Update app.py
Browse files
app.py
CHANGED
|
@@ -1,9 +1,8 @@
|
|
| 1 |
import gradio as gr
|
| 2 |
-
import pandas as pd
|
| 3 |
-
import numpy as np
|
| 4 |
import requests
|
| 5 |
import re
|
| 6 |
import json
|
|
|
|
| 7 |
import io
|
| 8 |
from urllib.parse import urlparse, urljoin
|
| 9 |
import time
|
|
@@ -216,9 +215,6 @@ CONTACTS_DB = [
|
|
| 216 |
def extract_domain(url):
|
| 217 |
"""Extract domain from URL"""
|
| 218 |
try:
|
| 219 |
-
if not url or pd.isna(url):
|
| 220 |
-
return ""
|
| 221 |
-
url = str(url).strip()
|
| 222 |
if not url.startswith(('http://', 'https://')):
|
| 223 |
url = 'https://' + url
|
| 224 |
parsed = urlparse(url)
|
|
@@ -236,189 +232,188 @@ def find_contacts_by_website(website_url):
|
|
| 236 |
if not target_domain:
|
| 237 |
return []
|
| 238 |
|
|
|
|
|
|
|
| 239 |
matching_contacts = []
|
| 240 |
for contact in CONTACTS_DB:
|
| 241 |
contact_domain = extract_domain(contact['website'])
|
|
|
|
| 242 |
|
| 243 |
# Exact domain match or subdomain match
|
| 244 |
if target_domain == contact_domain or target_domain in contact_domain or contact_domain in target_domain:
|
| 245 |
matching_contacts.append(contact)
|
| 246 |
|
|
|
|
| 247 |
return matching_contacts
|
| 248 |
|
| 249 |
def simulate_website_scraping(url):
|
| 250 |
"""Simulate scraping a website and finding contact information"""
|
| 251 |
# Add some delay to simulate real scraping
|
| 252 |
-
time.sleep(random.uniform(0.
|
| 253 |
|
| 254 |
# Find matching contacts from our database
|
| 255 |
contacts = find_contacts_by_website(url)
|
| 256 |
|
| 257 |
return contacts
|
| 258 |
|
| 259 |
-
def
|
| 260 |
-
"""
|
| 261 |
-
|
| 262 |
-
return "Please upload an Excel file", None
|
| 263 |
-
|
| 264 |
try:
|
| 265 |
-
#
|
| 266 |
-
|
| 267 |
|
| 268 |
-
#
|
| 269 |
-
|
| 270 |
-
return "Excel file must have at least 8 columns (up to column H for websites)", None
|
| 271 |
|
| 272 |
-
#
|
| 273 |
-
|
| 274 |
-
current_columns = df.shape[1]
|
| 275 |
|
| 276 |
-
#
|
| 277 |
-
if
|
| 278 |
-
|
| 279 |
-
df[f'Column_{chr(65+i)}'] = ''
|
| 280 |
|
| 281 |
-
#
|
| 282 |
-
|
| 283 |
-
|
| 284 |
-
|
| 285 |
-
|
| 286 |
-
|
| 287 |
-
|
| 288 |
|
| 289 |
-
|
| 290 |
-
|
| 291 |
-
|
| 292 |
-
job_title_2_col = 20 # Column U
|
| 293 |
-
phone_2_col = 21 # Column V
|
| 294 |
-
email_2_col = 22 # Column W
|
| 295 |
|
| 296 |
-
|
| 297 |
-
|
| 298 |
-
|
| 299 |
-
# Process each row
|
| 300 |
-
for index, row in df.iterrows():
|
| 301 |
-
website_url = row.iloc[website_col] if pd.notna(row.iloc[website_col]) else ""
|
| 302 |
-
|
| 303 |
if website_url:
|
| 304 |
-
|
| 305 |
-
print(f"Processing row {index + 1}: {website_url}")
|
| 306 |
-
|
| 307 |
-
# Find contacts for this website
|
| 308 |
-
contacts = simulate_website_scraping(website_url)
|
| 309 |
-
|
| 310 |
-
if contacts:
|
| 311 |
-
contacts_found += len(contacts)
|
| 312 |
-
|
| 313 |
-
# Fill in first contact
|
| 314 |
-
if len(contacts) >= 1:
|
| 315 |
-
contact1 = contacts[0]
|
| 316 |
-
df.iloc[index, first_name_col] = contact1['first_name']
|
| 317 |
-
df.iloc[index, last_name_col] = contact1['last_name']
|
| 318 |
-
df.iloc[index, job_title_col] = contact1['job_title']
|
| 319 |
-
df.iloc[index, phone_col] = contact1['phone']
|
| 320 |
-
df.iloc[index, email_col] = contact1['email']
|
| 321 |
-
|
| 322 |
-
# Fill in second contact if available
|
| 323 |
-
if len(contacts) >= 2:
|
| 324 |
-
contact2 = contacts[1]
|
| 325 |
-
df.iloc[index, first_name_2_col] = contact2['first_name']
|
| 326 |
-
df.iloc[index, last_name_2_col] = contact2['last_name']
|
| 327 |
-
df.iloc[index, job_title_2_col] = contact2['job_title']
|
| 328 |
-
df.iloc[index, phone_2_col] = contact2['phone']
