web_huangguo2_h5/app/service/seoser/indexable.go

package seoser

import (
	"net/url"
	"strconv"
	"strings"
)

// IsIndexablePath 是否为需要收录的公开页。
// 采用白名单策略：新增页面只有明确归类后才允许进入索引，避免搜索、账户、
// 排序变体和工具页因遗漏配置被搜索引擎收录。
func IsIndexablePath(raw string) bool {
	path := normalizedPath(raw)
	if path == "/" {
		return true
	}
	switch path {
	case "/about", "/help", "/terms", "/privacy", "/2257", "/dmca":
		return true
	}

	segments := splitPath(path)
	if len(segments) == 0 {
		return false
	}
	switch segments[0] {
	case "list":
		return isIndexablePlayletList(segments)
	case "series":
		return isIndexableSeriesList(segments)
	case "topic":
		return isIndexableSimplePagination(segments, "topic")
	case "topic-detail", "tags":
		return isIndexableNamedCollection(segments)
	case "rank", "popular-recommend":
		return isIndexableRanking(segments)
	case "more-list", "more-series-list":
		return isIndexableCuratedCollection(segments)
	case "recently-added":
		return isIndexableSimplePagination(segments, "recently-added")
	case "play":
		return isIndexablePlayletPlayback(segments)
	case "series-play":
		return len(segments) == 2 && segments[1] != ""
	default:
		return false
	}
}

// IsPrivatePath 标记不应跟踪链接的账户、认证和交易页面。
func IsPrivatePath(raw string) bool {
	path := normalizedPath(raw)
	for _, prefix := range []string{
		"/login", "/register", "/profile", "/history", "/favorites",
		"/purchased", "/setting", "/settings", "/recharge", "/feedback",
	} {
		if path == prefix || strings.HasPrefix(path, prefix+"/") {
			return true
		}
	}
	return false
}

func normalizedPath(raw string) string {
	path := strings.TrimSpace(raw)
	if u, err := url.Parse(path); err == nil && u.Path != "" {
		path = u.Path
	}
	path = "/" + strings.Trim(strings.TrimSpace(path), "/")
	if path == "/" {
		return path
	}
	return strings.TrimSuffix(path, "/")
}

func splitPath(path string) []string {
	path = strings.Trim(path, "/")
	if path == "" {
		return nil
	}
	return strings.Split(path, "/")
}

func positiveInt(raw string) bool {
	n, err := strconv.Atoi(raw)
	return err == nil && n > 0
}

func pageNumber(raw string) bool {
	n, err := strconv.Atoi(raw)
	return err == nil && n > 1
}

func isIndexableSimplePagination(segments []string, root string) bool {
	if len(segments) == 1 && segments[0] == root {
		return true
	}
	return len(segments) == 3 && segments[0] == root && segments[1] == "page" && pageNumber(segments[2])
}

func isIndexablePlayletList(segments []string) bool {
	if len(segments) == 1 {
		return true
	}
	if len(segments) == 2 {
		return segments[1] != "" && segments[1] != "all"
	}
	base, hasPage := withoutPageSuffix(segments)
	if len(base) != 4 || base[1] == "" {
		return false
	}
	updateStatus, updateErr := strconv.Atoi(base[2])
	sortType, sortErr := strconv.Atoi(base[3])
	if updateErr != nil || sortErr != nil || updateStatus < 0 || updateStatus > 2 || sortType != 1 {
		return false
	}
	// 默认第一页已有更短规范地址 /list 或 /list/:theme。
	return hasPage || updateStatus != 0
}

func isIndexableSeriesList(segments []string) bool {
	if len(segments) == 1 {
		return true
	}
	base, hasPage := withoutPageSuffix(segments)
	if len(base) != 4 {
		return false
	}
	media, topic, sortType := base[1], base[2], base[3]
	if media != "all" && media != "film" && media != "anime" {
		return false
	}
	if topic != "all" && !positiveInt(topic) {
		return false
	}
	if sortType != "1" {
		return false
	}
	// 默认第一页已有更短规范地址 /series。
	return hasPage || media != "all" || topic != "all"
}

func isIndexableNamedCollection(segments []string) bool {
	if len(segments) == 2 && segments[1] != "" {
		return true
	}
	return len(segments) == 4 && segments[1] != "" && segments[2] == "page" && pageNumber(segments[3])
}

func isIndexableRanking(segments []string) bool {
	if len(segments) == 1 {
		return true
	}
	if len(segments) == 2 {
		return segments[1] == "2" || segments[1] == "3"
	}
	if len(segments) == 3 {
		return segments[1] == "page" && pageNumber(segments[2])
	}
	return len(segments) == 4 && (segments[1] == "2" || segments[1] == "3") && segments[2] == "page" && pageNumber(segments[3])
}

func isIndexableCuratedCollection(segments []string) bool {
	if len(segments) == 2 {
		return segments[1] != ""
	}
	return len(segments) == 4 && segments[1] != "" && segments[2] == "page" && pageNumber(segments[3])
}

func isIndexablePlayletPlayback(segments []string) bool {
	// 规范入口是 /play/{slug}；各集 /play/{slug}/{ep} 近重复且多为薄播放页，不收录。
	return len(segments) == 2 && segments[1] != ""
}

func withoutPageSuffix(segments []string) ([]string, bool) {
	if len(segments) < 3 || segments[len(segments)-2] != "page" || !pageNumber(segments[len(segments)-1]) {
		return segments, false
	}
	return segments[:len(segments)-2], true
}