feat: paginated ranking scrape with lazy page fetching

- ScrapeRanking now accepts a maxPages int parameter (0 = all pages).
  Each page is fetched strictly sequentially; the next page is only
  requested after every entry from the current page has been sent,
  so there is no pre-fetching or look-ahead.
  Pagination stops automatically when no next-page link is present
  or when the rank-novels container is absent/empty.

- The ranking URL pattern follows the existing catalogue convention:
  /ranking?page=N (next-page link detection as the stop condition).

- Server: handleRankingRefresh reads an optional 'pages' form field
  and passes it to ScrapeRanking. Timeout scales at 90 s/page.

- UI: Refresh Rankings button is now a small form with a numeric
  'Pages' input (default 1), letting the user choose how many pages
  to pull in one refresh without touching the server config.

scraper/internal/novelfire/scraper.go

@@ -365,25 +365,29 @@ func (s *Scraper) ScrapeChapterList(ctx context.Context, bookURL string) ([]scra
 
 // ─── RankingProvider ───────────────────────────────────────────────────────────
 
-func (s *Scraper) ScrapeRanking(ctx context.Context) (<-chan scraper.BookMeta, <-chan error) {
-	entries := make(chan scraper.BookMeta, 64)
+// ScrapeRanking pages through up to maxPages ranking pages on novelfire.net/ranking.
+// Pages are fetched one at a time, strictly sequentially: the next page is only
+// requested after every entry from the current page has been sent to the channel.
+// maxPages <= 0 means "fetch all pages until no more are found".
+func (s *Scraper) ScrapeRanking(ctx context.Context, maxPages int) (<-chan scraper.BookMeta, <-chan error) {
+	entries := make(chan scraper.BookMeta, 32)
 	errs := make(chan error, 16)
 
 	go func() {
 		defer close(entries)
 		defer close(errs)
 
-		pageURL := baseURL + rankingPath
 		rank := 1
 
-		for pageURL != "" {
+		for page := 1; maxPages <= 0 || page <= maxPages; page++ {
 			select {
 			case <-ctx.Done():
 				return
 			default:
 			}
 
-			s.log.Info("scraping ranking page", "url", pageURL)
+			pageURL := fmt.Sprintf("%s%s?page=%d", baseURL, rankingPath, page)
+			s.log.Info("scraping ranking page", "page", page, "url", pageURL)
 
 			// Always use the urlClient for the ranking page — it requires JS rendering.
 			raw, err := s.urlClient.GetContent(ctx, browser.ContentRequest{
@@ -394,23 +398,29 @@ func (s *Scraper) ScrapeRanking(ctx context.Context) (<-chan scraper.BookMeta, <
 				BestAttempt:         true,
 			})
 			if err != nil {
-				s.log.Debug("ranking page fetch failed", "url", pageURL, "err", err)
-				errs <- fmt.Errorf("ranking page: %w", err)
+				s.log.Debug("ranking page fetch failed", "page", page, "url", pageURL, "err", err)
+				errs <- fmt.Errorf("ranking page %d: %w", page, err)
 				return
 			}
 
 			root, err := htmlutil.ParseHTML(raw)
 			if err != nil {
-				errs <- fmt.Errorf("ranking page parse: %w", err)
+				errs <- fmt.Errorf("ranking page %d parse: %w", page, err)
 				return
 			}
 
 			rankList := htmlutil.FindFirst(root, scraper.Selector{Class: "rank-novels"})
 			if rankList == nil {
+				s.log.Debug("rank-novels container not found, stopping pagination", "page", page)
 				break
 			}
 
 			items := htmlutil.FindAll(rankList, scraper.Selector{Tag: "li", Class: "novel-item"})
+			if len(items) == 0 {
+				s.log.Debug("no ranking items on page, stopping pagination", "page", page)
+				break
+			}
+
 			for _, item := range items {
 				// Cover: <figure class="cover"><a href="/book/slug"><img data-src="..."></a></figure>
 				var cover string
@@ -436,7 +446,7 @@ func (s *Scraper) ScrapeRanking(ctx context.Context) (<-chan scraper.BookMeta, <
 				// Status: <span class="status"> Ongoing/Completed </span>
 				status := htmlutil.ExtractFirst(item, scraper.Selector{Tag: "span", Class: "status"})
 
-				// Genres: <div class="categories"><div class="scroll"><span>Genre1</span><span>Genre2</span>...</div></div>
+				// Genres: <div class="categories"><div class="scroll"><span>Genre1</span>...</div></div>
 				var genres []string
 				categoriesNode := htmlutil.FindFirst(item, scraper.Selector{Tag: "div", Class: "categories"})
 				if categoriesNode != nil {
@@ -463,8 +473,12 @@ func (s *Scraper) ScrapeRanking(ctx context.Context) (<-chan scraper.BookMeta, <
 				}
 			}
 