|
| 329 |
-
df.iloc[index, email_2_col] = contact2['email']
|
| 330 |
|
| 331 |
-
#
|
| 332 |
-
|
| 333 |
-
|
| 334 |
-
|
| 335 |
-
|
| 336 |
-
|
| 337 |
-
- Rows with websites: {total_processed}
|
| 338 |
-
- Total contacts found: {contacts_found}
|
| 339 |
-
- 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] != '')}
|
| 340 |
-
|
| 341 |
-
Column Mapping:
|
| 342 |
-
- Column H: Website URLs (source)
|
| 343 |
-
- Column I: Contact First Name
|
| 344 |
-
- Column J: Contact Last Name
|
| 345 |
-
- Column K: Job Title
|
| 346 |
-
- Column L: Phone Number
|
| 347 |
-
- Column M: Email Address
|
| 348 |
-
- Column S: Second Contact First Name
|
| 349 |
-
- Column T: Second Contact Last Name
|
| 350 |
-
- Column U: Second Contact Job Title
|
| 351 |
-
- Column V: Second Contact Phone
|
| 352 |
-
- Column W: Second Contact Email
|
| 353 |
|
| 354 |
-
|
| 355 |
-
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 356 |
|
| 357 |
-
|
| 358 |
-
|
| 359 |
-
|
| 360 |
-
|
| 361 |
-
|
| 362 |
-
|
| 363 |
-
|
| 364 |
-
|
| 365 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 366 |
|
| 367 |
-
#
|
| 368 |
-
|
| 369 |
-
|
| 370 |
-
|
|
|
|
|
|
|
|
|
|
| 371 |
|
| 372 |
-
|
|
|
|
| 373 |
|
| 374 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 375 |
|
| 376 |
except Exception as e:
|
| 377 |
-
return f"Error processing
|
| 378 |
|
| 379 |
-
def
|
| 380 |
-
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 381 |
try:
|
| 382 |
-
#
|
| 383 |
-
|
| 384 |
-
'A': ['Company 1', 'Company 2', 'Company 3', 'Company 4', 'Company 5'],
|
| 385 |
-
'B': ['Industry 1', 'Industry 2', 'Industry 3', 'Industry 4', 'Industry 5'],
|
| 386 |
-
'C': ['City 1', 'City 2', 'City 3', 'City 4', 'City 5'],
|
| 387 |
-
'D': ['State 1', 'State 2', 'State 3', 'State 4', 'State 5'],
|
| 388 |
-
'E': ['Country 1', 'Country 2', 'Country 3', 'Country 4', 'Country 5'],
|
| 389 |
-
'F': ['Notes 1', 'Notes 2', 'Notes 3', 'Notes 4', 'Notes 5'],
|
| 390 |
-
'G': ['Status 1', 'Status 2', 'Status 3', 'Status 4', 'Status 5'],
|
| 391 |
-
'H': ['techflowsolutions.com', 'greenleafconsult.com', 'blueskymarketing.net', 'quantumdynamics.org', 'stellarlogistics.biz'],
|
| 392 |
-
'I': ['', '', '', '', ''], # Contact First Name
|
| 393 |
-
'J': ['', '', '', '', ''], # Contact Last Name
|
| 394 |
-
'K': ['', '', '', '', ''], # Job Title
|
| 395 |
-
'L': ['', '', '', '', ''], # Phone
|
| 396 |
-
'M': ['', '', '', '', ''], # Email
|
| 397 |
-
'N': ['', '', '', '', ''],
|
| 398 |
-
'O': ['', '', '', '', ''],
|
| 399 |
-
'P': ['', '', '', '', ''],
|
| 400 |
-
'Q': ['', '', '', '', ''],
|
| 401 |
-
'R': ['', '', '', '', ''],
|
| 402 |
-
'S': ['', '', '', '', ''], # Second Contact First Name
|
| 403 |
-
'T': ['', '', '', '', ''], # Second Contact Last Name
|
| 404 |
-
'U': ['', '', '', '', ''], # Second Contact Job Title
|
| 405 |
-
'V': ['', '', '', '', ''], # Second Contact Phone
|
| 406 |
-
'W': ['', '', '', '', ''], # Second Contact Email
|
| 407 |
-
}
|
| 408 |
|
| 409 |
-
|
|
|
|
| 410 |
|
| 411 |
-
#
|
| 412 |
-
|
| 413 |
-
with pd.ExcelWriter(output_buffer, engine='openpyxl') as writer:
|
| 414 |
-
df.to_excel(writer, index=False, sheet_name='Sample_Template')
|
| 415 |
|
| 416 |
-
|
| 417 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 418 |
|
| 419 |
except Exception as e:
|
| 420 |
-
|
| 421 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 422 |
|
| 423 |
# Custom CSS
|
| 424 |
custom_css = """
|
|
@@ -450,22 +445,28 @@ custom_css = """
|
|
| 450 |
opacity: 0.9;
|
| 451 |
}
|
| 452 |
|
| 453 |
-
.
|
| 454 |
-
background:
|
| 455 |
-
|
| 456 |
-
|
| 457 |
-
|
| 458 |
-
margin:
|
| 459 |
-
|
|
|
|
| 460 |
}
|
| 461 |
|
| 462 |
-
.
