Merge pull request 'fix: extract title from h1 or URL slug when page title starts with #' (#5) from feat/title-h1-fallback into main

Reviewed-on: #5

.dockerignore

@@ -0,0 +1,5 @@
+.git
+.github
+*.md
+library/
+*_test.go

.github/workflows/release.yaml

@@ -1,4 +1,4 @@
-name: Build and Release
+name: Release
 
 on:
   push:
@@ -6,185 +6,32 @@ on:
       - 'v*'
 
 jobs:
-  build-and-release-linux:
+  release:
-    name: Build and Release for Linux
+    name: Build and Release
     runs-on: [self-hosted, linux, arm64]
 
     steps:
-      - name: Checkout code
+      - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Set up Go
-        uses: actions/setup-go@v3
+        uses: actions/setup-go@v5
         with:
           go-version: '1.22.3'
 
-      - name: Build for Linux
+      - name: Build
-        run: go build -o myapp
+        run: make all
 
-      - name: Create Release
+      - name: Release
-        id: create_release
+        uses: softprops/action-gh-release@v2
-        uses: actions/create-release@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
           tag_name: ${{ github.ref_name }}
-          release_name: Release ${{ github.ref_name }}
+          name: ${{ github.ref_name }}
-          body: Release notes for ${{ github.ref_name }}
+          files: build/*
-          draft: false
+          generate_release_notes: true
-          prerelease: false
-
-      - name: Save upload_url
-        run: echo "UPLOAD_URL=${{ steps.create_release.outputs.upload_url }}" > upload_url.txt
-        shell: bash
-
-      - name: Upload upload_url artifact
-        uses: actions/upload-artifact@v3
-        with:
-          name: upload_url
-          path: upload_url.txt
-
-  build-and-release-windows:
-    name: Build and Release for Windows
-    runs-on: windows-latest
-    needs: build-and-release-linux
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-
-      - name: Set up Go
-        uses: actions/setup-go@v3
-        with:
-          go-version: '1.22.3'
-
-      - name: Build for Windows
-        run: go build -o myapp.exe
-
-      - name: Download upload_url artifact
-        uses: actions/download-artifact@v3
-        with:
-          name: upload_url
-          path: .
-
-      - name: Read upload_url
-        id: read_upload_url
-        run: |
-          UPLOAD_URL=$(cat upload_url.txt)
-          echo "::set-output name=upload_url::$UPLOAD_URL"
-        shell: bash
-
-      - name: Debug upload_url
-        run: | 
-            echo "Upload URL: ${{ steps.read_upload_url.outputs.upload_url }}"
-
-      - name: Upload Windows Release Asset
-        if: startsWith(github.ref, 'refs/tags/')
-        uses: actions/upload-release-asset@v1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.read_upload_url.outputs.upload_url }}
-          asset_path: ./myapp.exe
-          asset_name: myapp-windows.exe
-          asset_content_type: application/octet-stream
 
