mathias/tapir
1
0
Fork 0
Code Issues 25 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(youtube): acquire captions via player/timedtext baseUrl (ADR-010)
CI / Lint / Test / Vet (push) Successful in 6s
Details
CI / Build & Import (push) Failing after 1s
Details
CI / Mirror to GitHub (push) Has been skipped
Details

Browse Source 
The Data API captions.download endpoint is owner-only: every subscription
video the user does not own returned HTTP 403, producing 0 summaries and a
~150-line error spew in the first live Stage-0 run. Captions-first (ADR-007)
is sound; only the acquisition mechanism was wrong.

FetchTranscript now resolves caption tracks from the InnerTube player
response (ANDROID client, unauthenticated) and GETs the chosen track's
timedtext baseUrl with a plain http.Client — no OAuth token, which can break
the endpoint. The srv3 XML, json3, and legacy <transcript> formats all parse;
non-asr tracks in a preferred language win. Watch-page ytInitialPlayerResponse
scrape is the fallback when InnerTube returns no tracks.

Degrade, don't error (explicit quick-fix): no captionTracks, empty baseUrl, a
non-200 fetch, or an unparseable body yield Source=none, not an error. Only
genuine transport faults error — this kills the spew. OAuth stays on
ListSubscriptions/NewVideos (Data API); only transcript fetch goes unauthed.

