backend/internal/latest/browser.go

@@ -2,7 +2,9 @@ package latest
 
 import (
 	"context"
+	"encoding/base64"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"net/url"
 	"regexp"
@@ -22,6 +24,12 @@ const challengeTimeout = 45 * time.Second
 
 var kaganeSeriesRe = regexp.MustCompile(`^/series/([0-9a-f-]{36})/?$`)
 
+// kaganeImageIDRe pins the only path segment Image interpolates into an
+// outbound URL. The id arrives from a stored cover URL, which a client
+// supplied, so it is matched rather than trusted: a headless browser is a
+// strong SSRF primitive.
+var kaganeImageIDRe = regexp.MustCompile(`^[0-9a-f-]{36}$`)
+
 // BrowserFetcher retrieves pages through a remote headless Chrome over the
 // DevTools Protocol.
 //
@@ -91,23 +99,6 @@ func (f *BrowserFetcher) Get(ctx context.Context, seriesURL string) (string, int
 		return "", 0, fmt.Errorf("not a fetchable browser series url: %q", seriesURL)
 	}
 
-	f.mu.Lock()
-	defer f.mu.Unlock()
-
-	ctx, cancel := context.WithTimeout(ctx, challengeTimeout)
-	defer cancel()
-	// A fresh tab per fetch, closed on return, so one wedged page cannot
-	// poison later polls.
-	tabCtx, cancelTab := chromedp.NewContext(f.allocCtx)
-	defer cancelTab()
-	// Bind the caller's deadline to the tab.
-	tabCtx, cancelDeadline := context.WithCancel(tabCtx)
-	defer cancelDeadline()
-	go func() {
-		<-ctx.Done()
-		cancelDeadline()
-	}()
-
 	var body string
 	// kagane's chapter list is only in its JSON API, which must be called from
 	// inside the page so the request carries the clearance cookie. novelfull
@@ -123,24 +114,134 @@ func (f *BrowserFetcher) Get(ctx context.Context, seriesURL string) (string, int
 		)
 	}
 
-	err := chromedp.Run(tabCtx,
-		chromedp.Navigate(seriesURL),
-		// The challenge reloads the page itself when it passes; waiting for the
-		// site's own root element is what tells us we are through it.
-		chromedp.WaitReady("body", chromedp.ByQuery),
-		read,
-	)
-	if err != nil {
+	// novelfull's payload is the DOM itself, and the interstitial has a DOM
+	// too, so "we have an answer" has to exclude it explicitly. kagane's
+	// in-page fetch just fails while challenged, which is already the signal.
+	done := func() bool { return body != "" && (isKagane || !isInterstitial(body)) }
+	if err := f.run(ctx, seriesURL, read, done); err != nil {
+		// Challenge never cleared, or the API refused. Indistinguishable from
+		// here and handled identically by the caller.
+		if errors.Is(err, errChallengeHeld) {
+			return "", 403, nil
+		}
 		return "", 0, fmt.Errorf("browser fetch %q: %w", seriesURL, err)
 	}
-	if body == "" {
-		// Challenge still up, or the API refused. Indistinguishable from here
-		// and handled identically by the caller.
-		return "", 403, nil
-	}
 	return body, 200, nil
 }
 
