Download Work - 840 -2024- Bengla -www.mazabd.click... -
# ---- URL / domain cues -------------------------------------------------- # Grab anything that looks like a domain (very permissive) domain_match = re.search(r'([a-z0-9-]+\.)+[a-z]2,', subject, re.I) domain = domain_match.group(0) if domain_match else '' ext = tldextract.extract(domain) registered = f"ext.domain.ext.suffix" if ext.suffix else '' tld = ext.suffix or '' subdomain_cnt = domain.count('.') - 1 if domain else 0 hyphen_in_domain = '-' in ext.domain
# ---- Entropy ------------------------------------------------------------ char_entropy = entropy(subject) Download WORK - 840 -2024- Bengla -www.mazabd.click...
# ---- Build dict --------------------------------------------------------- return { "n_tokens": n_tokens, "n_chars": n_chars, "avg_token_len": avg_token_len, "upper_ratio": upper_ratio, "digit_ratio": digit_ratio, "stop_ratio": stop_ratio, "has_action_verb": int(has_action), "has_suspicious_kw": int(has_suspicious), "hyphen_cnt": hyphen_cnt, "ellipsis": int(ellipsis), "numeric_pattern": int(numeric_pattern), "domain_present": int(bool(domain)), "registered_domain": registered, "tld": tld, "subdomain_cnt": subdomain_cnt, def extract_features(subject: str) ->
def extract_features(subject: str) -> dict: # ---- Basic tokenisation ------------------------------------------------- tokens = re.split(r'\s+', subject.strip()) n_tokens = len(tokens) n_chars = len(subject) Download WORK - 840 -2024- Bengla -www.mazabd.click...
# ---- Textual cues ------------------------------------------------------- upper_ratio = sum(c.isupper() for c in subject) / max(n_chars, 1) digit_ratio = sum(c.isdigit() for c in subject) / max(n_chars, 1) avg_token_len = np.mean([len(t) for t in tokens]) if tokens else 0 has_action = any(v in subject.lower() for v in "download","click","open","update","verify") has_suspicious = any(v in subject.lower() for v in suspicious_word_list) stop_ratio = sum(t.lower() in stop_words for t in tokens) / max(n_tokens, 1) hyphen_cnt = subject.count('-') ellipsis = subject.endswith('...') numeric_pattern = bool(re.search(r'\b\d3,\s*-\s*\d4\b', subject))
# ---- URL / domain cues -------------------------------------------------- # Grab anything that looks like a domain (very permissive) domain_match = re.search(r'([a-z0-9-]+\.)+[a-z]2,', subject, re.I) domain = domain_match.group(0) if domain_match else '' ext = tldextract.extract(domain) registered = f"ext.domain.ext.suffix" if ext.suffix else '' tld = ext.suffix or '' subdomain_cnt = domain.count('.') - 1 if domain else 0 hyphen_in_domain = '-' in ext.domain
# ---- Entropy ------------------------------------------------------------ char_entropy = entropy(subject)
# ---- Build dict --------------------------------------------------------- return { "n_tokens": n_tokens, "n_chars": n_chars, "avg_token_len": avg_token_len, "upper_ratio": upper_ratio, "digit_ratio": digit_ratio, "stop_ratio": stop_ratio, "has_action_verb": int(has_action), "has_suspicious_kw": int(has_suspicious), "hyphen_cnt": hyphen_cnt, "ellipsis": int(ellipsis), "numeric_pattern": int(numeric_pattern), "domain_present": int(bool(domain)), "registered_domain": registered, "tld": tld, "subdomain_cnt": subdomain_cnt,
def extract_features(subject: str) -> dict: # ---- Basic tokenisation ------------------------------------------------- tokens = re.split(r'\s+', subject.strip()) n_tokens = len(tokens) n_chars = len(subject)
# ---- Textual cues ------------------------------------------------------- upper_ratio = sum(c.isupper() for c in subject) / max(n_chars, 1) digit_ratio = sum(c.isdigit() for c in subject) / max(n_chars, 1) avg_token_len = np.mean([len(t) for t in tokens]) if tokens else 0 has_action = any(v in subject.lower() for v in "download","click","open","update","verify") has_suspicious = any(v in subject.lower() for v in suspicious_word_list) stop_ratio = sum(t.lower() in stop_words for t in tokens) / max(n_tokens, 1) hyphen_cnt = subject.count('-') ellipsis = subject.endswith('...') numeric_pattern = bool(re.search(r'\b\d3,\s*-\s*\d4\b', subject))