1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
| import argparse
import csv
import re
from collections import Counter, defaultdict
from urllib.parse import unquote
RULES = {
"SQL注入": [
r"union\s+select",
r"\bor\s+1=1\b",
r"\band\s+1=1\b",
r"sleep\s*\(",
r"benchmark\s*\(",
r"information_schema",
r"(--|%2d%2d|#|%23)"
],
"XSS探测": [
r"<script",
r"%3cscript",
r"onerror",
r"onload",
r"javascript:",
r"alert\s*\("
],
"敏感路径访问": [
r"/\.git/config",
r"/\.env",
r"/admin",
r"/phpinfo\.php",
r"/backup",
r"/config\.php"
],
"命令执行探测": [
r"cmd=",
r"whoami",
r"\bid\b",
r"uname",
r"/bin/bash",
r"curl\s+",
r"wget\s+"
],
"疑似登录爆破": [
r"post\s+/login",
r"post\s+/admin",
r"post\s+/user/login"
]
}
LOG_PATTERN = re.compile(
r'(?P<ip>\S+) \S+ \S+ \[(?P<time>.*?)\] '
r'"(?P<method>\S+)\s+(?P<url>\S+)\s+(?P<protocol>[^"]+)" '
r'(?P<status>\d+) (?P<size>\S+) '
r'"(?P<referer>[^"]*)" "(?P<ua>[^"]*)"'
)
def parse_line(line):
match = LOG_PATTERN.search(line)
if not match:
return None
data = match.groupdict()
data["decoded_url"] = unquote(data["url"])
return data
def detect(record):
text = f'{record["method"]} {record["decoded_url"]} {record["ua"]}'.lower()
hits = []
for attack_type, rules in RULES.items():
for rule in rules:
if re.search(rule, text, re.IGNORECASE):
hits.append(attack_type)
break
return hits
def analyze(log_path):
attack_counter = Counter()
ip_counter = Counter()
url_counter = Counter()
status_counter = Counter()
timeline = defaultdict(list)
rows = []
with open(log_path, "r", encoding="utf-8", errors="ignore") as f:
for line in f:
record = parse_line(line)
if not record:
continue
hits = detect(record)
if not hits:
continue
ip = record["ip"]
url = record["decoded_url"]
status = record["status"]
ip_counter[ip] += 1
url_counter[url] += 1
status_counter[status] += 1
for hit in hits:
attack_counter[hit] += 1
timeline[ip].append((record["time"], hit, record["method"], url, status))
rows.append({
"ip": ip,
"time": record["time"],
"attack_type": hit,
"method": record["method"],
"url": url,
"status": status,
"user_agent": record["ua"]
})
return attack_counter, ip_counter, url_counter, status_counter, timeline, rows
def write_csv(rows, output):
if not rows:
return
fields = ["ip", "time", "attack_type", "method", "url", "status", "user_agent"]
with open(output, "w", newline="", encoding="utf-8-sig") as f:
writer = csv.DictWriter(f, fieldnames=fields)
writer.writeheader()
writer.writerows(rows)
def print_top(title, counter, limit=10):
print(f"\n[+] {title}")
for key, value in counter.most_common(limit):
print(f"{value:>5} {key}")
def main():
parser = argparse.ArgumentParser(description="Web access log attack feature extractor")
parser.add_argument("-f", "--file", required=True, help="access.log path")
parser.add_argument("-o", "--output", default="result.csv", help="CSV output path")
args = parser.parse_args()
attack_counter, ip_counter, url_counter, status_counter, timeline, rows = analyze(args.file)
print_top("攻击类型统计", attack_counter)
print_top("异常 IP TOP 10", ip_counter)
print_top("异常 URL TOP 10", url_counter)
print_top("状态码统计", status_counter)
print("\n[+] 攻击时间线示例")
for ip, events in list(timeline.items())[:5]:
print(f"\nIP: {ip}")
for time, attack_type, method, url, status in events[:10]:
print(f"{time} [{attack_type}] {method} {url} status={status}")
write_csv(rows, args.output)
print(f"\n[+] CSV 已导出: {args.output}")
if __name__ == "__main__":
main()
|