2025-09-03 13:20:23 +02:00

100 lines
4.7 KiB
Python

import phonenumbers
import logging
import re
def parse(text, default_regions = [
'US', 'GB', 'DE', 'FR', 'ES', 'IT', 'RU', 'CN', 'IN', 'JP',
'BR', 'ZA', 'NG', 'EG', 'TR', 'ID', 'AU', 'CA', 'MX', 'AR',
'KR', 'TH', 'VN', 'PH', 'MY', 'SA', 'IR', 'PK', 'BD', 'UA',
'PL', 'NL', 'BE', 'CH', 'AT', 'SE', 'NO', 'DK', 'FI', 'IL',
'SG', 'HK', 'NZ', 'AE', 'KE', 'CO', 'VE', 'PE', 'CL', 'GR',
'PT', 'CZ', 'RO', 'HU', 'BG', 'SK', 'SI', 'HR', 'RS', 'LT',
'LV', 'EE', 'CY', 'LU', 'MT', 'IS', 'KZ', 'UZ', 'AM', 'AZ',
'GE', 'MN', 'KG', 'TJ', 'TM', 'BT', 'NP', 'LK', 'MM', 'KH',
'LA', 'BN', 'FJ', 'PW', 'SB', 'VU', 'FM', 'WS', 'TO', 'TV',
'KI', 'NR', 'MQ', 'GF', 'RE', 'YT', 'PF', 'NC', 'WF', 'TF',
'AI', 'AG', 'AW', 'BS', 'BB', 'BZ', 'BM', 'VG', 'KY', 'CU',
'CW', 'DM', 'DO', 'GD', 'GP', 'HT', 'JM', 'MQ', 'MS', 'PR',
'KN', 'LC', 'VC', 'SX', 'TT', 'TC', 'VI', 'BO', 'BQ', 'EC',
'GY', 'PY', 'SR', 'UY', 'DZ', 'AO', 'BJ', 'BW', 'BF', 'BI',
'CV', 'CM', 'CF', 'TD', 'KM', 'CG', 'CD', 'DJ', 'GQ', 'ER',
'SZ', 'ET', 'GA', 'GM', 'GH', 'GN', 'GW', 'CI', 'LS', 'LR',
'LY', 'MG', 'MW', 'ML', 'MR', 'MU', 'MA', 'MZ', 'NA', 'NE',
'NG', 'RW', 'ST', 'SN', 'SC', 'SL', 'SO', 'SS', 'SD', 'TZ',
'TG', 'TN', 'UG', 'ZM', 'ZW'
]
):
matches = []
timestamp_patterns = [
(r'\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}', '%Y-%m-%d %H:%M:%S'), # ISO 8601 Extended
(r'\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2}', '%Y/%m/%d %H:%M:%S'), # ISO 8601 with slashes
(r'\d{2}/\d{2}/\d{4} \d{2}:\d{2}:\d{2}', '%d/%m/%Y %H:%M:%S'), # European Date Format
(r'\d{2}-\d{2}-\d{4} \d{2}:\d{2}:\d{2}', '%m-%d-%Y %H:%M:%S'), # US Date Format
(r'\d{8}_\d{6}', '%Y%m%d_%H%M%S'), # Compact Format
(r'\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}', '%Y-%m-%dT%H:%M:%S'), # ISO 8601 Basic
(r'\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}:\d{2}', '%d.%m.%Y %H:%M:%S'),# German Date Format
(r'\d{4}\d{2}\d{2} \d{2}:\d{2}:\d{2}', '%Y%m%d %H:%M:%S'), # Basic Format without Separators
(r'\d{1,2}-[A-Za-z]{3}-\d{4} \d{2}:\d{2}:\d{2}', '%d-%b-%Y %H:%M:%S'), # English Date Format with Month Name
(r'(?:19|20)\d{10}', '%Y%m%d%H%M'), # Compact Numeric Format
# Add more patterns as needed
]
unlikely_phone_patterns = [
r'\d{5,}\s?bytes', # File size in bytes
r'https?://\S+', # URLs
r'\bversion \d+', # 'version' followed by numbers
r'cve-\d{4}-\d+', # CVE identifiers
r'\S+\.onion\S*', # Onion addresses
r'Product ID: \S+', # Product IDs
r'\|\s*[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}\s*\|', # UUIDs
r'\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b', # IP addresses
r'Mem: \d+\s+\d+\s+\d+', # Memory sizes
r'Total: \d+\s+\d+\s+\d+', # Total memory
r'block_size=\d+', # Block size
r'-rw-------\s+\d+\s+\S+\s+\S+\s+\d+\s+\S+\s+\d{1,2}\s+\d{1,2}:\d{2}', # File details
r'\d+\.\d+\.\d+\.\d+\s+\d+\s+\S+\s+\d+', # IP and port patterns
# Add more patterns as needed
]
# More specific regex for phone numbers
def is_unlikely_phone_context(extended_text):
# Check against timestamp patterns
for pattern, _ in timestamp_patterns:
if re.search(pattern, extended_text):
return True
# Check against other unlikely phone patterns
for pattern in unlikely_phone_patterns:
if re.search(pattern, extended_text):
return True
return False
# More specific regex for phone numbers
phone_regex = r'\b(\+?\d{1,3}[\s-]?)?(\(?\d{1,4}\)?[\s-]?)?\d{3,5}[\s-]?\d{3,5}\b'
for number_match in re.finditer(phone_regex, text):
raw_number = number_match.group()
start_pos, end_pos = number_match.span()
# Extend the search window for additional context
extended_start = max(0, start_pos - 50)
extended_end = min(len(text), end_pos + 50)
extended_text = text[extended_start:extended_end]
if is_unlikely_phone_context(extended_text):
continue # Skip if the context indicates it's not a phone number
valid_number_found = False
for region in default_regions:
try:
parsed_number = phonenumbers.parse(raw_number, region)
if phonenumbers.is_valid_number(parsed_number):
matches.append((raw_number, start_pos, end_pos))
valid_number_found = True
break
except phonenumbers.NumberParseException:
continue
if not valid_number_found:
logging.debug(f"Failed to parse number: {raw_number}")
return matches