Update utility/utils.py
Browse files- utility/utils.py +135 -34
utility/utils.py
CHANGED
|
@@ -328,42 +328,143 @@ def extract_text_from_images(image_paths):
|
|
| 328 |
|
| 329 |
|
| 330 |
def extract_contact_details(text):
|
| 331 |
-
#
|
| 332 |
-
#
|
| 333 |
combined_phone_regex = re.compile(r'''
|
| 334 |
-
(?:
|
| 335 |
-
\+
|
| 336 |
-
\(\d{3}\)\s\d{3}-\d{4} |
|
| 337 |
-
\(\d{3}\)\s\d{3}\
|
| 338 |
-
\
|
| 339 |
-
\d{
|
| 340 |
-
\+
|
| 341 |
-
\
|
| 342 |
-
|
| 343 |
-
|
| 344 |
-
\
|
| 345 |
-
0\d{
|
| 346 |
-
\+
|
| 347 |
-
\
|
| 348 |
-
\+
|
| 349 |
-
\
|
| 350 |
-
\+
|
| 351 |
-
\
|
| 352 |
-
\+91\s\d{
|
| 353 |
-
\+91\s\d{
|
| 354 |
-
\
|
| 355 |
-
\d{
|
| 356 |
-
|
| 357 |
-
\+91\d{
|
| 358 |
-
\d{
|
| 359 |
-
\d{
|
| 360 |
-
\d{
|
| 361 |
-
\d{
|
| 362 |
-
\d{
|
| 363 |
-
\
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 364 |
\+\d{3}-\d{3}-\d{4}
|
| 365 |
-
)
|
| 366 |
-
|
|
|
|
|
|
|
| 367 |
|
| 368 |
email_regex = re.compile(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b')
|
| 369 |
link_regex = re.compile(r'\b(?:https?:\/\/)?(?:www\.)[a-zA-Z0-9-]+\.(?:com|co\.in|co|io|org|net|edu|gov|mil|int|uk|us|in|de|au|app|tech|xyz|info|biz|fr|dev)\b')
|
|
|
|
| 328 |
|
| 329 |
|
| 330 |
def extract_contact_details(text):
|
| 331 |
+
# Regex patterns
|
| 332 |
+
# Phone numbers with at least 5 digits in any segment
|
| 333 |
combined_phone_regex = re.compile(r'''
|
| 334 |
+
(?:
|
| 335 |
+
#(?:(?:\+91[-.\s]?)?\d{5}[-.\s]?\d{5})|(?:\+?\d{1,3})?[-.\s()]?\d{5,}[-.\s()]?\d{5,}[-.\s()]?\d{1,9} | /^[\.-)( ]*([0-9]{3})[\.-)( ]*([0-9]{3})[\.-)( ]*([0-9]{4})$/ |
|
| 336 |
+
\+1\s\(\d{3}\)\s\d{3}-\d{4} | # USA/Canada Intl +1 (XXX) XXX-XXXX
|
| 337 |
+
\(\d{3}\)\s\d{3}-\d{4} | # USA/Canada STD (XXX) XXX-XXXX
|
| 338 |
+
\(\d{3}\)\s\d{3}\s\d{4} | # USA/Canada (XXX) XXX XXXX
|
| 339 |
+
\(\d{3}\)\s\d{3}\s\d{3} | # USA/Canada (XXX) XXX XXX
|
| 340 |
+
\+1\d{10} | # +1 XXXXXXXXXX
|
| 341 |
+
\d{10} | # XXXXXXXXXX
|
| 342 |
+
\+44\s\d{4}\s\d{6} | # UK Intl +44 XXXX XXXXXX
|
| 343 |
+
\+44\s\d{3}\s\d{3}\s\d{4} | # UK Intl +44 XXX XXX XXXX
|
| 344 |
