init: web_hgdjc_server

app/middleware/reptilerecord/reptilerecord.go

@@ -0,0 +1,50 @@
+package reptilerecord
+
+import (
+	"strings"
+	"videoweb/pub/common/ipaddr"
+	"videoweb/pub/common/log"
+
+	"github.com/gin-gonic/gin"
+)
+
+const ctxKeyIsBot = "isBot"
+
+var (
+	botPatterns = map[string]string{
+		"Googlebot":           "Googlebot",
+		"Bingbot":             "Bingbot",
+		"Slurp":               "Slurp",
+		"DuckDuckBot":         "DuckDuckBot",
+		"Baiduspider":         "Baiduspider",
+		"YandexBot":           "YandexBot",
+		"Sogou":               "Sogou",
+		"Exabot":              "Exabot",
+		"facebot":             "facebot",
+		"facebookexternalhit": "facebookexternalhit",
+	}
+)
+
+func ReptileRecord(c *gin.Context) {
+	ua := c.Request.UserAgent()
+	botName := identifyBot(ua)
+	if botName != "" {
+		c.Set(ctxKeyIsBot, true)
+		log.Info("爬虫访问:", log.Any("botName", botName), log.Any("ua", ua), log.Any("path", c.Request.URL.Path), log.Any("ip", ipaddr.ResolveClientIP(c)))
+	}
+}
+
+// IsBot 返回当前请求是否来自已知搜索引擎爬虫
+func IsBot(c *gin.Context) bool {
+	v, exists := c.Get(ctxKeyIsBot)
+	return exists && v.(bool)
+}
+
+func identifyBot(userAgent string) string {
+	for name, pattern := range botPatterns {
+		if strings.Contains(userAgent, pattern) {
+			return name
+		}
+	}
+	return ""
+}