-        quick_btn4 = gr.Button("Quantum Dynamics", size="sm", elem_classes=["secondary-btn"])
+    with gr.Tab("Sample Template"):
+        gr.HTML('<div class="section-header">Download Sample Template</div>')
+        
+        gr.HTML("""
+        <div class="info-box">
+            <h3>Sample Excel Template</h3>
+            <p>Download this sample template to see the expected format. The template includes:</p>
+            <ul>
+                <li>Sample data in columns A-G</li>
+                <li>Website URLs in column H</li>
+                <li>Empty contact columns (I-M) ready to be populated</li>
+                <li>Empty second contact columns (S-W) ready to be populated</li>
+            </ul>
+            <p>Replace the sample websites in column H with your actual website URLs.</p>
+        </div>
+        """)
+        
+        sample_download_btn = gr.Button(
+            "Download Sample Template", 
+            variant="secondary", 
+            size="lg"
+        )
+        
+        sample_file = gr.File(
+            label="Sample Template Download",
+            elem_classes=["results-container"]
+        )
     
-    with gr.Row():
-        quick_btn5 = gr.Button("Stellar Logistics", size="sm", elem_classes=["secondary-btn"])
-        quick_btn6 = gr.Button("Nexus Financial", size="sm", elem_classes=["secondary-btn"])
-        quick_btn7 = gr.Button("Horizon Health", size="sm", elem_classes=["secondary-btn"])
-        quick_btn8 = gr.Button("Phoenix Manufacturing", size="sm", elem_classes=["secondary-btn"])
+    with gr.Tab("Available Sample Websites"):
+        gr.HTML('<div class="section-header">Test Websites Database</div>')
+        
+        sample_websites_text = """Available websites in our test database:
+
+techflowsolutions.com - TechFlow Solutions
+greenleafconsult.com - GreenLeaf Consulting  
+blueskymarketing.net - BlueSky Marketing
+quantumdynamics.org - Quantum Dynamics Corp
+stellarlogistics.biz - Stellar Logistics
+nexusfinancial.pro - Nexus Financial
+horizonhealth.care - Horizon Health Systems
+phoenixmfg.com - Phoenix Manufacturing
+alpineeducation.edu - Alpine Education Group
+crimsoncreative.studio - Crimson Creative Studio
+
+You can use these websites in column H of your Excel file to test the system."""
+        
+        gr.Textbox(
+            value=sample_websites_text,
+            label="Sample Websites for Testing",
+            lines=15,
+            interactive=False,
+            elem_classes=["results-container"]
+        )
     
     # Event handlers
-    search_btn.click(
-        fn=search_website_contacts,
-        inputs=[website_input, max_results],
-        outputs=[results_display, csv_output]
+    process_btn.click(
+        fn=process_excel_file,
+        inputs=[excel_file],
+        outputs=[processing_report, download_file]
     )
     
-    csv_search_btn.click(
-        fn=search_csv_websites,
-        inputs=[csv_file, csv_max_results],
-        outputs=[csv_results_display, csv_export_output]
-    )
-    
-    # Quick search button handlers
-    quick_btn1.click(lambda: "techflowsolutions.com", outputs=website_input)
-    quick_btn2.click(lambda: "greenleafconsult.com", outputs=website_input)
-    quick_btn3.click(lambda: "blueskymarketing.net", outputs=website_input)
-    quick_btn4.click(lambda: "quantumdynamics.org", outputs=website_input)
-    quick_btn5.click(lambda: "stellarlogistics.biz", outputs=website_input)
-    quick_btn6.click(lambda: "nexusfinancial.pro", outputs=website_input)
-    quick_btn7.click(lambda: "horizonhealth.care", outputs=website_input)
-    quick_btn8.click(lambda: "phoenixmfg.com", outputs=website_input)
-    
-    # Examples
-    gr.Examples(
-        examples=[
-            ["techflowsolutions.com", 5],
-            ["greenleafconsult.com", 3],
-            ["blueskymarketing.net", 4],
-            ["quantumdynamics.org", 6]
-        ],
-        inputs=[website_input, max_results],
-        label="Sample Searches"
+    sample_download_btn.click(
+        fn=download_sample_excel,
+        inputs=[],
+        outputs=[sample_file]
     )
     
     # Footer
     gr.HTML("""
     <div style="text-align: center; padding: 30px 20px; background: linear-gradient(135deg, #64748b 0%, #475569 100%); color: white; border-radius: 15px; margin-top: 30px;">
-        <h3 style="margin: 0 0 10px 0;">Contact Intelligence Platform</h3>
-        <p style="margin: 0; opacity: 0.9;">Professional-grade contact discovery and lead generation technology</p>
-        <p style="margin: 10px 0 0 0; font-size: 0.9em; opacity: 0.7;">Powered by advanced web intelligence algorithms</p>
+        <h3 style="margin: 0 0 10px 0;">Excel Contact Discovery Platform</h3>
+        <p style="margin: 0; opacity: 0.9;">Automated contact discovery and Excel integration</p>
+        <p style="margin: 10px 0 0 0; font-size: 0.9em; opacity: 0.7;">Upload Excel → Find Contacts → Download Updated File</p>
     </div>
     """)