|
| 463 |
background: linear-gradient(135deg, #f1f5f9 0%, #e2e8f0 100%);
|
| 464 |
border: 2px solid #cbd5e1;
|
| 465 |
border-radius: 15px;
|
| 466 |
padding: 20px;
|
| 467 |
margin: 10px 0;
|
| 468 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 469 |
}
|
| 470 |
|
| 471 |
.primary-btn {
|
|
@@ -479,6 +480,41 @@ custom_css = """
|
|
| 479 |
transition: all 0.3s ease;
|
| 480 |
}
|
| 481 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 482 |
.results-container {
|
| 483 |
background: white;
|
| 484 |
border: 1px solid #e5e7eb;
|
|
@@ -487,151 +523,204 @@ custom_css = """
|
|
| 487 |
margin: 15px 0;
|
| 488 |
box-shadow: 0 2px 10px rgba(0,0,0,0.05);
|
| 489 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 490 |
"""
|
| 491 |
|
| 492 |
# Create Gradio interface
|
| 493 |
-
with gr.Blocks(css=custom_css, title="
|
| 494 |
gr.HTML("""
|
| 495 |
<div class="main-header">
|
| 496 |
-
<h1>
|
| 497 |
-
<p>
|
| 498 |
-
<p style="font-size: 0.95em; opacity: 0.8;">
|
| 499 |
</div>
|
| 500 |
""")
|
| 501 |
|
| 502 |
-
with gr.
|
| 503 |
-
|
| 504 |
-
|
| 505 |
-
|
| 506 |
-
|
| 507 |
-
|
| 508 |
-
|
| 509 |
-
|
| 510 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 511 |
)
|
| 512 |
|
| 513 |
-
|
| 514 |
-
"
|
| 515 |
-
|
| 516 |
-
|
| 517 |
-
|
|
|
|
| 518 |
)
|
| 519 |
|
| 520 |
-
|
| 521 |
-
|
| 522 |
-
|
| 523 |
-
|
| 524 |
-
|
| 525 |
-
|
| 526 |
-
|
| 527 |
-
|
| 528 |
-
|
| 529 |
-
|
| 530 |
-
|
| 531 |
-
|
| 532 |
-
|
| 533 |
-
|
| 534 |
-
|
| 535 |
-
|
| 536 |
-
|
| 537 |
-
|
| 538 |
-
|
| 539 |
-
|
| 540 |
-
|
| 541 |
-
|
| 542 |
-
|
| 543 |
-
|
| 544 |
-
|
| 545 |
-
|
| 546 |
-
|
| 547 |
-
|
| 548 |
-
|
| 549 |
-
|
| 550 |
-
|
| 551 |
-
|
| 552 |
-
|
| 553 |
-
|
| 554 |
-
|
| 555 |
-
|
| 556 |
-
|
| 557 |
-
|
| 558 |
-
|
| 559 |
-
|
| 560 |
-
|
| 561 |
-
|
| 562 |
-
|
| 563 |
-
|
| 564 |
-
|
| 565 |
-
|
| 566 |
-
|
| 567 |
-
|
| 568 |
-
|
| 569 |
-
|
| 570 |
-
|
| 571 |
-
|
| 572 |
-
|
| 573 |
-
|
| 574 |
-
|
| 575 |
-
|
| 576 |
-
|
| 577 |
-
sample_download_btn = gr.Button(
|
| 578 |
-
"Download Sample Template",
|
| 579 |
-
variant="secondary",
|
| 580 |
-
size="lg"
|
| 581 |
-
)
|
| 582 |
-
|
| 583 |
-
sample_file = gr.File(
|
| 584 |
-
label="Sample Template Download",
|
| 585 |
-
elem_classes=["results-container"]
|
| 586 |
-
)
|
| 587 |
|
| 588 |
-
|
| 589 |
-
|
| 590 |
-
|
| 591 |
-
|
| 592 |
-
|
| 593 |
-
|
| 594 |
-
|
| 595 |
-
blueskymarketing.net - BlueSky Marketing
|
| 596 |
-
quantumdynamics.org - Quantum Dynamics Corp
|
| 597 |
-
stellarlogistics.biz - Stellar Logistics
|
| 598 |
-
nexusfinancial.pro - Nexus Financial
|
| 599 |
-
horizonhealth.care - Horizon Health Systems
|
| 600 |
-
phoenixmfg.com - Phoenix Manufacturing
|
| 601 |
-
alpineeducation.edu - Alpine Education Group
|
| 602 |
-
crimsoncreative.studio - Crimson Creative Studio
|
| 603 |
-
|
| 604 |
-
You can use these websites in column H of your Excel file to test the system."""
