WINDOWS主机配置拦截恶意爬虫和AI抓取。

<?xml version="1.0" encoding="UTF-8"?>
<configuration>
    <system.webServer>
        <rewrite>
            <rules>
                <!-- 原来的 ASP 拦截规则 -->
                <rule name="403asp" stopProcessing="true">
                    <match url="(.*)\.asp$" ignoreCase="true" />
                    <action type="CustomResponse" statusCode="403" statusReason="Forbidden" statusDescription="Forbidden" />
                </rule>

                <!-- 禁止所有搜索引擎爬虫，允许百度 -->
                <rule name="BlockSearchBots" stopProcessing="true">
                    <match url=".*" />
                    <conditions logicalGrouping="MatchAny" trackAllCaptures="false">
                        <add input="{HTTP_USER_AGENT}" pattern="Googlebot" />
                        <add input="{HTTP_USER_AGENT}" pattern="bingbot" />
                        <add input="{HTTP_USER_AGENT}" pattern="360Spider" />
                        <add input="{HTTP_USER_AGENT}" pattern="Sogou" />
                        <add input="{HTTP_USER_AGENT}" pattern="YisouSpider" />
                        <add input="{HTTP_USER_AGENT}" pattern="Bytespider" />
                        <add input="{HTTP_USER_AGENT}" pattern="YandexBot" />
                        <add input="{HTTP_USER_AGENT}" pattern="DuckDuckBot" />
                        <add input="{HTTP_USER_AGENT}" pattern="AhrefsBot" />
                        <add input="{HTTP_USER_AGENT}" pattern="SemrushBot" />
                        <add input="{HTTP_USER_AGENT}" pattern="MJ12bot" />
                        <add input="{HTTP_USER_AGENT}" pattern="crawler" />
                        <add input="{HTTP_USER_AGENT}" pattern="spider" />
                        <add input="{HTTP_USER_AGENT}" pattern="bot" />
                    </conditions>
                    <conditions logicalGrouping="MatchAll">
                        <add input="{HTTP_USER_AGENT}" negate="true" pattern="Baiduspider" />
                    </conditions>
                    <action type="CustomResponse" statusCode="403" statusReason="Forbidden" statusDescription="Search Bots not allowed" />
                </rule>

                <!-- 专门拦截 AI 爬虫 -->
                <rule name="BlockAIBots" stopProcessing="true">
                    <match url=".*" />
                    <conditions logicalGrouping="MatchAny" trackAllCaptures="false">
                        <add input="{HTTP_USER_AGENT}" pattern="ChatGPT" />
                        <add input="{HTTP_USER_AGENT}" pattern="ClaudeBot" />
                        <add input="{HTTP_USER_AGENT}" pattern="Anthropic" />
                        <add input="{HTTP_USER_AGENT}" pattern="OpenAI" />
                        <add input="{HTTP_USER_AGENT}" pattern="Perplexity" />
                        <add input="{HTTP_USER_AGENT}" pattern="DeepSeek" />
                        <add input="{HTTP_USER_AGENT}" pattern="AIbot" />
                    </conditions>
                    <action type="CustomResponse" statusCode="403" statusReason="Forbidden" statusDescription="AI Bots not allowed" />
                </rule>
            </rules>
        </rewrite>
    </system.webServer>
</configuration>