egutierrez
dff0c0d2b7
Extractores nuevos en python/functions/cybersecurity/: - extract_ip_addresses (IPv4 + IPv6 con validacion ipaddress) - extract_emails (RFC 5322 simplificado) - extract_domains (FQDNs con TLD valido, lista estatica) - extract_file_hashes (MD5/SHA1/SHA256/SHA512, algoritmo por longitud) - extract_crypto_wallets (BTC legacy + bech32, ETH 0x+40hex) - extract_cve_ids (CVE-YYYY-NNNN+) - extract_mac_addresses (xx:xx:xx + xx-xx-xx, separador uniforme) - extract_phone_numbers (E.164 + ES local 9 digitos) Pipeline: - extract_iocs corre todos, deduplica spans contenidos. Mantiene purity:pure (kind:function con uses_functions no vacio) porque la regla del registry exige que los pipelines sean impuros. Todas devuelven list[dict] con value/start/end/type para que el caller (issues 0038-0040) pueda reconciliar offsets con spans NER sin reparsing. Refs #0037 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
59 lines
2.0 KiB
Python
59 lines
2.0 KiB
Python
"""Extrae FQDNs validos de un texto, con offsets."""
|
|
|
|
import re
|
|
|
|
# Lista estatica de TLDs comunes (no exhaustiva — IANA tiene >1500).
|
|
# Incluye los gTLD originales, los nuevos mas usados, y ccTLD frecuentes.
|
|
_VALID_TLDS = frozenset({
|
|
# gTLD originales
|
|
"com", "org", "net", "edu", "gov", "mil", "int",
|
|
# gTLD comunes
|
|
"info", "biz", "name", "pro", "mobi", "asia", "jobs", "tel", "travel",
|
|
"xxx", "post",
|
|
# nuevos gTLD populares
|
|
"app", "dev", "io", "ai", "tech", "cloud", "online", "site", "store",
|
|
"xyz", "top", "shop", "club", "fun", "live", "blog", "page", "news",
|
|
"media", "design", "studio", "agency", "io", "co", "me", "tv",
|
|
# ccTLD frecuentes
|
|
"us", "uk", "de", "fr", "es", "it", "nl", "be", "se", "no", "fi", "dk",
|
|
"ru", "ua", "pl", "cz", "ch", "at", "pt", "gr", "ie", "tr",
|
|
"ca", "mx", "br", "ar", "cl", "co", "pe", "ve", "uy",
|
|
"cn", "jp", "kr", "in", "id", "th", "vn", "my", "sg", "ph", "tw", "hk",
|
|
"au", "nz",
|
|
"za", "eg", "ma", "ng", "ke",
|
|
"il", "ae", "sa", "qa",
|
|
"eu",
|
|
})
|
|
|
|
# Componentes: letras/digitos con guiones internos, sin empezar/terminar en guion.
|
|
_LABEL = r"[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?"
|
|
_DOMAIN_REGEX = re.compile(
|
|
rf"(?<![A-Za-z0-9.-])"
|
|
rf"(?:{_LABEL}\.)+"
|
|
rf"[A-Za-z]{{2,63}}"
|
|
rf"(?![A-Za-z0-9.-])"
|
|
)
|
|
|
|
|
|
def extract_domains(text: str) -> list[dict]:
|
|
"""Extrae FQDNs cuyo TLD esta en la lista estatica.
|
|
|
|
Solo captura nombres con al menos un punto y un TLD reconocido. No
|
|
incluye URLs completas (ver `extract_urls`). Si el dominio aparece
|
|
dentro de un email, igual se extrae — el caller puede deduplicar
|
|
por offsets si lo necesita.
|
|
"""
|
|
results = []
|
|
for m in _DOMAIN_REGEX.finditer(text):
|
|
candidate = m.group(0)
|
|
tld = candidate.rsplit(".", 1)[-1].lower()
|
|
if tld not in _VALID_TLDS:
|
|
continue
|
|
results.append({
|
|
"value": candidate,
|
|
"start": m.start(),
|
|
"end": m.end(),
|
|
"type": "domain",
|
|
})
|
|
return results
|