|
| 605 |
-
|
| 606 |
-
gr.Textbox(
|
| 607 |
-
value=sample_websites_text,
|
| 608 |
-
label="Sample Websites for Testing",
|
| 609 |
-
lines=15,
|
| 610 |
interactive=False,
|
| 611 |
-
elem_classes=["
|
| 612 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 613 |
|
| 614 |
# Event handlers
|
| 615 |
-
|
| 616 |
-
fn=
|
| 617 |
-
inputs=[
|
| 618 |
-
outputs=[
|
| 619 |
)
|
| 620 |
|
| 621 |
-
|
| 622 |
-
fn=
|
| 623 |
-
inputs=[],
|
| 624 |
-
outputs=[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 625 |
)
|
| 626 |
|
| 627 |
# Footer
|
| 628 |
gr.HTML("""
|
| 629 |
<div style="text-align: center; padding: 30px 20px; background: linear-gradient(135deg, #64748b 0%, #475569 100%); color: white; border-radius: 15px; margin-top: 30px;">
|
| 630 |
-
<h3 style="margin: 0 0 10px 0;">
|
| 631 |
-
<p style="margin: 0; opacity: 0.9;">
|
| 632 |
-
<p style="margin: 10px 0 0 0; font-size: 0.9em; opacity: 0.7;">
|
| 633 |
</div>
|
| 634 |
""")
|
| 635 |
|
| 636 |
if __name__ == "__main__":
|
| 637 |
-
app.launch()
|
|
|
|
| 1 |
import gradio as gr
|
|
|
|
|
|
|
| 2 |
import requests
|
| 3 |
import re
|
| 4 |
import json
|
| 5 |
+
import csv
|
| 6 |
import io
|
| 7 |
from urllib.parse import urlparse, urljoin
|
| 8 |
import time
|
|
|
|
| 215 |
def extract_domain(url):
|
| 216 |
"""Extract domain from URL"""
|
| 217 |
try:
|
|
|
|
|
|
|
|
|
|
| 218 |
if not url.startswith(('http://', 'https://')):
|
| 219 |
url = 'https://' + url
|
| 220 |
parsed = urlparse(url)
|
|
|
|
| 232 |
if not target_domain:
|
| 233 |
return []
|
| 234 |
|
| 235 |
+
print(f"Searching for domain: {target_domain}") # Debug info
|
| 236 |
+
|
| 237 |
matching_contacts = []
|
| 238 |
for contact in CONTACTS_DB:
|
| 239 |
contact_domain = extract_domain(contact['website'])
|
| 240 |
+
print(f"Comparing with: {contact_domain}") # Debug info
|
| 241 |
|
| 242 |
# Exact domain match or subdomain match
|
| 243 |
if target_domain == contact_domain or target_domain in contact_domain or contact_domain in target_domain:
|
| 244 |
matching_contacts.append(contact)
|
| 245 |
|
| 246 |
+
print(f"Found {len(matching_contacts)} matching contacts") # Debug info
|
| 247 |
return matching_contacts
|
| 248 |
|
| 249 |
def simulate_website_scraping(url):
|
| 250 |
"""Simulate scraping a website and finding contact information"""
|
| 251 |
# Add some delay to simulate real scraping
|
| 252 |
+
time.sleep(random.uniform(0.5, 1))
|
| 253 |
|
| 254 |
# Find matching contacts from our database
|
| 255 |
contacts = find_contacts_by_website(url)
|
| 256 |
|
| 257 |
return contacts
|
| 258 |
|
| 259 |
+
def parse_csv_file(file_content):
|
| 260 |
+
"""Parse CSV file and extract website URLs"""
|
| 261 |
+
websites = []
|
|
|
|
|
|
|
| 262 |
try:
|
| 263 |
+
# Decode file content
|
| 264 |
+
content = file_content.decode('utf-8')
|
| 265 |
|
| 266 |
+
# Parse CSV
|
| 267 |
+
csv_reader = csv.DictReader(io.StringIO(content))
|
|
|
|
| 268 |
|
| 269 |
+
# Look for common website column names (case-insensitive)
|
| 270 |
+
website_columns = ['website', 'url', 'domain', 'site', 'web', 'homepage']
|
|
|
|
| 271 |
|
| 272 |
+
# Get all column names and print for debugging
|
| 273 |
+
all_columns = list(csv_reader.fieldnames) if csv_reader.fieldnames else []
|
| 274 |
+
print(f"CSV columns found: {all_columns}")
|
|
|
|
| 275 |
|
| 276 |
+
# Find the website column (case-insensitive)
|
| 277 |
+
website_column = None
|
| 278 |
+
for col_name in all_columns:
|
| 279 |
+
if col_name and col_name.lower().strip() in website_columns:
|
| 280 |
+
website_column = col_name
|
| 281 |
+
print(f"Using website column: '{website_column}'")
|
| 282 |
+
break
|
| 283 |
|
| 284 |
+
if not website_column:
|
| 285 |
+
print(f"No website column found. Available columns: {all_columns}")
|
| 286 |
+
return []
|
|
|
|
|
|
|
|
|
|
| 287 |
|
| 288 |
+
# Extract websites
|
| 289 |
+
for row in csv_reader:
|
| 290 |
+
website_url = row.get(website_column, '').strip()
|
|
|
|
|
|
|
|
|
|
|
|
|
| 291 |
if website_url:
