libnovel/scraper/internal/server/handlers_preview.go

package server

// handlers_preview.go — on-demand preview endpoints for books not yet in PocketBase.
//
// These endpoints allow the UI to display a book's metadata and chapter list
// (scraped live from novelfire.net) without requiring a full scrape to have
// been run first.  They are read-only: nothing is persisted to PocketBase or
// MinIO.
//
// Endpoints:
//
//	GET  /api/book-preview/{slug}               — scrape book metadata + chapter list live
//	GET  /api/chapter-text-preview/{slug}/{n}   — scrape a single chapter text live

import (
	"context"
	"encoding/json"
	"fmt"
	"net/http"
	"strconv"

	"github.com/libnovel/scraper/internal/scraper"
)

// BookPreviewResponse is the JSON response for /api/book-preview/{slug}.
type BookPreviewResponse struct {
	InLib    bool                 `json:"in_lib"`
	Meta     scraper.BookMeta     `json:"meta"`
	Chapters []scraper.ChapterRef `json:"chapters"`
}

// handleBookPreview handles GET /api/book-preview/{slug}.
//
// It scrapes book metadata and the full chapter list live from novelfire.net.
// It also checks whether the book exists in the local store (PocketBase) and
// sets the InLib flag accordingly.  Nothing is written to any store.
//
// Query param: source_url (optional) — if provided, uses that URL instead of
// constructing one from the slug.
func (s *Server) handleBookPreview(w http.ResponseWriter, r *http.Request) {
	slug := r.PathValue("slug")
	if slug == "" {
		http.Error(w, `{"error":"missing slug"}`, http.StatusBadRequest)
		return
	}

	// Determine the book URL: prefer explicit source_url query param.
	bookURL := r.URL.Query().Get("source_url")
	if bookURL == "" {
		bookURL = fmt.Sprintf("%s/book/%s", novelFireBase, slug)
	}

	ctx := r.Context()

	// Check whether the book is already in the local library.
	_, inLib, err := s.store.ReadMetadata(ctx, slug)
	if err != nil {
		// Non-fatal: we can still serve the preview.
		s.log.Warn("book-preview: ReadMetadata failed", "slug", slug, "err", err)
		inLib = false
	}

	// Scrape live metadata.
	meta, err := s.novel.ScrapeMetadata(ctx, bookURL)
	if err != nil {
		s.log.Error("book-preview: ScrapeMetadata failed", "slug", slug, "url", bookURL, "err", err)
		http.Error(w, fmt.Sprintf(`{"error":"metadata scrape failed: %s"}`, err.Error()), http.StatusBadGateway)
		return
	}

	// Scrape live chapter list.
	chapters, err := s.novel.ScrapeChapterList(ctx, bookURL)
	if err != nil {
		s.log.Error("book-preview: ScrapeChapterList failed", "slug", slug, "url", bookURL, "err", err)
		// Return partial response with metadata only — chapters are non-critical.
		chapters = []scraper.ChapterRef{}
	}

	// If the book was not already in the library, persist the metadata and
	// chapter list skeleton to PocketBase now so that subsequent visits load
	// from the local store rather than scraping live again.  Chapter text is
	// NOT fetched here — that still requires an explicit scrape job.
	if !inLib {
		go func() {
			bgCtx := context.Background()
			if werr := s.store.WriteMetadata(bgCtx, meta); werr != nil {
				s.log.Warn("book-preview: WriteMetadata failed (non-fatal)", "slug", slug, "err", werr)
			}
			if len(chapters) > 0 {
				if werr := s.store.WriteChapterRefs(bgCtx, slug, chapters); werr != nil {
					s.log.Warn("book-preview: WriteChapterRefs failed (non-fatal)", "slug", slug, "err", werr)
				}
			}
			s.log.Info("book-preview: metadata+chapter list persisted", "slug", slug, "chapters", len(chapters))
		}()
		inLib = true // will be true by the time the client navigates back
	}

	resp := BookPreviewResponse{
		InLib:    inLib,
		Meta:     meta,
		Chapters: chapters,
	}

	w.Header().Set("Content-Type", "application/json")
	_ = json.NewEncoder(w).Encode(resp)
}

// ChapterPreviewResponse is the JSON response for /api/chapter-text-preview/{slug}/{n}.
type ChapterPreviewResponse struct {
	Slug   string `json:"slug"`
	Number int    `json:"number"`
	Title  string `json:"title"`
	Text   string `json:"text"` // plain text (markdown stripped)
	URL    string `json:"url"`
}

// handleChapterTextPreview handles GET /api/chapter-text-preview/{slug}/{n}.
//
// It scrapes a single chapter from novelfire.net live without storing anything.
// The chapter URL is determined from either:
//   - the "chapter_url" query param (preferred — used when the UI knows it from
//     a prior book-preview call), or
//   - a best-effort construction: {novelFireBase}/book/{slug}/chapter-{n}
//
// Returns plain text (markdown stripped) suitable for TTS or display.
func (s *Server) handleChapterTextPreview(w http.ResponseWriter, r *http.Request) {
	slug := r.PathValue("slug")
	nStr := r.PathValue("n")
	n, err := strconv.Atoi(nStr)
	if err != nil || n < 1 || slug == "" {
		http.Error(w, `{"error":"invalid params"}`, http.StatusBadRequest)
		return
	}

	// Chapter URL: prefer explicit query param.
	chapterURL := r.URL.Query().Get("chapter_url")
	if chapterURL == "" {
		chapterURL = fmt.Sprintf("%s/book/%s/chapter-%d", novelFireBase, slug, n)
	}

	title := r.URL.Query().Get("title")

	ref := scraper.ChapterRef{
		Number: n,
		Title:  title,
		URL:    chapterURL,
	}

	chapter, err := s.novel.ScrapeChapterText(r.Context(), ref)
	if err != nil {
		s.log.Error("chapter-text-preview: ScrapeChapterText failed",
			"slug", slug, "n", n, "url", chapterURL, "err", err)
		http.Error(w, fmt.Sprintf(`{"error":"chapter scrape failed: %s"}`, err.Error()), http.StatusBadGateway)
		return
	}

	resp := ChapterPreviewResponse{
		Slug:   slug,
		Number: n,
		Title:  chapter.Ref.Title,
		Text:   stripMarkdown(chapter.Text),
		URL:    chapterURL,
	}

	w.Header().Set("Content-Type", "application/json")
	_ = json.NewEncoder(w).Encode(resp)
}