-
+      - name: Clean up
-# name: Yoink Release
+        if: always()
-
+        run: make clean
-# on:
-#   push:
-#     tags:
-#       - 'v*'
-
-# jobs:
-#   yoink-release:
-#     name: Yoink Build and Release
-#     runs-on: [self-hosted, linux, arm64]
-
-#     steps:
-#       - name: Checkout
-#         uses: actions/checkout@v3
-
-#       - name: Setup Go
-#         uses: actions/setup-go@v4
-#         with:
-#           go-version: '1.22.3'
-
-#       - name: Linux Build
-#         run: go build -o yoink
-
-#       - name: Create Release
-#         id: create_release
-#         uses: actions/create-release@v1
-#         env:
-#           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-#         with:
-#           tag_name: ${{ github.ref_name }}
-#           release_name: Release ${{ github.ref_name }}
-#           body: Release notes for ${{ github.ref_name }}
-#           draft: false
-#           prerelease: false
-
-#       - name: Save upload_url
-#         run: echo "UPLOAD_URL=${{ steps.create_release.outputs.upload_url }}" > upload_url.txt
-#         shell: bash
-
-#       - name: Upload upload_url artifact
-#         uses: actions/upload-artifact@v3
-#         with:
-#           name: upload_url.txt
-#           path: ./upload_url.txt
-
-#       - name: Upload Linux Release Asset
-#         uses: actions/upload-release-asset@v1
-#         env:
-#           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-#         with:
-#           upload_url: ${{ steps.create_release.outputs.upload_url }}
-#           asset_path: ./yoink
-#           asset_name: yoink
-#           asset_content_type: application/x-executable
-
-#   build-and-release-win:
-#     runs-on: windows-latest
-#     needs: yoink-release
-    
-#     steps:
-#       - name: Checkout
-#         uses: actions/checkout@v3
-
-#       - name: Setup Go
-#         uses: actions/setup-go@v4
-#         with:
-#           go-version: '1.22.3'
-
-#       - name: Windows Build
-#         run: go build -o yoink.exe
-
-#       - name: Download upload_url artifact
-#         uses: actions/download-artifact@v3
-#         with:
-#           name: upload_url.txt
-#           path: .
-
-#       - name: Read upload_url artifact
-#         id: read_upload_url
-#         run: |
-#           UPLOAD_URL=$(cat upload_url.txt)
-#           echo "::set-output name=upload_url::$UPLOAD_URL"
-#         shell: bash
-
-#       - name: Debug upload_url
-#         run: echo ${{ steps.read_upload_url.outputs.upload_url }}
-#         shell: bash  
-
-#       - name: Upload Windows Release Asset
-#         uses: actions/upload-release-asset@v1
-#         env:
-#           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-#         with:
-#           upload_url: ${{ steps.read_upload_url.outputs.upload_url }}
-#           asset_path: ./yoink.exe
-#           asset_name: yoink.exe
-#           asset_content_type: application/x-executable

.gitignore

@@ -19,4 +19,15 @@ go.work
 go.work.sum
 
 # env file
-.env
+.env
+
+# Built binary
+yoink
+yoink.exe
+
+# Comic library (downloaded content)
+library/
+
+# IDE
+.vscode/
+.idea/

Dockerfile

@@ -0,0 +1,37 @@
+# ── Build stage ────────────────────────────────────────────────────────────
+FROM mcr.microsoft.com/oss/go/microsoft/golang:1.22-bullseye AS builder
+
+WORKDIR /app
+
+# Restore modules in a separate layer so it's cached until go.mod/go.sum change
+COPY go.mod go.sum ./
+RUN go mod download && go mod verify
+
+# Copy source and build a fully static binary
+COPY . .
+RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 \
+    go build -ldflags="-s -w" -trimpath -o yoink .
+
+# ── Runtime stage ──────────────────────────────────────────────────────────
+# distroless/base-debian12:nonroot — minimal attack surface, non-root by default
+FROM gcr.io/distroless/base-debian12:nonroot
+
+LABEL org.opencontainers.image.title="yoink" \
+      org.opencontainers.image.description="Comic downloader web UI" \
+      org.opencontainers.image.source="https://git.brizzle.dev/bryan/yoink-go"
+
+WORKDIR /app
+
+COPY --from=builder --chown=nonroot:nonroot /app/yoink .
+
+ENV YOINK_LIBRARY=/library
+
+VOLUME ["/library"]
+EXPOSE 8080
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=5s --retries=3 \
+    CMD ["/app/yoink", "healthcheck"]
+
+USER nonroot
+
+CMD ["/app/yoink", "serve"]

Makefile

@@ -1,7 +1,10 @@
 BIN := yoink
 BUILD_DIR := build
+REGISTRY := git.brizzle.dev/bryan/yoink-go
+VERSION ?= $(shell git describe --tags --always --dirty)
+NOTES ?= ""
 
