Update app.py

app.py

@@ -4,7 +4,6 @@ import re
 import json
 import csv
 import io
-import pandas as pd
 from urllib.parse import urlparse, urljoin
 import time
 import random
@@ -257,92 +256,6 @@ def simulate_website_scraping(url):
     
     return contacts
 
-def process_excel_file(file_path):
-    """Process Excel file and update with contact information"""
-    if file_path is None:
-        return "Please upload an Excel file", ""
-    
-    try:
-        # Read the Excel file
-        df = pd.read_excel(file_path)
-        
-        print(f"Excel file loaded with {len(df)} rows and {len(df.columns)} columns")
-        print(f"Columns: {list(df.columns)}")
-        
-        # Check if column H exists (0-indexed, so H is column 7)
-        if len(df.columns) < 8:
-            return "Excel file must have at least 8 columns (up to column H for websites)", ""
-        
-        # Extend dataframe to have all required columns (up to column W = 22 columns)
-        required_columns = 23  # A through W (0-indexed)
-        current_columns = len(df.columns)
-        
-        if current_columns < required_columns:
-            for i in range(current_columns, required_columns):
-                df[f'Column_{chr(65+i)}'] = ''
-        
-        processed_websites = []
-        contacts_found = 0
-        
-        # Process each row
-        for index, row in df.iterrows():
-            website_url = str(row.iloc[7]).strip() if pd.notna(row.iloc[7]) else ""  # Column H (0-indexed 7)
-            
-            if not website_url or website_url.lower() in ['nan', 'none', '']:
-                continue
-            
-            print(f"Processing row {index + 1}: {website_url}")
-            
-            # Find contacts for this website
-            contacts = simulate_website_scraping(website_url)
-            
-            if contacts:
-                processed_websites.append(website_url)
-                contacts_found += len(contacts)
-                
-                # First contact - columns I, J, K, L, M (0-indexed: 8, 9, 10, 11, 12)
-                if len(contacts) >= 1:
-                    df.iloc[index, 8] = contacts[0]['first_name']    # Column I
-                    df.iloc[index, 9] = contacts[0]['last_name']     # Column J
-                    df.iloc[index, 10] = contacts[0]['job_title']    # Column K
-                    df.iloc[index, 11] = contacts[0]['phone']        # Column L
-                    df.iloc[index, 12] = contacts[0]['email']        # Column M
-                
-                # Second contact - columns S, T, U, V, W (0-indexed: 18, 19, 20, 21, 22)
-                if len(contacts) >= 2:
-                    df.iloc[index, 18] = contacts[1]['first_name']   # Column S
-                    df.iloc[index, 19] = contacts[1]['last_name']    # Column T
-                    df.iloc[index, 20] = contacts[1]['job_title']    # Column U
-                    df.iloc[index, 21] = contacts[1]['phone']        # Column V
-                    df.iloc[index, 22] = contacts[1]['email']        # Column W
-        
-        # Create results summary
-        results_text = f"EXCEL PROCESSING REPORT\n"
-        results_text += f"Total Rows Processed: {len(df)}\n"
-        results_text += f"Websites Found in Column H: {len([x for x in df.iloc[:, 7] if pd.notna(x) and str(x).strip() and str(x).lower() not in ['nan', 'none']])}\n"
-        results_text += f"Websites with Contacts: {len(processed_websites)}\n"
-        results_text += f"Total Contacts Found: {contacts_found}\n"
-        results_text += f"{'='*60}\n\n"
-        
-        if processed_websites:
-            results_text += f"Websites Successfully Processed:\n"
-            for i, website in enumerate(processed_websites, 1):
-                results_text += f"{i}. {website}\n"
-        else:
-            results_text += "No contacts found for any websites in the Excel file.\n"
-            results_text += f"Sample websites from Column H: {list(df.iloc[:5, 7].dropna())}\n"
-        
-        # Save updated Excel file to a temporary location and convert to CSV for display
-        csv_buffer = io.StringIO()
-        df.to_csv(csv_buffer, index=False)
-        csv_output = csv_buffer.getvalue()
-        
-        return results_text, csv_output
-        
-    except Exception as e:
-        print(f"Error processing Excel file: {e}")
-        return f"Error processing Excel file: {str(e)}", ""
-
 def parse_csv_file(file_content):
     """Parse CSV file and extract website URLs"""
     websites = []
@@ -681,59 +594,57 @@ with gr.Blocks(css=custom_css, title="Contact Discovery Platform", theme=gr.them
                     elem_classes=["results-container"]
                 )
         