+
0\d{4}\s\d{6} | # UK STD 0XXXX XXXXXX
|
| 345 |
+
0\d{3}\s\d{3}\s\d{4} | # UK STD 0XXX XXX XXXX
|
| 346 |
+
\+44\d{10} | # +44 XXXXXXXXXX
|
| 347 |
+
0\d{10} | # 0XXXXXXXXXX
|
| 348 |
+
\+61\s\d\s\d{4}\s\d{4} | # Australia Intl +61 X XXXX XXXX
|
| 349 |
+
0\d\s\d{4}\s\d{4} | # Australia STD 0X XXXX XXXX
|
| 350 |
+
\+61\d{9} | # +61 XXXXXXXXX
|
| 351 |
+
0\d{9} | # 0XXXXXXXXX
|
| 352 |
+
\+91\s\d{5}-\d{5} | # India Intl +91 XXXXX-XXXXX
|
| 353 |
+
\+91\s\d{4}-\d{6} | # India Intl +91 XXXX-XXXXXX
|
| 354 |
+
\+91\s\d{10} | # India Intl +91 XXXXXXXXXX
|
| 355 |
+
\+91\s\d{3}\s\d{3}\s\d{4} | # India Intl +91 XXX XXX XXXX
|
| 356 |
+
\+91\s\d{3}-\d{3}-\d{4} | # India Intl +91 XXX-XXX-XXXX
|
| 357 |
+
\+91\s\d{2}\s\d{4}\s\d{4} | # India Intl +91 XX XXXX XXXX
|
| 358 |
+
\+91\s\d{2}-\d{4}-\d{4} | # India Intl +91 XX-XXXX-XXXX
|
| 359 |
+
\+91\s\d{5}\s\d{5} | # India Intl +91 XXXXX XXXXX
|
| 360 |
+
\d{5}\s\d{5} | # India XXXXX XXXXX
|
| 361 |
+
\d{5}-\d{5} | # India XXXXX-XXXXX
|
| 362 |
+
0\d{2}-\d{7} | # India STD 0XX-XXXXXXX
|
| 363 |
+
\+91\d{10} | # +91 XXXXXXXXXX
|
| 364 |
+
\d{10} | # XXXXXXXXXX # Here is the regex to handle all possible combination of the contact
|
| 365 |
+
\d{6}-\d{4} | # XXXXXX-XXXX
|
| 366 |
+
\d{4}-\d{6} | # XXXX-XXXXXX
|
| 367 |
+
\d{3}\s\d{3}\s\d{4} | # XXX XXX XXXX
|
| 368 |
+
\d{3}-\d{3}-\d{4} | # XXX-XXX-XXXX
|
| 369 |
+
\d{4}\s\d{3}\s\d{3} | # XXXX XXX XXX
|
| 370 |
+
\d{4}-\d{3}-\d{3} | # XXXX-XXX-XXX #-----
|
| 371 |
+
\+49\s\d{4}\s\d{8} | # Germany Intl +49 XXXX XXXXXXXX
|
| 372 |
+
\+49\s\d{3}\s\d{7} | # Germany Intl +49 XXX XXXXXXX
|
| 373 |
+
0\d{3}\s\d{8} | # Germany STD 0XXX XXXXXXXX
|
| 374 |
+
\+49\d{12} | # +49 XXXXXXXXXXXX
|
| 375 |
+
\+49\d{10} | # +49 XXXXXXXXXX
|
| 376 |
+
0\d{11} | # 0XXXXXXXXXXX
|
| 377 |
+
\+86\s\d{3}\s\d{4}\s\d{4} | # China Intl +86 XXX XXXX XXXX
|
| 378 |
+
0\d{3}\s\d{4}\s\d{4} | # China STD 0XXX XXXX XXXX
|
| 379 |
+
\+86\d{11} | # +86 XXXXXXXXXXX
|
| 380 |
+
\+81\s\d\s\d{4}\s\d{4} | # Japan Intl +81 X XXXX XXXX
|
| 381 |
+
\+81\s\d{2}\s\d{4}\s\d{4} | # Japan Intl +81 XX XXXX XXXX
|
