sitemap 播放页直接写第一集地址，避免 /play/{slug}/ 301

取第一集的规则与 app 详情接口选集列表一致（集号、ID 升序；原创剧只算已加水印的剧集），
没有可播放剧集的短剧不再写入 sitemap。

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

app/skd/job/sitemap/data.go

@@ -2,11 +2,14 @@ package sitemap
 
 import (
 	"context"
+	"strconv"
 	"strings"
 	"sync"
 	"time"
+	"videoweb/pub/common/log"
 	"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 +19,10 @@ import (
 )
 
 type idWithTime struct {
-	Id      int64
-	Slug    string
-	LastMod time.Time
+	Id         int64
+	Slug       string
+	LastMod    time.Time
+	IsOriginal bool // 仅短剧使用：原创剧只算已加水印的剧集
 }
 
 type staticPageEntry struct {
@@ -144,7 +148,7 @@ 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 {
+	if urls := buildPlayletPlayURLs(webAddr, listed.items, firstPlayletChapterIDs(ctx, listed.items), "weekly", 0.6); len(urls) > 0 {
 		_ = sg.writeSitemapFiles("sitemap-playletplay", urls)
 	}
 }
@@ -194,6 +198,78 @@ func buildPlayletPathURLs(webAddr string, items []idWithTime, prefix string, cha
 	return urls
 }
 
+// buildPlayletPlayURLs 播放页直接写第一集的规范地址 /play/{slug}/{chapterId}/，
+// 避免 /play/{slug}/ 在 h5 再 301 一次；没有可播放剧集的短剧不写入（h5 会返回 404）。
+func buildPlayletPlayURLs(webAddr string, items []idWithTime, firstChapter map[int64]int64, changeFreq string, priority float32) []URL {
+	urls := make([]URL, 0, len(items))
+	for _, item := range items {
+		chapterID := firstChapter[item.Id]
+		if chapterID <= 0 {
+			continue
+		}
+		lastMod := formatLastMod(item.LastMod)
+		if lastMod == "" {
+			lastMod = time.Now().Format(time.DateOnly)
+		}
+		urls = append(urls, URL{
+			Loc:        utils.JoinUrlPathKeepSlash(webAddr, entityPath("/play", item.Slug, item.Id)+strconv.FormatInt(chapterID, 10)+"/"),
+			LastMod:    lastMod,
+			ChangeFreq: changeFreq,
+			Priority:   priority,
+		})
+	}
+	return urls
+}
+
+// firstPlayletChapterIDs 取每部短剧的第一集 ID，规则与 app 详情接口的选集列表一致
+// （按集号、ID 升序；原创剧只算已加水印的剧集），h5 播放页跳转也取这一集。
+func firstPlayletChapterIDs(ctx context.Context, items []idWithTime) map[int64]int64 {
+	result := make(map[int64]int64, len(items))
+	original := make(map[int64]bool, len(items))
+	ids := make([]int64, 0, len(items))
+	for _, item := range items {
+		if item.Id > 0 {
+			ids = append(ids, item.Id)
+			original[item.Id] = item.IsOriginal
+		}
+	}
+	const batch = 500
+	for start := 0; start < len(ids); start += batch {
+		end := start + batch
+		if end > len(ids) {
+			end = len(ids)
+		}
+		list, err := playletchaptermod.FindManyPlayletChapter(ctx, bson.M{
+			playletchaptermod.FN.PlayletChapter.PlayletId: bson.M{"$in": ids[start:end]},
+		}, options.Find().
+			SetSort(bson.D{
+				{Key: playletchaptermod.FN.PlayletChapter.PlayletId, Value: 1},
+				{Key: playletchaptermod.FN.PlayletChapter.CurrentEpisode, Value: 1},
+				{Key: playletchaptermod.FN.PlayletChapter.Id, Value: 1},
+			}).
+			SetProjection(bson.M{
+				playletchaptermod.FN.PlayletChapter.Id:                1,
+				playletchaptermod.FN.PlayletChapter.PlayletId:         1,
+				playletchaptermod.FN.PlayletChapter.CurrentEpisode:    1,
+				playletchaptermod.FN.PlayletChapter.WatermarkVideoUrl: 1,
+			}))
+		if err != nil {
+			log.Error("sitemap 查询短剧第一集失败", log.E(err))
+			continue
+		}
+		for _, ch := range list {
+			if ch == nil || ch.Id <= 0 || result[ch.PlayletId] > 0 {
+				continue
+			}
+			if original[ch.PlayletId] && ch.WatermarkVideoUrl == "" {
+				continue
+			}
+			result[ch.PlayletId] = ch.Id
+		}
+	}
+	return result
+}
+
 func formatLastMod(t time.Time) string {
 	if t.IsZero() {
 		return ""
@@ -226,6 +302,7 @@ func getPlayletList(ctx context.Context) listedPlaylets {
 				playletmod.FN.Playlet.ThemeIds:    1,
 				playletmod.FN.Playlet.TagIds:      1,
 				playletmod.FN.Playlet.CategoryIds: 1,
+				playletmod.FN.Playlet.IsOriginal:  1,
 			}))
 		for _, info := range list {
 			if info == nil || info.Id <= 0 {
@@ -235,7 +312,7 @@ 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)

app/skd/job/sitemap/play_url_test.go

@@ -0,0 +1,17 @@
+package sitemap
+
+import "testing"
+
+func TestBuildPlayletPlayURLs(t *testing.T) {
+	items := []idWithTime{
+		{Id: 12, Slug: "xionnhge"},
+		{Id: 13, Slug: "nochapter"},
+	}
+	urls := buildPlayletPlayURLs("https://hgaidj.net", items, map[int64]int64{12: 27939}, "weekly", 0.6)
+	if len(urls) != 1 {
+		t.Fatalf("got %d urls, want 1 (playlet without chapters must be skipped)", len(urls))
+	}
+	if urls[0].Loc != "https://hgaidj.net/play/xionnhge/27939/" {
+		t.Errorf("Loc = %q", urls[0].Loc)
+	}
+}