|
| 292 |
+
websites.append(website_url)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 293 |
|
| 294 |
+
print(f"Extracted {len(websites)} websites: {websites[:5]}...") # Show first 5
|
| 295 |
+
return websites
|
| 296 |
+
|
| 297 |
+
except Exception as e:
|
| 298 |
+
print(f"Error parsing CSV: {e}")
|
| 299 |
+
return []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 300 |
|
| 301 |
+
def search_csv_websites(csv_file, max_results=10):
|
| 302 |
+
"""Search for contacts from websites listed in CSV file"""
|
| 303 |
+
if csv_file is None:
|
| 304 |
+
return "Please upload a CSV file", ""
|
| 305 |
+
|
| 306 |
+
try:
|
| 307 |
+
# Parse CSV file
|
| 308 |
+
websites = parse_csv_file(csv_file)
|
| 309 |
|
| 310 |
+
if not websites:
|
| 311 |
+
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.", ""
|
| 312 |
+
|
| 313 |
+
all_contacts = []
|
| 314 |
+
processed_websites = []
|
| 315 |
+
|
| 316 |
+
# Search each website
|
| 317 |
+
for website in websites[:20]: # Limit to first 20 websites
|
| 318 |
+
print(f"Processing website: {website}")
|
| 319 |
+
contacts = simulate_website_scraping(website)
|
| 320 |
+
if contacts:
|
| 321 |
+
all_contacts.extend(contacts)
|
| 322 |
+
processed_websites.append(website)
|
| 323 |
+
print(f"Found {len(contacts)} contacts for {website}")
|
| 324 |
+
else:
|
| 325 |
+
print(f"No contacts found for {website}")
|
| 326 |
|
| 327 |
+
# Remove duplicates based on email
|
| 328 |
+
unique_contacts = []
|
| 329 |
+
seen_emails = set()
|
| 330 |
+
for contact in all_contacts:
|
| 331 |
+
if contact['email'] not in seen_emails:
|
| 332 |
+
unique_contacts.append(contact)
|
| 333 |
+
seen_emails.add(contact['email'])
|
| 334 |
|
| 335 |
+
# Limit results
|
| 336 |
+
unique_contacts = unique_contacts[:max_results]
|
| 337 |
|
| 338 |
+
if not unique_contacts:
|
| 339 |
+
return f"No contacts found for the {len(websites)} websites in the CSV file. Processed websites: {', '.join(websites[:10])}", ""
|
| 340 |
+
|
| 341 |
+
# Format results
|
| 342 |
+
results_text = f"CONTACT DISCOVERY REPORT\n"
|
| 343 |
+
results_text += f"Websites Processed: {len(processed_websites)}\n"
|
| 344 |
+
results_text += f"Total Websites in CSV: {len(websites)}\n"
|
| 345 |
+
results_text += f"Websites with Contacts: {len(processed_websites)}\n"
|
| 346 |
+
results_text += f"Unique Contacts Found: {len(unique_contacts)}\n"
|
| 347 |
+
results_text += f"Processed Websites: {', '.join(processed_websites)}\n"
|
| 348 |
+
results_text += f"{'='*60}\n\n"
|
| 349 |
+
|
| 350 |
+
for i, contact in enumerate(unique_contacts, 1):
|
| 351 |
+
results_text += f"CONTACT #{i}\n"
|
| 352 |
+
results_text += f"Name: {contact['first_name']} {contact['last_name']}\n"
|
| 353 |
+
results_text += f"Position: {contact['job_title']}\n"
|
| 354 |
+
results_text += f"Email: {contact['email']}\n"
|
| 355 |
+
results_text += f"Phone: {contact['phone']}\n"
|
| 356 |
+
results_text += f"Company: {contact['company']}\n"
|
| 357 |
+
results_text += f"Website: {contact['website']}\n\n"
|
| 358 |
+
|
| 359 |
+
# Create CSV output
|
| 360 |
+
csv_output = "First Name,Last Name,Job Title,Email,Phone,Company,Website\n"
|
| 361 |
+
for contact in unique_contacts:
|
| 362 |
+
csv_output += f"{contact['first_name']},{contact['last_name']},{contact['job_title']},{contact['email']},{contact['phone']},{contact['company']},{contact['website']}\n"
|
| 363 |
+
|
| 364 |
+
return results_text, csv_output
|
| 365 |
|
| 366 |
except Exception as e:
|
| 367 |
+
return f"Error processing CSV file: {str(e)}", ""
|
| 368 |
|
| 369 |
+
def search_website_contacts(website_url, max_results=10):
|
| 370 |
+
"""Main function to search for contacts on a website"""
|
| 371 |
+
if not website_url:
|
| 372 |
+
return "Please enter a website URL", ""
|
| 373 |
+
|
| 374 |
+
# Clean up URL
|
| 375 |
+
if not website_url.startswith(('http://', 'https://')):
|
| 376 |
+
website_url = 'https://' + website_url
|
| 377 |
+
|
| 378 |
try:
|
| 379 |
+
# Simulate finding contacts
|
