Python实现多文本文件中指定IP相关规则块的信息提取

直接上可运行的代码，能遍历所有st.txt文件，筛选出包含169.176.39.0/24的规则块，并提取你需要的信息：

import os

TARGET_IP = "169.176.39.0/24"

def parse_rule_block(block_lines):
    # 初始化提取的信息
    combo_tuple = ""
    source_ips = []
    dest_ips = []
    ports = []
    
    for line in block_lines:
        line = line.strip()
        if not line:
            continue
        # 提取Combination和Tuple编号
        if line.startswith("Combination"):
            combo_tuple = line.split(":", 1)[1].strip()
        # 提取Source Groups里的IP
        elif "Source Groups" in line:
            ip_part = line.split(":", 1)[1].strip().strip("[]")
            if ip_part:
                source_ips = [ip.strip() for ip in ip_part.split(",")]
        # 提取Destination Group里的IP
        elif "Destination Group" in line:
            ip_part = line.split(":", 1)[1].strip().strip("[]")
            if ip_part:
                dest_ips = [ip.strip() for ip in ip_part.split(",")]
        # 提取端口信息
        elif any(keyword in line for keyword in ["Port", "Destination Port"]):
            port_part = line.split(":", 1)[1].strip()
            if port_part:
                ports = [p.strip() for p in port_part.split(",")]
    
    return {
        "combination_tuple": combo_tuple,
        "source_ips": source_ips,
        "dest_ips": dest_ips,
        "ports": ports
    }

def process_st_file(file_path):
    matched_blocks = []
    with open(file_path, "r", encoding="utf-8") as f:
        lines = f.readlines()
    
    current_block = []
    for line in lines:
        # 遇到新的Combination行，先处理之前的块
        if line.strip().startswith("Combination"):
            if current_block:
                if TARGET_IP in " ".join(current_block):
                    parsed = parse_rule_block(current_block)
                    matched_blocks.append(parsed)
                current_block = []
            current_block.append(line)
        else:
            current_block.append(line)
    # 处理最后一个块
    if current_block and TARGET_IP in " ".join(current_block):
        parsed = parse_rule_block(current_block)
        matched_blocks.append(parsed)
    
    return matched_blocks

def main():
    # 遍历当前目录及子目录下所有st.txt文件
    for root, dirs, files in os.walk("."):
        for file in files:
            if file == "st.txt":
                file_path = os.path.join(root, file)
                print(f"=== 处理文件: {file_path} ===")
                matched = process_st_file(file_path)
                if not matched:
                    print("无匹配规则块\n")
                    continue
                # 按指定格式输出
                for idx, block in enumerate(matched, 1):
                    print(f"规则块 {idx}:")
                    print(f"  Combination&Tuple: {block['combination_tuple']}")
                    print(f"  Source Groups IP: {', '.join(block['source_ips'])}")
                    print(f"  Destination Group IP: {', '.join(block['dest_ips'])}")
                    print(f"  端口信息: {', '.join(block['ports'])}\n")

if __name__ == "__main__":
    main()

代码说明 #

1. 遍历文件：用os.walk自动扫描所有子目录里的st.txt，无需手动指定路径
2. 分割规则块：以Combination开头的行作为规则块起始，每遇到新的起始行就处理完上一个块
3. 筛选目标IP：将块内所有内容拼接成字符串，检查是否包含目标IP
4. 提取字段：针对规则块内的关键行，按字符串分割提取对应信息，适配常见规则格式；如果你的文件格式有特殊之处，直接修改parse_rule_block里的判断逻辑即可
5. 输出格式：目前是分文件、分规则块的清晰排版，你可以根据需求调整成写入文件或其他格式

注意事项 #

如果你的st.txt字段格式和代码假设的不同（比如Source Groups不是[IP1,IP2]格式），直接修改parse_rule_block里对应字段的处理代码，调整分割符或改用正则匹配都可以。

内容的提问来源于stack exchange，提问作者Noah