| 382 |
+
0\d\s\d{4}\s\d{4} | # Japan STD 0X XXXX XXXX
|
| 383 |
+
\+81\d{10} | # +81 XXXXXXXXXX
|
| 384 |
+
\+81\d{9} | # +81 XXXXXXXXX
|
| 385 |
+
0\d{9} | # 0XXXXXXXXX
|
| 386 |
+
\+55\s\d{2}\s\d{5}-\d{4} | # Brazil Intl +55 XX XXXXX-XXXX
|
| 387 |
+
\+55\s\d{2}\s\d{4}-\d{4} | # Brazil Intl +55 XX XXXX-XXXX
|
| 388 |
+
0\d{2}\s\d{4}\s\d{4} | # Brazil STD 0XX XXXX XXXX
|
| 389 |
+
\+55\d{11} | # +55 XXXXXXXXXXX
|
| 390 |
+
\+55\d{10} | # +55 XXXXXXXXXX
|
| 391 |
+
0\d{10} | # 0XXXXXXXXXX
|
| 392 |
+
\+33\s\d\s\d{2}\s\d{2}\s\d{2}\s\d{2} | # France Intl +33 X XX XX XX XX
|
| 393 |
+
0\d\s\d{2}\s\d{2}\s\d{2}\s\d{2} | # France STD 0X XX XX XX XX
|
| 394 |
+
\+33\d{9} | # +33 XXXXXXXXX
|
| 395 |
+
0\d{9} | # 0XXXXXXXXX
|
| 396 |
+
\+7\s\d{3}\s\d{3}-\d{2}-\d{2} | # Russia Intl +7 XXX XXX-XX-XX
|
| 397 |
+
8\s\d{3}\s\d{3}-\d{2}-\d{2} | # Russia STD 8 XXX XXX-XX-XX
|
| 398 |
+
\+7\d{10} | # +7 XXXXXXXXXX
|
| 399 |
+
8\d{10} | # 8 XXXXXXXXXX
|
| 400 |
+
\+27\s\d{2}\s\d{3}\s\d{4} | # South Africa Intl +27 XX XXX XXXX
|
| 401 |
+
0\d{2}\s\d{3}\s\d{4} | # South Africa STD 0XX XXX XXXX
|
| 402 |
+
\+27\d{9} | # +27 XXXXXXXXX
|
| 403 |
+
0\d{9} | # 0XXXXXXXXX
|
| 404 |
+
\+52\s\d{3}\s\d{3}\s\d{4} | # Mexico Intl +52 XXX XXX XXXX
|
| 405 |
+
\+52\s\d{2}\s\d{4}\s\d{4} | # Mexico Intl +52 XX XXXX XXXX
|
| 406 |
+
01\s\d{3}\s\d{4} | # Mexico STD 01 XXX XXXX
|
| 407 |
+
\+52\d{10} | # +52 XXXXXXXXXX
|
| 408 |
+
01\d{7} | # 01 XXXXXXX
|
| 409 |
+
\+234\s\d{3}\s\d{3}\s\d{4} | # Nigeria Intl +234 XXX XXX XXXX
|
| 410 |
+
0\d{3}\s\d{3}\s\d{4} | # Nigeria STD 0XXX XXX XXXX
|
| 411 |
+
\+234\d{10} | # +234 XXXXXXXXXX
|
| 412 |
+
0\d{10} | # 0XXXXXXXXXX
|
| 413 |
+
\+971\s\d\s\d{3}\s\d{4} | # UAE Intl +971 X XXX XXXX
|
| 414 |
+
0\d\s\d{3}\s\d{4} | # UAE STD 0X XXX XXXX
|
| 415 |
+
\+971\d{8} | # +971 XXXXXXXX
|
| 416 |
+
0\d{8} | # 0XXXXXXXX
|
| 417 |
+
\+54\s9\s\d{3}\s\d{3}\s\d{4} | # Argentina Intl +54 9 XXX XXX XXXX
|
| 418 |
+
\+54\s\d{1}\s\d{4}\s\d{4} | # Argentina Intl +54 X XXXX XXXX
|
| 419 |
+
0\d{3}\s\d{4} | # Argentina STD 0XXX XXXX
|
| 420 |
+
\+54\d{10} | # +54 9 XXXXXXXXXX