+// Image retrieves one kagane cover as raw bytes and its content type.
+//
+// It exists because kagane serves covers behind the same challenge as its
+// pages *and* with `cross-origin-resource-policy: same-origin`, so an <img> on
+// the web UI's origin cannot load one even from a browser that already holds
+// the clearance cookie (verified 2026-08-08). Proxying is the only route.
+//
+// The image URL is navigated to rather than fetched from some other kagane
+// page: the challenge only runs on a top-level navigation, and once it clears
+// the document *is* the image, so a same-origin fetch of location.href reads
+// it straight back out of the cache.
+//
+// The challenge is not solved by the first read: WaitReady("body") is satisfied
+// by the interstitial too. run holds the tab open until the in-page fetch
+// succeeds, which is what gives the challenge script the seconds it needs.
+func (f *BrowserFetcher) Image(ctx context.Context, imageID string) ([]byte, string, error) {
+	if !kaganeImageIDRe.MatchString(imageID) {
+		return nil, "", fmt.Errorf("not a kagane image id: %q", imageID)
+	}
+	var dataURL string
+	err := f.run(ctx, "https://kagane.to/api/v2/image/"+imageID+"/compressed",
+		chromedp.Evaluate(`fetch(location.href).then(r => r.ok
+			? r.blob().then(b => new Promise(res => {
+					const fr = new FileReader();
+					fr.onload = () => res(fr.result);
+					fr.readAsDataURL(b);
+				}))
+			: "")`, &dataURL, awaitPromise),
+		func() bool { return dataURL != "" })
+	if err != nil {
+		return nil, "", fmt.Errorf("browser image %s: %w", imageID, err)
+	}
+	// "data:image/webp;base64,<payload>".
+	head, payload, ok := strings.Cut(dataURL, ";base64,")
+	if !ok {
+		return nil, "", fmt.Errorf("browser image %s: not a data url", imageID)
+	}
+	raw, err := base64.StdEncoding.DecodeString(payload)
+	if err != nil {
+		return nil, "", fmt.Errorf("browser image %s: %w", imageID, err)
+	}
+	return raw, strings.TrimPrefix(head, "data:"), nil
+}
+
+// errChallengeHeld reports that the budget ran out with the interstitial still
+// up. Distinct from a transport failure: it means "this site said no", which
+// the poller answers with a 403 and its ordinary cooldown.
+var errChallengeHeld = errors.New("challenge held")
+
+// challengePollInterval paces re-reads while a challenge solves itself.
+const challengePollInterval = 2 * time.Second
+
+// isInterstitial reports whether html is Cloudflare's challenge page rather
+// than the site's own. Matched on the challenge runtime's script path, which is
+// stable across the interstitial's wording and locale — the visible "Just a
+// moment..." title is neither.
+func isInterstitial(html string) bool {
+	return strings.Contains(html, "/cdn-cgi/challenge-platform/")
+}
+
+// run navigates to target and re-reads until done reports an answer, bounded by
+// challengeTimeout and by the caller's own deadline, in a tab that is closed on
+// return so one wedged page cannot poison later calls.
+//
+// Holding the tab open across re-reads is the whole point. A Cloudflare
+// interstitial needs several seconds of a live page to solve itself and write
+// clearance into the browser's shared cookie jar; reading once and closing the
+// tab — which is what this did before 2026-08-08 — never gives it that window,
+// so every fetch lands on the interstitial and the clearance that would have
+// unblocked all the later ones is never obtained.
+func (f *BrowserFetcher) run(ctx context.Context, target string, read chromedp.Action, done func() bool) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+
+	ctx, cancel := context.WithTimeout(ctx, challengeTimeout)
+	defer cancel()
+	tabCtx, cancelTab := chromedp.NewContext(f.allocCtx)
+	defer cancelTab()
+	// Bind the caller's deadline to the tab.
+	tabCtx, cancelDeadline := context.WithCancel(tabCtx)
+	defer cancelDeadline()
+	go func() {
+		<-ctx.Done()
+		cancelDeadline()
+	}()
+
+	if err := chromedp.Run(tabCtx,
+		chromedp.Navigate(target),
+		chromedp.WaitReady("body", chromedp.ByQuery),
+	); err != nil {
+		return err
+	}
+
+	var lastErr error
+	for {
+		// The challenge reloads the page when it passes, which tears down the
+		// execution context mid-read. That is a retry, not a failure.
+		if err := chromedp.Run(tabCtx, read); err != nil {
+			lastErr = err
+		} else if done() {
+			return nil
+		}
+		select {
+		case <-ctx.Done():
+			if lastErr != nil {
+				return fmt.Errorf("%w (last read: %v)", errChallengeHeld, lastErr)
+			}
+			return errChallengeHeld
+		case <-time.After(challengePollInterval):
+		}
+	}
+}
+
 // kaganeAPIURL maps a stored series_url to the JSON endpoint carrying its
 // chapter list. Returning false for anything else is a second line of defence
 // behind fetchableSeriesURL: a headless browser is a strong SSRF primitive and