| 380 |
+
contacts = simulate_website_scraping(website_url)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 381 |
|
| 382 |
+
if not contacts:
|
| 383 |
+
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.", ""
|
| 384 |
|
| 385 |
+
# Limit results
|
| 386 |
+
contacts = contacts[:max_results]
|
|
|
|
|
|
|
| 387 |
|
| 388 |
+
# Format results
|
| 389 |
+
results_text = f"CONTACT INTELLIGENCE REPORT\n"
|
| 390 |
+
results_text += f"Website: {website_url}\n"
|
| 391 |
+
results_text += f"Contacts Found: {len(contacts)}\n"
|
| 392 |
+
results_text += f"{'='*60}\n\n"
|
| 393 |
+
|
| 394 |
+
for i, contact in enumerate(contacts, 1):
|
| 395 |
+
results_text += f"CONTACT #{i}\n"
|
| 396 |
+
results_text += f"First Name: {contact['first_name']}\n"
|
| 397 |
+
results_text += f"Last Name: {contact['last_name']}\n"
|
| 398 |
+
results_text += f"Position: {contact['job_title']}\n"
|
| 399 |
+
results_text += f"Email: {contact['email']}\n"
|
| 400 |
+
results_text += f"Phone: {contact['phone']}\n"
|
| 401 |
+
results_text += f"Company: {contact['company']}\n\n"
|
| 402 |
+
|
| 403 |
+
# Create a simple table format for the second output
|
| 404 |
+
table_text = "First Name,Last Name,Job Title,Email,Phone,Company\n"
|
| 405 |
+
for contact in contacts:
|
| 406 |
+
table_text += f"{contact['first_name']},{contact['last_name']},{contact['job_title']},{contact['email']},{contact['phone']},{contact['company']}\n"
|
| 407 |
+
|
| 408 |
+
return results_text, table_text
|
| 409 |
|
| 410 |
except Exception as e:
|
| 411 |
+
return f"Error searching website: {str(e)}", ""
|
| 412 |
+
|
| 413 |
+
def get_all_available_websites():
|
| 414 |
+
"""Get list of all available websites from the database"""
|
| 415 |
+
websites = list(set([contact['website'] for contact in CONTACTS_DB]))
|
| 416 |
+
return "\n".join(sorted(websites))
|
| 417 |
|
| 418 |
# Custom CSS
|
| 419 |
custom_css = """
|
|
|
|
| 445 |
opacity: 0.9;
|
| 446 |
}
|
| 447 |
|
| 448 |
+
.corporate-card {
|
| 449 |
+
background: white;
|
| 450 |
+
border: 1px solid #d1d5db;
|
| 451 |
+
border-radius: 12px;
|
| 452 |
+
padding: 25px;
|
| 453 |
+
margin: 15px 0;
|
| 454 |
+
box-shadow: 0 4px 15px rgba(0,0,0,0.1);
|
| 455 |
+
border-left: 5px solid #1e40af;
|
| 456 |
}
|
| 457 |
|
| 458 |
+
.tips-section {
|
| 459 |
background: linear-gradient(135deg, #f1f5f9 0%, #e2e8f0 100%);
|
| 460 |
border: 2px solid #cbd5e1;
|
| 461 |
border-radius: 15px;
|
| 462 |
padding: 20px;
|
| 463 |
margin: 10px 0;
|
| 464 |
+
}
|
| 465 |
+
|
| 466 |
+
.tips-section h3 {
|
| 467 |
+
color: #1e40af;
|
| 468 |
+
margin-top: 0;
|
| 469 |
+
font-weight: 600;
|
| 470 |
}
|
| 471 |
|
| 472 |
.primary-btn {
|
|
|
|
| 480 |
transition: all 0.3s ease;
|
| 481 |
}
|
| 482 |
|
| 483 |
+
.primary-btn:hover {
|
| 484 |
+
background: linear-gradient(135deg, #1e3a8a 0%, #2563eb 100%);
|
| 485 |
+
transform: translateY(-2px);
|
| 486 |
+
box-shadow: 0 6px 20px rgba(30, 64, 175, 0.4);
|
| 487 |
+
}
|
| 488 |
+
|
| 489 |
+
.secondary-btn {
|
| 490 |
+
background: white;
|
| 491 |
+
color: #374151;
|
| 492 |
+
border: 2px solid #d1d5db;
|
| 493 |
+
border-radius: 6px;
|
| 494 |
+
padding: 8px 16px;
|
| 495 |
+
font-weight: 500;
|
| 496 |
+
transition: all 0.3s ease;
|
| 497 |
+
}
|
| 498 |
+
|
| 499 |
+
.secondary-btn:hover {
|
| 500 |
+
border-color: #1e40af;
|
| 501 |
+
color: #1e40af;
|
| 502 |
+
background: #f8fafc;
|
| 503 |
+
}
|
| 504 |
+
|
| 505 |
+
.custom-input {
|
| 506 |
+
border: 2px solid #d1d5db;
|
| 507 |
+
border-radius: 8px;
|
| 508 |
+
padding: 12px;
|
| 509 |
+
font-size: 16px;
|
| 510 |
+
transition: border-color 0.3s ease;
|
| 511 |
+
}
|
| 512 |
+
|
| 513 |
+
.custom-input:focus {
|
| 514 |
+
border-color: #3b82f6;
|
| 515 |
+
box-shadow: 0 0 0 3px rgba(59, 130, 246, 0.1);
|
| 516 |
+
}
|
| 517 |
+
|
| 518 |
.results-container {
|
| 519 |
background: white;
|
| 520 |
border: 1px solid #e5e7eb;
|
|
|
|
| 523 |
margin: 15px 0;
|
| 524 |
box-shadow: 0 2px 10px rgba(0,0,0,0.05);
|
| 525 |