Validated live from koala: the ANDROID client returned working baseUrls and
real transcript text for public videos the run identity does not own.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
mathias
2026-06-02 23:08:13 +02:00
co-authored by Claude Opus 4.8
parent fa16a62e6d
commit 8b14ef4add
4 changed files with 530 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/adapters/youtube/youtube_test.go
+112 -27
View File
@@ -46,6 +46,7 @@ func newTestAdapter(t *testing.T, handler http.HandlerFunc) (*Adapter, *fakeSecr
ConnectionID: "conn-1",
PreferredLanguages: []string{"en"},
BaseURL: srv.URL,
PlayerBaseURL: srv.URL,
}, secrets)
a.transport = srv.Client().Transport
return a, secrets
@@ -150,24 +151,51 @@ func TestNewVideos(t *testing.T) {
}
}
// --- transcript: captions present ------------------------------------------
// --- transcript: captions present (player response + timedtext baseUrl) ------
// captionTracksJSON builds a player-response body whose captionTracks point their
// baseUrls back at the test server (via the request Host), so the unauthenticated
// baseUrl GET lands on the same httptest handler.
func playerBody(host string) string {
base := "http://" + host
return `{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[
{"baseUrl":"` + base + `/api/timedtext?lang=sv","languageCode":"sv"},
{"baseUrl":"` + base + `/api/timedtext?lang=en&kind=asr","languageCode":"en","kind":"asr"},
{"baseUrl":"` + base + `/api/timedtext?lang=en","languageCode":"en"}
]}}}`
}
// TestFetchTranscriptWithCaptions: ANDROID player response yields tracks; the en
// non-asr track is preferred over both the sv track and the en asr track; its
// srv3 timedtext XML is fetched unauthenticated and reduced to plain text.
func TestFetchTranscriptWithCaptions(t *testing.T) {
a, secrets := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
switch r.URL.Path {
case "/captions":
if got := r.URL.Query().Get("videoId"); got != "vid1" {
t.Errorf("expected videoId=vid1, got %q", got)
case "/youtubei/v1/player":
if r.Method != http.MethodPost {
t.Errorf("player must be POST, got %s", r.Method)
}
_, _ = w.Write([]byte(`{"items":[
{"id":"cap-sv","snippet":{"language":"sv","trackKind":"standard","status":"serving"}},
{"id":"cap-en","snippet":{"language":"en","trackKind":"standard","status":"serving"}}
]}`))
case "/captions/cap-en":
if got := r.URL.Query().Get("tfmt"); got != "vtt" {
t.Errorf("expected tfmt=vtt, got %q", got)
if h := r.Header.Get("Authorization"); h != "" {
t.Errorf("player request must not be authenticated, got Authorization=%q", h)
}
_, _ = w.Write([]byte(playerBody(r.Host)))
case "/api/timedtext":
if h := r.Header.Get("Authorization"); h != "" {
t.Errorf("timedtext request must not be authenticated, got Authorization=%q", h)
}
switch r.URL.Query().Get("kind") {
case "asr":
_, _ = w.Write([]byte(`<timedtext format="3"><body><p t="0" d="1">WRONG asr track</p></body></timedtext>`))
default:
if got := r.URL.Query().Get("lang"); got != "en" {
t.Errorf("expected en track selected, got lang=%q", got)
}
_, _ = w.Write([]byte(`<?xml version="1.0" encoding="utf-8" ?><timedtext format="3"><body>` +
`<p t="0" d="2000">Hello world</p>` +
`<p t="2000" d="2000">Hello world</p>` +
`<p t="4000" d="2000">Second line</p>` +
`</body></timedtext>`))
}
_, _ = w.Write([]byte("WEBVTT\n\n1\n00:00:00.000 --> 00:00:02.000\nHello <c>world</c>\n\n2\n00:00:02.000 --> 00:00:04.000\nHello world\n\n3\n00:00:04.000 --> 00:00:06.000\nSecond line\n"))
default:
t.Errorf("unexpected path %q", r.URL.Path)
}
@@ -184,7 +212,7 @@ func TestFetchTranscriptWithCaptions(t *testing.T) {
if tr.Language != "en" {
t.Errorf("expected preferred language en, got %q", tr.Language)
}
// Markup stripped, timestamps/indices dropped, consecutive duplicate collapsed.
// Consecutive duplicate cue collapsed; asr track not chosen.
want := "Hello world\nSecond line"
if tr.Content != want {
t.Errorf("transcript text mismatch:\n got %q\nwant %q", tr.Content, want)
@@ -192,8 +220,35 @@ func TestFetchTranscriptWithCaptions(t *testing.T) {
if !tr.HasText() {
t.Error("expected HasText() true")
}
if len(secrets.requested) == 0 {
t.Error("expected SecretStore consulted for OAuth token")
}
// TestFetchTranscriptJSON3: a json3 timedtext body parses to clean text.
func TestFetchTranscriptJSON3(t *testing.T) {
a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
switch r.URL.Path {
case "/youtubei/v1/player":
base := "http://" + r.Host
_, _ = w.Write([]byte(`{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[` +
`{"baseUrl":"` + base + `/api/timedtext?lang=en","languageCode":"en"}]}}}`))
case "/api/timedtext":
_, _ = w.Write([]byte(`{"events":[` +
`{"segs":[{"utf8":"Hello "},{"utf8":"world"}]},` +
`{"segs":[{"utf8":"\n"}]},` +
`{"segs":[{"utf8":"Second line"}]}]}`))
default:
t.Errorf("unexpected path %q", r.URL.Path)
}
})
tr, err := a.FetchTranscript(context.Background(), domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid1"})
if err != nil {
t.Fatalf("FetchTranscript: %v", err)
}
if tr.Source != domain.SourceCaptions {
t.Fatalf("expected SourceCaptions, got %q", tr.Source)
}
if want := "Hello world\nSecond line"; tr.Content != want {
t.Errorf("json3 text mismatch:\n got %q\nwant %q", tr.Content, want)
}
}
@@ -201,10 +256,11 @@ func TestFetchTranscriptWithCaptions(t *testing.T) {
func TestFetchTranscriptNoCaptionsReturnsSourceNone(t *testing.T) {
a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/captions" {
t.Errorf("download must not be attempted when no track exists; got path %q", r.URL.Path)
if r.URL.Path == "/api/timedtext" {
t.Errorf("timedtext must not be fetched when no track exists")
}
_, _ = w.Write([]byte(`{"items":[]}`))
// Player response with no captions block at all.
_, _ = w.Write([]byte(`{"videoDetails":{"videoId":"vid-nocaps"}}`))
})
v := domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid-nocaps"}
@@ -223,15 +279,44 @@ func TestFetchTranscriptNoCaptionsReturnsSourceNone(t *testing.T) {
}
}
// A missing-token reference surfaces as an error rather than a silent skip.
func TestFetchTranscriptSecretResolutionError(t *testing.T) {
a, _ := newTestAdapter(t, func(w http.ResponseWriter, _ *http.Request) {
_, _ = w.Write([]byte(`{"items":[]}`))
// A 403/empty baseUrl fetch degrades to SourceNone, never an error (the explicit
// quick-fix: a finicky unofficial endpoint must not produce an error spew).
func TestFetchTranscriptBaseURLForbiddenDegrades(t *testing.T) {
a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
switch r.URL.Path {
case "/youtubei/v1/player":
base := "http://" + r.Host
_, _ = w.Write([]byte(`{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[` +
`{"baseUrl":"` + base + `/api/timedtext?lang=en","languageCode":"en"}]}}}`))
case "/api/timedtext":
w.WriteHeader(http.StatusForbidden)
}
})
a.cfg.TokenSecretRef = "op://HomeLab/missing#refresh"
_, err := a.FetchTranscript(context.Background(), domain.Video{ID: "v1", ProviderVideoID: "x"})
if err == nil {
t.Fatal("expected error when secret ref cannot be resolved")
tr, err := a.FetchTranscript(context.Background(), domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid1"})
if err != nil {
t.Fatalf("403 on baseUrl must degrade, not error: %v", err)
}
if tr.Source != domain.SourceNone {
t.Fatalf("expected SourceNone on 403, got %q", tr.Source)
}
}
// An empty baseUrl on the selected track degrades to SourceNone, never an error.
func TestFetchTranscriptEmptyBaseURLDegrades(t *testing.T) {
a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path == "/api/timedtext" {
t.Errorf("must not fetch an empty baseUrl")
}
_, _ = w.Write([]byte(`{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[` +
`{"baseUrl":"","languageCode":"en"}]}}}`))
})
tr, err := a.FetchTranscript(context.Background(), domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid1"})
if err != nil {
t.Fatalf("empty baseUrl must degrade, not error: %v", err)
}
if tr.Source != domain.SourceNone {
t.Fatalf("expected SourceNone on empty baseUrl, got %q", tr.Source)
}
}