sitemap /play 页输出带默认剧集 ID 的规范地址

前端 /play/[slug]/ 会 301 到 /play/[slug]/[chapterId]/，sitemap 直接按首集 ID 拼好地址，避免爬虫走一次 301 浪费抓取预算。原创短剧要求 watermarkVideoUrl 非空。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

app/skd/job/sitemap/data.go

@@ -2,11 +2,13 @@ package sitemap
 
 import (
 	"context"
+	"strconv"
 	"strings"
 	"sync"
 	"time"
 	"videoweb/pub/common/utils"
 	"videoweb/pub/models/playletcategorymod"
+	"videoweb/pub/models/playletchaptermod"
 	"videoweb/pub/models/playletmod"
 	"videoweb/pub/models/playlettagmod"
 	"videoweb/pub/models/playletthememod"
@@ -16,9 +18,10 @@ import (
 )
 
 type idWithTime struct {
-	Id      int64
-	Slug    string
-	LastMod time.Time
+	Id         int64
+	Slug       string
+	LastMod    time.Time
+	IsOriginal bool
 }
 
 type staticPageEntry struct {
@@ -144,7 +147,9 @@ func getURL(sg *SitemapGenerator) {
 	if urls := buildPlayletPathURLs(webAddr, listed.items, "/detail", "weekly", 0.7); len(urls) > 0 {
 		_ = sg.writeSitemapFiles("sitemap-playletdetail", urls)
 	}
-	if urls := buildPlayletPathURLs(webAddr, listed.items, "/play", "weekly", 0.6); len(urls) > 0 {
+	// /play 页面需带上默认剧集 ID，否则前端会 301 到 /play/[slug]/[chapterId]/，浪费爬虫抓取预算。
+	chapterMap := getPlayletFirstChapterMap(ctx, listed.items)
+	if urls := buildPlayletPlayURLs(webAddr, listed.items, chapterMap, "weekly", 0.6); len(urls) > 0 {
 		_ = sg.writeSitemapFiles("sitemap-playletplay", urls)
 	}
 }
@@ -194,6 +199,94 @@ func buildPlayletPathURLs(webAddr string, items []idWithTime, prefix string, cha
 	return urls
 }
 
+// buildPlayletPlayURLs 构建播放页 sitemap URL：有默认剧集时直接拼成 /play/[slug]/[chapterId]/，与前端规范地址一致，
+// 避免爬虫经由 301 跳到带剧集 ID 的地址。查不到剧集的短剧跳过，不输出会 301 或 404 的 URL。
+func buildPlayletPlayURLs(webAddr string, items []idWithTime, chapterMap map[int64]int64, changeFreq string, priority float32) []URL {
+	urls := make([]URL, 0, len(items))
+	for _, item := range items {
+		chapterId, ok := chapterMap[item.Id]
+		if !ok || chapterId <= 0 {
+			continue
+		}
+		segment := utils.PathSegment(item.Slug, item.Id)
+		if segment == "" {
+			continue
+		}
+		path := "/play/" + segment + "/" + strconv.FormatInt(chapterId, 10) + "/"
+		lastMod := formatLastMod(item.LastMod)
+		if lastMod == "" {
+			lastMod = time.Now().Format(time.DateOnly)
+		}
+		urls = append(urls, URL{
+			Loc:        utils.JoinUrlPathKeepSlash(webAddr, path),
+			LastMod:    lastMod,
+			ChangeFreq: changeFreq,
+			Priority:   priority,
+		})
+	}
+	return urls
+}
+
+// getPlayletFirstChapterMap 批量查询每部短剧的默认（首集）剧集 ID，与前端 /play/[slug]/ 的 301 目标保持一致：
+// 按 currentEpisode 升序取首条；原创短剧要求 watermarkVideoUrl 非空（未处理好的集数不露出，避免前端再次跳转）。
+func getPlayletFirstChapterMap(ctx context.Context, items []idWithTime) map[int64]int64 {
+	result := make(map[int64]int64, len(items))
+	if len(items) == 0 {
+		return result
+	}
+	ids := make([]int64, 0, len(items))
+	originalSet := make(map[int64]struct{}, len(items))
+	for _, item := range items {
+		if item.Id <= 0 {
+			continue
+		}
+		ids = append(ids, item.Id)
+		if item.IsOriginal {
+			originalSet[item.Id] = struct{}{}
+		}
+	}
+	const batchSize = 200
+	for start := 0; start < len(ids); start += batchSize {
+		end := start + batchSize
+		if end > len(ids) {
+			end = len(ids)
+		}
+		batch := ids[start:end]
+		list, err := playletchaptermod.FindManyPlayletChapter(ctx, bson.M{
+			playletchaptermod.FN.PlayletChapter.PlayletId: bson.M{"$in": batch},
+		}, options.Find().
+			SetProjection(bson.M{
+				playletchaptermod.FN.PlayletChapter.Id:                1,
+				playletchaptermod.FN.PlayletChapter.PlayletId:         1,
+				playletchaptermod.FN.PlayletChapter.CurrentEpisode:    1,
+				playletchaptermod.FN.PlayletChapter.WatermarkVideoUrl: 1,
+			}).
+			SetSort(bson.D{
+				{Key: playletchaptermod.FN.PlayletChapter.PlayletId, Value: 1},
+				{Key: playletchaptermod.FN.PlayletChapter.CurrentEpisode, Value: 1},
+				{Key: playletchaptermod.FN.PlayletChapter.Id, Value: 1},
+			}))
+		if err != nil {
+			continue
+		}
+		for _, chapter := range list {
+			if chapter == nil || chapter.PlayletId <= 0 || chapter.Id <= 0 {
+				continue
+			}
+			if _, ok := result[chapter.PlayletId]; ok {
+				continue
+			}
+			if _, isOriginal := originalSet[chapter.PlayletId]; isOriginal {
+				if strings.TrimSpace(chapter.WatermarkVideoUrl) == "" {
+					continue
+				}
+			}
+			result[chapter.PlayletId] = chapter.Id
+		}
+	}
+	return result
+}
+
 func formatLastMod(t time.Time) string {
 	if t.IsZero() {
 		return ""
@@ -223,6 +316,7 @@ func getPlayletList(ctx context.Context) listedPlaylets {
 				playletmod.FN.Playlet.Slug:        1,
 				playletmod.FN.Playlet.UpdatedAt:   1,
 				playletmod.FN.Playlet.OnlineAt:    1,
+				playletmod.FN.Playlet.IsOriginal:  1,
 				playletmod.FN.Playlet.ThemeIds:    1,
 				playletmod.FN.Playlet.TagIds:      1,
 				playletmod.FN.Playlet.CategoryIds: 1,
@@ -235,7 +329,12 @@ func getPlayletList(ctx context.Context) listedPlaylets {
 			if lastMod.IsZero() {
 				lastMod = info.OnlineAt
 			}
-			result.items = append(result.items, idWithTime{Id: info.Id, Slug: info.Slug, LastMod: lastMod})
+			result.items = append(result.items, idWithTime{
+				Id:         info.Id,
+				Slug:       info.Slug,
+				LastMod:    lastMod,
+				IsOriginal: info.IsOriginal,
+			})
 			addListedIDs(result.themeIDs, info.ThemeIds)
 			addListedIDs(result.tagIDs, info.TagIds)
 			addListedIDs(result.categoryIDs, info.CategoryIds)