-			// Next page - ranking pages use different pagination, just get first page for now
-			break
+			// Stop if no next-page link exists (natural end of ranking list).
+			nextHref := htmlutil.ExtractFirst(root, scraper.Selector{Tag: "a", Class: "next", Attr: "href"})
+			if nextHref == "" {
+				s.log.Debug("no next-page link found, stopping pagination", "page", page)
+				break
+			}
 		}
 	}()
 

scraper/internal/scraper/interfaces.go

@@ -112,9 +112,12 @@ type ChapterTextProvider interface {
 
 // RankingProvider can enumerate novels from a ranking page.
 type RankingProvider interface {
-	// ScrapeRanking pages through the ranking list, sending BookMeta values
-	// (with basic info like title, cover, genres, status, sourceURL) to the returned channel.
-	ScrapeRanking(ctx context.Context) (<-chan BookMeta, <-chan error)
+	// ScrapeRanking pages through up to maxPages ranking pages, sending BookMeta
+	// values (with basic info like title, cover, genres, status, sourceURL) to
+	// the returned channel. Pages are fetched sequentially and lazily: the next
+	// page is only requested once all entries from the current page have been
+	// sent. maxPages <= 0 means "all pages".
+	ScrapeRanking(ctx context.Context, maxPages int) (<-chan BookMeta, <-chan error)
 }
 
 // NovelScraper is the full interface that a concrete novel source must implement.

scraper/internal/server/ui.go

@@ -222,13 +222,21 @@ const rankingTmpl = `
          class="text-sm px-3 py-1.5 rounded-lg bg-zinc-700 hover:bg-zinc-600 text-white inline-flex items-center gap-1">
         View Markdown
       </a>
-      <button
+      <form
         hx-post="/ranking/refresh"
         hx-target="#ranking-refresh-status"
         hx-swap="innerHTML"
-        class="text-sm px-3 py-1.5 rounded-lg bg-amber-700 hover:bg-amber-600 text-white inline-flex items-center gap-2">
-        Refresh Rankings
-      </button>
+        class="flex items-center gap-2">
+        <label class="flex items-center gap-1.5">
+          <span class="text-xs text-zinc-400 whitespace-nowrap">Pages</span>
+          <input type="number" name="pages" value="1" min="1"
+                 class="w-16 rounded-lg bg-zinc-800 border border-zinc-700 px-2 py-1 text-sm text-zinc-100 text-center focus:outline-none focus:border-amber-500 transition-colors" />
+        </label>
+        <button type="submit"
+          class="text-sm px-3 py-1.5 rounded-lg bg-amber-700 hover:bg-amber-600 text-white inline-flex items-center gap-2">
+          Refresh Rankings
+        </button>
+      </form>
     </div>
   </div>
   <div id="ranking-refresh-status" class="mt-2"></div>
@@ -353,7 +361,18 @@ func (s *Server) handleRanking(w http.ResponseWriter, r *http.Request) {
 // handleRankingRefresh starts an async scrape of novelfire.net/ranking and
 // immediately returns a polling badge. The browser polls /ui/ranking/status
 // until the job finishes, then follows an HX-Redirect back to /ranking.
+//
+// Accepts an optional form field "pages" (integer ≥ 1). 0 or absent means
+// fetch all pages; otherwise at most that many pages are scraped.
 func (s *Server) handleRankingRefresh(w http.ResponseWriter, r *http.Request) {
+	_ = r.ParseForm()
+	maxPages := 0
+	if p := strings.TrimSpace(r.FormValue("pages")); p != "" {
+		if n, err := strconv.Atoi(p); err == nil && n > 0 {
+			maxPages = n
+		}
+	}
+
 	s.mu.Lock()
 	if s.rankingRunning {
 		s.mu.Unlock()
@@ -370,10 +389,15 @@ func (s *Server) handleRankingRefresh(w http.ResponseWriter, r *http.Request) {
 			s.mu.Unlock()
 		}()
 
-		ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
+		// Allow ~90 s per page; minimum 120 s for a single page.
+		timeout := 120 * time.Second
+		if maxPages > 1 {
+			timeout = time.Duration(maxPages) * 90 * time.Second
+		}
+		ctx, cancel := context.WithTimeout(context.Background(), timeout)
 		defer cancel()
 
-		rankingCh, errCh := s.novel.ScrapeRanking(ctx)
+		rankingCh, errCh := s.novel.ScrapeRanking(ctx, maxPages)
 
 		var rankingItems []writer.RankingItem
 		for {