-.PHONY: all windows linux darwin clean
+.PHONY: all windows linux darwin clean docker-build docker-push tag gitea-release release
 
 all: windows linux darwin
 
@@ -16,5 +19,38 @@ darwin:
 	GOOS=darwin GOARCH=amd64 go build -o $(BUILD_DIR)/$(BIN)-darwin-amd64
 	GOOS=darwin GOARCH=arm64 go build -o $(BUILD_DIR)/$(BIN)-darwin-arm64
 
+docker-build:
+	podman build --format docker \
+		-t $(REGISTRY):$(VERSION) \
+		-t $(REGISTRY):latest \
+		.
+
+docker-push: docker-build
+	podman push $(REGISTRY):$(VERSION)
+	podman push $(REGISTRY):latest
+
+tag:
+	@if [ -z "$(VERSION)" ]; then echo "Usage: make tag VERSION=1.2.0"; exit 1; fi
+	git tag $(VERSION)
+	git push origin $(VERSION)
+
+gitea-release:
+	tea release create \
+		--tag $(VERSION) \
+		--title "$(VERSION)" \
+		--note $(NOTES) \
+		--asset $(BUILD_DIR)/$(BIN)-windows-amd64.exe \
+		--asset $(BUILD_DIR)/$(BIN)-linux-amd64 \
+		--asset $(BUILD_DIR)/$(BIN)-linux-arm64 \
+		--asset $(BUILD_DIR)/$(BIN)-darwin-amd64 \
+		--asset $(BUILD_DIR)/$(BIN)-darwin-arm64
+
+release:
+	@if [ -z "$(VERSION)" ]; then echo "Usage: make release VERSION=1.3.0 NOTES='...'"; exit 1; fi
+	$(MAKE) tag VERSION=$(VERSION)
+	$(MAKE) clean all
+	$(MAKE) gitea-release VERSION=$(VERSION) NOTES=$(NOTES)
+	$(MAKE) docker-push VERSION=$(VERSION)
+
 clean:
 	rm -rf $(BUILD_DIR)

README.md

@@ -1,6 +1,6 @@
 # yoink
 
-A CLI tool for downloading comics from readallcomics.com and packaging them as `.cbz` archives.
+A tool for downloading comics from readallcomics.com and packaging them as `.cbz` archives. Available as a CLI command or a self-hosted web application. The web UI also lets you package local image folders into `.cbz` archives directly from your browser.
 
 ## How it works
 
@@ -9,17 +9,33 @@ A CLI tool for downloading comics from readallcomics.com and packaging them as `
 3. Packages the images into a `.cbz` (Comic Book Zip) archive
 4. Cleans up downloaded images, keeping only the cover (`001`)
 
+---
+
 ## Installation
 
-Build from source (requires Go 1.22.3+):
+### From source
+
+Requires Go 1.22.3+:
 
 ```shell
 go build -o yoink
 ```
 
-Pre-built binaries for Linux (arm64) and Windows are available on the [releases page](../../releases).
+### Pre-built binaries
 
-## Usage
+Pre-built binaries for Linux (arm64) and Windows are available on the [releases page](https://git.brizzle.dev/bryan/yoink-go/releases).
+
+### Docker
+
+```shell
+docker pull git.brizzle.dev/bryan/yoink-go:latest
+```
+
+---
+
+## CLI
+
+Download a single comic issue:
 
 ```shell
 yoink <url>
@@ -37,16 +53,94 @@ The comic title is extracted from the page and used to name the archive. Output
 <library>/<Title>/<Title>.cbz
 ```
 
