spider/internal/processor/tmechecker.go

package processor

import (
	"context"
	"log"
	"spider/internal/crawler"
	"spider/internal/model"
)

// TMeChecker filters dead TG accounts via HTTP t.me page scraping.
// Free, unlimited, 100% accurate.
type TMeChecker struct {
	validator *crawler.TMeValidator
}

// NewTMeChecker creates a new TMeChecker.
func NewTMeChecker() *TMeChecker {
	return &TMeChecker{validator: crawler.NewTMeValidator()}
}

// Filter checks each raw merchant's tg_username against t.me.
// Returns alive merchants; dead ones are returned separately with status="invalid".
func (c *TMeChecker) Filter(ctx context.Context, raws []model.MerchantRaw) (alive []model.MerchantRaw, dead []model.MerchantRaw) {
	for _, raw := range raws {
		if ctx.Err() != nil {
			break
		}
		if raw.TgUsername == "" {
			alive = append(alive, raw)
			continue
		}
		if c.validator.IsAlive(ctx, raw.TgUsername) {
			alive = append(alive, raw)
		} else {
			log.Printf("[tmechecker] dead: @%s", raw.TgUsername)
			dead = append(dead, raw)
		}
	}
	return
}