spider/internal/crawler/tme_validator.go

package crawler

import (
	"context"
	"fmt"
	"net/http"
	"strings"
	"time"
)

// TMeValidator t.me 死号预检
type TMeValidator struct {
	http *http.Client
}

// NewTMeValidator 创建 TMeValidator
func NewTMeValidator() *TMeValidator {
	return &TMeValidator{
		http: &http.Client{
			Timeout: 10 * time.Second,
			CheckRedirect: func(req *http.Request, via []*http.Request) error {
				return nil // 跟随重定向
			},
		},
	}
}

// IsAlive 检查 TG 用户名是否活跃
// 通过抓取 t.me/{username} 网页，检查是否包含头像元素来判断
func (v *TMeValidator) IsAlive(ctx context.Context, username string) bool {
	url := fmt.Sprintf("https://t.me/%s", username)
	req, err := http.NewRequestWithContext(ctx, "GET", url, nil)
	if err != nil {
		return false
	}

	req.Header.Set("User-Agent", "Mozilla/5.0 (compatible; Googlebot/2.1)")

	resp, err := v.http.Do(req)
	if err != nil {
		return false
	}
	defer resp.Body.Close()

	if resp.StatusCode == 404 {
		return false
	}

	// 读取部分响应体（前 10KB 足够判断）
	buf := make([]byte, 10240)
	n, _ := resp.Body.Read(buf)
	body := string(buf[:n])

	// 有效账号的页面包含头像相关的 HTML 元素
	if strings.Contains(body, "tgme_page_photo") || strings.Contains(body, "og:image") {
		return true
	}
	if strings.Contains(body, "tgme_page_description") {
		return true
	}
	return false
}