chore: 重写初始提交(清空历史,整理后全量提交)

2026-08-16 16:54:14 +08:00
commit 6c1a106bc1
1808 changed files with 238144 additions and 0 deletions
@@ -0,0 +1,84 @@
+<?php
+// +----------------------------------------------------------------------
+// | YwxApp [ WE CAN DO IT JUST THINK ]
+// +----------------------------------------------------------------------
+// | Copyright (c) 2026-2036 http://ywxapp.cn All rights reserved.
+// +----------------------------------------------------------------------
+// | Author: ywxapp<admin@ywxapp.cn>
+// +----------------------------------------------------------------------
+declare(strict_types=1);
+
+namespace ywxapp\library;
+
+/**
+ * 搜索引擎蜘蛛识别
+ *
+ * 仅按 User-Agent 特征串识别（不做 DNS 反查，保证零阻塞）。
+ * 新增蜘蛛只需在 SPIDERS 追加一行：标识 => [UA特征串列表, 显示名]。
+ *
+ * @author ywxapp <admin@ywxapp.cn>
+ */
+class SpiderDetect
+{
+    /**
+     * 蜘蛛特征表：key=入库标识，value=[UA 特征串（不区分大小写，命中任一即算）, 中文显示名]
+     */
+    public const SPIDERS = [
+        'baidu'      => [['Baiduspider'], '百度'],
+        'google'     => [['Googlebot', 'Google-InspectionTool', 'AdsBot-Google'], '谷歌'],
+        'bing'       => [['bingbot', 'msnbot', 'BingPreview'], '必应'],
+        'sogou'      => [['Sogou web spider', 'Sogou inst spider', 'Sogou Pic Spider'], '搜狗'],
+        'so360'      => [['360Spider', 'HaoSouSpider', 'qihoobot'], '360'],
+        'bytedance'  => [['Bytespider', 'ToutiaoSpider'], '字节跳动'],
+        'shenma'     => [['YisouSpider'], '神马'],
+        'huawei'     => [['PetalBot'], '华为花瓣'],
+        'yandex'     => [['YandexBot'], 'Yandex'],
+        'duckduckgo' => [['DuckDuckBot', 'DuckDuckGo-Favicons-Bot'], 'DuckDuckGo'],
+        'yahoo'      => [['Yahoo! Slurp'], '雅虎'],
+        'apple'      => [['Applebot'], '苹果'],
+        'gptbot'     => [['GPTBot', 'ChatGPT-User', 'OAI-SearchBot'], 'OpenAI'],
+        'claudebot'  => [['ClaudeBot', 'anthropic-ai'], 'Anthropic'],
+        'semrush'    => [['SemrushBot'], 'Semrush'],
+        'ahrefs'     => [['AhrefsBot'], 'Ahrefs'],
+        'mj12'       => [['MJ12bot'], 'Majestic'],
+        'facebook'   => [['facebookexternalhit', 'FacebookBot'], 'Facebook'],
+    ];
+
+    /**
+     * 识别 UA，命中返回蜘蛛标识（SPIDERS 的 key），未命中返回 null
+     */
+    public static function detect(string $userAgent): ?string
+    {
+        if ($userAgent === '') {
+            return null;
+        }
+        foreach (self::SPIDERS as $key => [$needles]) {
+            foreach ($needles as $needle) {
+                if (stripos($userAgent, $needle) !== false) {
+                    return $key;
+                }
+            }
+        }
+        return null;
+    }
+
+    /**
+     * 蜘蛛标识 → 中文显示名（未知标识原样返回）
+     */
+    public static function label(string $key): string
+    {
+        return self::SPIDERS[$key][1] ?? $key;
+    }
+
+    /**
+     * 全部蜘蛛 标识=>显示名（后台下拉/报表用）
+     */
+    public static function labels(): array
+    {
+        $out = [];
+        foreach (self::SPIDERS as $key => [, $label]) {
+            $out[$key] = $label;
+        }
+        return $out;
+    }
+}