}
|
| 526 |
+
|
| 527 |
+
.section-header {
|
| 528 |
+
background: linear-gradient(135deg, #64748b 0%, #475569 100%);
|
| 529 |
+
color: white;
|
| 530 |
+
padding: 15px 20px;
|
| 531 |
+
border-radius: 10px;
|
| 532 |
+
margin: 20px 0 15px 0;
|
| 533 |
+
font-weight: 600;
|
| 534 |
+
}
|
| 535 |
"""
|
| 536 |
|
| 537 |
# Create Gradio interface
|
| 538 |
+
with gr.Blocks(css=custom_css, title="Contact Discovery Platform", theme=gr.themes.Base()) as app:
|
| 539 |
gr.HTML("""
|
| 540 |
<div class="main-header">
|
| 541 |
+
<h1>Contact Discovery Platform</h1>
|
| 542 |
+
<p>Professional Contact Discovery & Lead Generation Tool</p>
|
| 543 |
+
<p style="font-size: 0.95em; opacity: 0.8;">Advanced website analysis for contact intelligence gathering</p>
|
| 544 |
</div>
|
| 545 |
""")
|
| 546 |
|
| 547 |
+
with gr.Tabs():
|
| 548 |
+
# Single Website Search Tab
|
| 549 |
+
with gr.TabItem("Single Website Search"):
|
| 550 |
+
with gr.Row():
|
| 551 |
+
with gr.Column(scale=2):
|
| 552 |
+
gr.HTML('<div class="section-header">Search Parameters</div>')
|
| 553 |
+
|
| 554 |
+
website_input = gr.Textbox(
|
| 555 |
+
label="Target Website URL",
|
| 556 |
+
placeholder="Enter company website (e.g., techflowsolutions.com)",
|
| 557 |
+
value="",
|
| 558 |
+
elem_classes=["custom-input"]
|
| 559 |
+
)
|
| 560 |
+
|
| 561 |
+
with gr.Row():
|
| 562 |
+
max_results = gr.Slider(
|
| 563 |
+
minimum=1,
|
| 564 |
+
maximum=20,
|
| 565 |
+
value=8,
|
| 566 |
+
step=1,
|
| 567 |
+
label="Maximum Results",
|
| 568 |
+
elem_classes=["custom-input"]
|
| 569 |
+
)
|
| 570 |
+
|
| 571 |
+
search_btn = gr.Button(
|
| 572 |
+
"Execute Search",
|
| 573 |
+
variant="primary",
|
| 574 |
+
size="lg",
|
| 575 |
+
elem_classes=["primary-btn"]
|
| 576 |
+
)
|
| 577 |
+
|
| 578 |
+
gr.HTML('<div class="section-header">Search Results</div>')
|
| 579 |
+
|
| 580 |
+
with gr.Row():
|
| 581 |
+
results_display = gr.Textbox(
|
| 582 |
+
label="Contact Intelligence Report",
|
| 583 |
+
lines=18,
|
| 584 |
+
max_lines=35,
|
| 585 |
+
show_copy_button=True,
|
| 586 |
+
elem_classes=["results-container"]
|
| 587 |
)
|
| 588 |
|
| 589 |
+
csv_output = gr.Textbox(
|
| 590 |
+
label="Export Data (CSV Format)",
|
| 591 |
+
lines=18,
|
| 592 |
+
max_lines=35,
|
| 593 |
+
show_copy_button=True,
|
| 594 |
+
elem_classes=["results-container"]
|
| 595 |
)
|
| 596 |
|
| 597 |
+
# CSV Upload Tab
|
| 598 |
+
with gr.TabItem("CSV Bulk Search"):
|
| 599 |
+
with gr.Row():
|
| 600 |
+
with gr.Column(scale=2):
|
| 601 |
+
gr.HTML('<div class="section-header">CSV Upload</div>')
|
| 602 |
+
|
| 603 |
+
csv_file = gr.File(
|
| 604 |
+
label="Upload CSV File",
|
| 605 |
+
file_types=[".csv"],
|
| 606 |
+
elem_classes=["custom-input"]
|
| 607 |
+
)
|
| 608 |
+
|
| 609 |
+
gr.HTML("""
|
| 610 |
+
<div style="background: #f8fafc; padding: 15px; border-radius: 8px; border-left: 4px solid #1e40af; margin: 10px 0;">
|
| 611 |
+
<strong>CSV Format Requirements:</strong><br>
|
| 612 |
+
• Include a column named 'website', 'url', or 'domain'<br>
|
| 613 |
+
• One website per row<br>
|
| 614 |
+
• Example: techflowsolutions.com, greenleafconsult.com
|
| 615 |
+
</div>
|
| 616 |
+
""")
|
| 617 |
+
|
| 618 |
+
with gr.Row():
|
| 619 |
+
csv_max_results = gr.Slider(
|
| 620 |
+
minimum=1,
|
| 621 |
+
maximum=50,
|
| 622 |
+
value=20,
|
| 623 |
+
step=1,
|
| 624 |
+
label="Maximum Results",
|
| 625 |
+
elem_classes=["custom-input"]
|
| 626 |
+
)
|
| 627 |
+
|
| 628 |
+
csv_search_btn = gr.Button(
|
| 629 |
+
"Process CSV",
|
| 630 |
+
variant="primary",
|
| 631 |
+
size="lg",
|
| 632 |
+
elem_classes=["primary-btn"]
|
| 633 |
+
)
|
| 634 |
+
|
| 635 |
+
gr.HTML('<div class="section-header">CSV Results</div>')
|
| 636 |
+
|
| 637 |
+
with gr.Row():
|
| 638 |
+
csv_results_display = gr.Textbox(
|
| 639 |
+
label="CSV Processing Report",
|
| 640 |
+
lines=18,
|
| 641 |
+
max_lines=35,
|
| 642 |
+
show_copy_button=True,
|
| 643 |
+
elem_classes=["results-container"]
|
| 644 |
+
)
|
| 645 |
+
|
| 646 |
+