backend/internal/latest/smoke_image_test.go

@@ -0,0 +1,91 @@
+package latest
+
+import (
+	"context"
+	"net/http"
+	"os"
+	"testing"
+	"time"
+)
+
+// TestSmokeKaganeImage is the live proof that the cover proxy's fetch actually
+// clears Cloudflare and returns image bytes. It needs a real headless Chrome
+// with outbound network, so it runs only when SMOKE_BROWSER_WS_URL is set:
+//
+//	docker run --rm --shm-size=1gb -p 19222:9222 chromedp/headless-shell:stable
+//	SMOKE_BROWSER_WS_URL=ws://127.0.0.1:19222 go test -run TestSmokeKaganeImage ./internal/latest
+func TestSmokeKaganeImage(t *testing.T) {
+	ws := os.Getenv("SMOKE_BROWSER_WS_URL")
+	if ws == "" {
+		t.Skip("SMOKE_BROWSER_WS_URL unset")
+	}
+	const imageID = "019fe11a-84c3-7fc3-a84b-88787374b617" // SP Baby's cover
+
+	// The same URL through a plain client is what the web UI's <img> gets.
+	// Asserting on it keeps the test honest about why the browser is needed.
+	req, err := http.NewRequest(http.MethodGet,
+		"https://kagane.to/api/v2/image/"+imageID+"/compressed", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if res, err := (&http.Client{Timeout: 15 * time.Second}).Do(req); err == nil {
+		res.Body.Close()
+		if res.StatusCode == http.StatusOK {
+			t.Log("note: kagane answered a plain request 200 — the challenge is not up right now")
+		}
+	}
+
+	f, err := NewBrowserFetcher(ws)
+	if err != nil {
+		t.Fatalf("NewBrowserFetcher: %v", err)
+	}
+	defer f.Close()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 90*time.Second)
+	defer cancel()
+	body, contentType, err := f.Image(ctx, imageID)
+	if err != nil {
+		t.Fatalf("Image: %v", err)
+	}
+	if len(body) < 1000 {
+		t.Fatalf("body is %d bytes, want a real image", len(body))
+	}
+	if contentType != "image/webp" {
+		t.Fatalf("content type = %q, want image/webp", contentType)
+	}
+	// WebP files start with "RIFF....WEBP".
+	if string(body[:4]) != "RIFF" || string(body[8:12]) != "WEBP" {
+		t.Fatalf("body is not a WebP: % x", body[:12])
+	}
+	t.Logf("fetched %d bytes of %s", len(body), contentType)
+
+	if _, _, err := f.Image(ctx, "not-a-uuid"); err == nil {
+		t.Fatal("Image accepted a non-uuid id")
+	}
+}
+
+// Control for the test above: the poller's own kagane path, same sidecar. If
+// this fails too, the sidecar is not clearing the challenge at all and the
+// image result says nothing about Image itself.
+func TestSmokeKaganeGet(t *testing.T) {
+	ws := os.Getenv("SMOKE_BROWSER_WS_URL")
+	if ws == "" {
+		t.Skip("SMOKE_BROWSER_WS_URL unset")
+	}
+	f, err := NewBrowserFetcher(ws)
+	if err != nil {
+		t.Fatalf("NewBrowserFetcher: %v", err)
+	}
+	defer f.Close()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 90*time.Second)
+	defer cancel()
+	body, status, err := f.Get(ctx, "https://kagane.to/series/019fe11a-8670-7cf3-8343-0b02057d3787")
+	if err != nil {
+		t.Fatalf("Get: %v", err)
+	}
+	t.Logf("status=%d bytes=%d head=%.80q", status, len(body), body)
+	if status != 200 {
+		t.Fatalf("status = %d, want 200 — the sidecar is not clearing the challenge", status)
+	}
+}