|
| 421 |
+
\+54\d{9} | # +54 XXXXXXXXX
|
| 422 |
+
0\d{7} | # 0XXXXXXX
|
| 423 |
+
\+966\s\d\s\d{3}\s\d{4} | # Saudi Intl +966 X XXX XXXX
|
| 424 |
+
0\d\s\d{3}\s\d{4} | # Saudi STD 0X XXX XXXX
|
| 425 |
+
\+966\d{8} | # +966 XXXXXXXX
|
| 426 |
+
0\d{8} | # 0XXXXXXXX
|
| 427 |
+
\+1\d{10} | # +1 XXXXXXXXXX
|
| 428 |
+
\+1\s\d{3}\s\d{3}\s\d{4} | # +1 XXX XXX XXXX
|
| 429 |
+
\d{5}\s\d{5} | # XXXXX XXXXX
|
| 430 |
+
\d{10} | # XXXXXXXXXX
|
| 431 |
+
\+44\d{10} | # +44 XXXXXXXXXX
|
| 432 |
+
0\d{10} | # 0XXXXXXXXXX
|
| 433 |
+
\+61\d{9} | # +61 XXXXXXXXX
|
| 434 |
+
0\d{9} | # 0XXXXXXXXX
|
| 435 |
+
\+91\d{10} | # +91 XXXXXXXXXX
|
| 436 |
+
\+49\d{12} | # +49 XXXXXXXXXXXX
|
| 437 |
+
\+49\d{10} | # +49 XXXXXXXXXX
|
| 438 |
+
0\d{11} | # 0XXXXXXXXXXX
|
| 439 |
+
\+86\d{11} | # +86 XXXXXXXXXXX
|
| 440 |
+
\+81\d{10} | # +81 XXXXXXXXXX
|
| 441 |
+
\+81\d{9} | # +81 XXXXXXXXX
|
| 442 |
+
0\d{9} | # 0XXXXXXXXX
|
| 443 |
+
\+55\d{11} | # +55 XXXXXXXXXXX
|
| 444 |
+
\+55\d{10} | # +55 XXXXXXXXXX
|
| 445 |
+
0\d{10} | # 0XXXXXXXXXX
|
| 446 |
+
\+33\d{9} | # +33 XXXXXXXXX
|
| 447 |
+
0\d{9} | # 0XXXXXXXXX
|
| 448 |
+
\+7\d{10} | # +7 XXXXXXXXXX
|
| 449 |
+
8\d{10} | # 8 XXXXXXXXXX
|
| 450 |
+
\+27\d{9} | # +27 XXXXXXXXX
|
| 451 |
+
0\d{9} | # 0XXXXXXXXX (South Africa STD)
|
| 452 |
+
\+52\d{10} | # +52 XXXXXXXXXX
|
| 453 |
+
01\d{7} | # 01 XXXXXXX
|
| 454 |
+
\+234\d{10} | # +234 XXXXXXXXXX
|
| 455 |
+
0\d{10} | # 0XXXXXXXXXX
|
| 456 |
+
\+971\d{8} | # +971 XXXXXXXX
|
| 457 |
+
0\d{8} | # 0XXXXXXXX
|
| 458 |
+
\+54\s9\s\d{10} | # +54 9 XXXXXXXXXX
|
| 459 |
+
\+54\d{9} | # +54 XXXXXXXXX
|
| 460 |
+
0\d{7} | # 0XXXXXXX
|
| 461 |
+
\+966\d{8} | # +966 XXXXXXXX
|
| 462 |
+
0\d{8} # 0XXXXXXXX
|
| 463 |
\+\d{3}-\d{3}-\d{4}
|
| 464 |
+
)
|
| 465 |
+
|
| 466 |
+
|
| 467 |
+
''',re.VERBOSE)
|
| 468 |
|
| 469 |
email_regex = re.compile(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b')
|
| 470 |
link_regex = re.compile(r'\b(?:https?:\/\/)?(?:www\.)[a-zA-Z0-9-]+\.(?:com|co\.in|co|io|org|net|edu|gov|mil|int|uk|us|in|de|au|app|tech|xyz|info|biz|fr|dev)\b')
|