HTMLClassifier.py 文件源码

def scan(html):
        alerts = list()
        matches = HTMLClassifier.yara_rules.match(data=html)
        if not len(matches) > 0:
            return alerts

        for match in matches['html']:
           print match
           alert_reason = ", ".join([" ".join(t.split('_')) for t in match['tags']])
           alert_data = "\n".join([s['data'] for s in match['strings']])
           alerts.append((alert_reason, alert_data))
           log.msg("Yara HTML Classification Match: " + alert_reason, level=log.INFO)
        return alerts