-        # Excel/CSV Upload Tab
-        with gr.TabItem("Excel/CSV Bulk Search"):
+        # CSV Upload Tab
+        with gr.TabItem("CSV Bulk Search"):
             with gr.Row():
                 with gr.Column(scale=2):
-                    gr.HTML('<div class="section-header">File Upload</div>')
+                    gr.HTML('<div class="section-header">CSV Upload</div>')
                     
-                    excel_file = gr.File(
-                        label="Upload Excel or CSV File",
-                        file_types=[".xlsx", ".xls", ".csv"],
+                    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>Excel File Requirements:</strong><br>
-                        • Websites should be in column H<br>
-                        • Contact info will be populated in:<br>
-                        &nbsp;&nbsp;- First contact: I(First Name), J(Last Name), K(Job Title), L(Phone), M(Email)<br>
-                        &nbsp;&nbsp;- Second contact: S(First Name), T(Last Name), U(Job Title), V(Phone), W(Email)<br><br>
-                        <strong>CSV File Requirements:</strong><br>
+                        <strong>CSV Format Requirements:</strong><br>
                         • Include a column named 'website', 'url', or 'domain'<br>
-                        • One website per row
+                        • One website per row<br>
+                        • Example: techflowsolutions.com, greenleafconsult.com
                     </div>
                     """)
                     
                     with gr.Row():
-                        file_type = gr.Radio(
-                            choices=["Excel Processing", "CSV Processing"],
-                            value="Excel Processing",
-                            label="File Type",
+                        csv_max_results = gr.Slider(
+                            minimum=1,
+                            maximum=50,
+                            value=20,
+                            step=1,
+                            label="Maximum Results",
                             elem_classes=["custom-input"]
                         )
                         
-                        process_btn = gr.Button(
-                            "Process File", 
+                        csv_search_btn = gr.Button(
+                            "Process CSV", 
                             variant="primary", 
                             size="lg",
                             elem_classes=["primary-btn"]
                         )
             
-            gr.HTML('<div class="section-header">Processing Results</div>')
+            gr.HTML('<div class="section-header">CSV Results</div>')
             
             with gr.Row():
-                file_results_display = gr.Textbox(
-                    label="File Processing Report",
+                csv_results_display = gr.Textbox(
+                    label="CSV Processing Report",
                     lines=18,
                     max_lines=35,
                     show_copy_button=True,
                     elem_classes=["results-container"]
                 )
                 
-                file_export_output = gr.Textbox(
-                    label="Updated File Data (CSV Format)",
+                csv_export_output = gr.Textbox(
+                    label="Export Data (CSV Format)",
                     lines=18,
                     max_lines=35,
                     show_copy_button=True,
@@ -753,4 +664,63 @@ with gr.Blocks(css=custom_css, title="Contact Discovery Platform", theme=gr.them
         gr.HTML('</div>')
     
     # Quick search buttons
-    gr.HTML('<div class="section-header">
+    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.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"])
+    
+    # Event handlers
+    search_btn.click(
+        fn=search_website_contacts,
+        inputs=[website_input, max_results],
+        outputs=[results_display, csv_output]
+    )
+    
+    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"
+    )
+    
+    # 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>
+    </div>
+    """)
+
+if __name__ == "__main__":
+    app.launch()