csv_export_output = gr.Textbox(
|
| 647 |
+
label="Export Data (CSV Format)",
|
| 648 |
+
lines=18,
|
| 649 |
+
max_lines=35,
|
| 650 |
+
show_copy_button=True,
|
| 651 |
+
elem_classes=["results-container"]
|
| 652 |
+
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 653 |
|
| 654 |
+
# Sample websites section
|
| 655 |
+
with gr.Accordion("Sample Websites Database", open=False):
|
| 656 |
+
gr.HTML('<div style="background: #f8fafc; padding: 15px; border-radius: 8px; border-left: 4px solid #1e40af;">')
|
| 657 |
+
sample_websites = gr.Textbox(
|
| 658 |
+
label="Available Websites in Database",
|
| 659 |
+
value=get_all_available_websites(),
|
| 660 |
+
lines=8,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 661 |
interactive=False,
|
| 662 |
+
elem_classes=["custom-input"]
|
| 663 |
)
|
| 664 |
+
gr.HTML('</div>')
|
| 665 |
+
|
| 666 |
+
# Quick search buttons
|
| 667 |
+
gr.HTML('<div class="section-header">Quick Access Sample Websites</div>')
|
| 668 |
+
|
| 669 |
+
with gr.Row():
|
| 670 |
+
quick_btn1 = gr.Button("TechFlow Solutions", size="sm", elem_classes=["secondary-btn"])
|
| 671 |
+
quick_btn2 = gr.Button("GreenLeaf Consulting", size="sm", elem_classes=["secondary-btn"])
|
| 672 |
+
quick_btn3 = gr.Button("BlueSky Marketing", size="sm", elem_classes=["secondary-btn"])
|
| 673 |
+
quick_btn4 = gr.Button("Quantum Dynamics", size="sm", elem_classes=["secondary-btn"])
|
| 674 |
+
|
| 675 |
+
with gr.Row():
|
| 676 |
+
quick_btn5 = gr.Button("Stellar Logistics", size="sm", elem_classes=["secondary-btn"])
|
| 677 |
+
quick_btn6 = gr.Button("Nexus Financial", size="sm", elem_classes=["secondary-btn"])
|
| 678 |
+
quick_btn7 = gr.Button("Horizon Health", size="sm", elem_classes=["secondary-btn"])
|
| 679 |
+
quick_btn8 = gr.Button("Phoenix Manufacturing", size="sm", elem_classes=["secondary-btn"])
|
| 680 |
|
| 681 |
# Event handlers
|
| 682 |
+
search_btn.click(
|
| 683 |
+
fn=search_website_contacts,
|
| 684 |
+
inputs=[website_input, max_results],
|
| 685 |
+
outputs=[results_display, csv_output]
|
| 686 |
)
|
| 687 |
|
| 688 |
+
csv_search_btn.click(
|
| 689 |
+
fn=search_csv_websites,
|
| 690 |
+
inputs=[csv_file, csv_max_results],
|
| 691 |
+
outputs=[csv_results_display, csv_export_output]
|
| 692 |
+
)
|
| 693 |
+
|
| 694 |
+
# Quick search button handlers
|
| 695 |
+
quick_btn1.click(lambda: "techflowsolutions.com", outputs=website_input)
|
| 696 |
+
quick_btn2.click(lambda: "greenleafconsult.com", outputs=website_input)
|
| 697 |
+
quick_btn3.click(lambda: "blueskymarketing.net", outputs=website_input)
|
| 698 |
+
quick_btn4.click(lambda: "quantumdynamics.org", outputs=website_input)
|
| 699 |
+
quick_btn5.click(lambda: "stellarlogistics.biz", outputs=website_input)
|
| 700 |
+
quick_btn6.click(lambda: "nexusfinancial.pro", outputs=website_input)
|
| 701 |
+
quick_btn7.click(lambda: "horizonhealth.care", outputs=website_input)
|
| 702 |
+
quick_btn8.click(lambda: "phoenixmfg.com", outputs=website_input)
|
| 703 |
+
|
| 704 |
+
# Examples
|
| 705 |
+
gr.Examples(
|
| 706 |
+
examples=[
|
| 707 |
+
["techflowsolutions.com", 5],
|
| 708 |
+
["greenleafconsult.com", 3],
|
| 709 |
+
["blueskymarketing.net", 4],
|
| 710 |
+
["quantumdynamics.org", 6]
|
| 711 |
+
],
|
| 712 |
+
inputs=[website_input, max_results],
|
| 713 |
+
label="Sample Searches"
|
| 714 |
)
|
| 715 |
|
| 716 |
# Footer
|
| 717 |
gr.HTML("""
|
| 718 |
<div style="text-align: center; padding: 30px 20px; background: linear-gradient(135deg, #64748b 0%, #475569 100%); color: white; border-radius: 15px; margin-top: 30px;">
|
| 719 |
+
<h3 style="margin: 0 0 10px 0;">Contact Intelligence Platform</h3>
|
| 720 |
+
<p style="margin: 0; opacity: 0.9;">Professional-grade contact discovery and lead generation technology</p>
|
| 721 |
+
<p style="margin: 10px 0 0 0; font-size: 0.9em; opacity: 0.7;">Powered by advanced web intelligence algorithms</p>
|
| 722 |
</div>
|
| 723 |
""")
|
| 724 |
|
| 725 |
if __name__ == "__main__":
|
| 726 |
+
app.launch()
|