spider/internal/processor/tagger.go

package processor

import (
	"strings"
)

// Industry keywords for matching. Extensible via config in the future.
var industryKeywords = map[string][]string{
	"机场": {
		"机场", "节点", "订阅", "clash", "v2ray", "trojan", "shadowsocks", "ss/ssr",
		"翻墙", "梯子", "科学上网", "加速器", "proxy", "代理",
	},
	"VPN": {
		"vpn", "VPN", "wireguard", "openvpn",
	},
}

// TagAndGrade assigns industry_tag and level (Hot/Warm/Cold) to each merchant.
func TagAndGrade(merchants []MergedMerchant) []TaggedMerchant {
	var result []TaggedMerchant
	for _, m := range merchants {
		tagged := TaggedMerchant{Merged: m}

		// Industry matching: check merchant_name + original_text
		text := strings.ToLower(m.Best.MerchantName + " " + m.Best.OriginalText)
		for industry, keywords := range industryKeywords {
			for _, kw := range keywords {
				if strings.Contains(text, strings.ToLower(kw)) {
					tagged.IndustryTag = industry
					break
				}
			}
			if tagged.IndustryTag != "" {
				break
			}
		}

		// Inherit from raw if no match found
		if tagged.IndustryTag == "" && m.Best.IndustryTag != "" {
			tagged.IndustryTag = m.Best.IndustryTag
		}

		// Level grading
		hasIndustry := tagged.IndustryTag != ""
		hasWebsiteOrEmail := m.Best.Website != "" || m.Best.Email != ""

		switch {
		case hasIndustry && hasWebsiteOrEmail:
			tagged.Level = "Hot"
		case hasIndustry:
			tagged.Level = "Warm"
		default:
			tagged.Level = "Cold"
		}

		result = append(result, tagged)
	}
	return result
}

// TaggedMerchant is the final output of the processor.
type TaggedMerchant struct {
	Merged      MergedMerchant
	IndustryTag string
	Level       string // Hot / Warm / Cold
}