+---
+
+## Web UI
+
+Yoink includes a self-hosted web interface for browsing and downloading comics from your browser.
+
+![Yoink Web UI](Screenshot_01.png)
+
+### Running directly
+
+```shell
+yoink serve
+```
+
+By default the server listens on port `8080`. Use the `-p` flag to change it:
+
+```shell
+yoink serve -p 3000
+```
+
+### Running with Docker
+
+A `docker-compose.yml` is included for quick deployment:
+
+```shell
+docker compose up -d
+```
+
+Or with Podman:
+
+```shell
+podman compose up -d
+```
+
+The web UI is then available at `http://localhost:8080`.
+
+### Features
+
+- **Download queue** — paste a comic URL into the input bar and track download progress in real time
+- **Local packaging** — drag and drop a folder of images (or use the file picker) to package them as a `.cbz` archive and add it to your library without downloading anything
+- **Library grid** — browse your comics as a 150×300 cover grid with title-initial placeholders for missing covers
+- **Filter & sort** — filter by title and sort by newest, oldest, A–Z, or Z–A
+- **One-click download** — click any cover to download the `.cbz` archive directly
+
+#### Packaging local images
+
+![Local packaging panel](Screenshot_02.png)
+
+Click the upload icon (↑) in the header to open the packaging panel. Enter a title, then either:
+
+- **Drag and drop** a folder or image files onto the drop zone
+- **Select folder** to pick an entire directory at once
+- **Select files** to pick individual images
+
+Images are sorted by filename, the first image is used as the cover, and the result is saved to your library as `<Title>/<Title>.cbz`.
+
+### Library volume
+
+Downloaded comics are stored at the path set by `YOINK_LIBRARY`. When using Docker, mount this as a volume to persist your library across container restarts:
+
+```yaml
+# docker-compose.yml
+services:
+  yoink:
+    image: git.brizzle.dev/bryan/yoink-go:latest
+    ports:
+      - "8080:8080"
+    volumes:
+      - ./library:/library
+    environment:
+      - YOINK_LIBRARY=/library
+    restart: unless-stopped
+```
+
+---
+
 ## Configuration
 
-| Variable        | Default      | Description                          |
+| Variable        | Default    | Description                       |
-|-----------------|--------------|--------------------------------------|
+|-----------------|------------|-----------------------------------|
-| `YOINK_LIBRARY` | `~/.yoink`   | Directory where comics are stored    |
+| `YOINK_LIBRARY` | `~/.yoink` | Directory where comics are stored |
 
 ```shell
 YOINK_LIBRARY=/mnt/media/comics yoink https://readallcomics.com/some-comic-001/
 ```
 
+---
+
 ## Dependencies
 
 - [goquery](https://github.com/PuerkitoBio/goquery) — HTML parsing

cli/healthcheck.go

@@ -0,0 +1,28 @@
+package cli
+
+import (
+	"fmt"
+	"net/http"
+	"os"
+
+	"github.com/spf13/cobra"
+)
+
+var healthcheckCmd = &cobra.Command{
+	Use:    "healthcheck",
+	Short:  "Check if the web server is running (used by Docker HEALTHCHECK)",
+	Args:   cobra.NoArgs,
+	Hidden: true,
+	Run: func(cmd *cobra.Command, args []string) {
+		port, _ := cmd.Flags().GetString("port")
+		resp, err := http.Get(fmt.Sprintf("http://localhost:%s/health", port))
+		if err != nil || resp.StatusCode != http.StatusOK {
+			os.Exit(1)
+		}
+	},
+}
+
+func init() {
+	healthcheckCmd.Flags().StringP("port", "p", "8080", "Port the server is listening on")
+	cli.AddCommand(healthcheckCmd)
+}

cli/serve.go

@@ -0,0 +1,36 @@
+package cli
+
+import (
+	"fmt"
+	"log"
+	"os"
+	"path/filepath"
+
+	"github.com/spf13/cobra"
+	"yoink/web"
+)
+
+var serveCmd = &cobra.Command{
+	Use:   "serve",
+	Short: "Start the Yoink web UI",
+	Args:  cobra.NoArgs,
+	Run: func(cmd *cobra.Command, args []string) {
+		library, ok := os.LookupEnv("YOINK_LIBRARY")
+		if !ok {
+			userHome, _ := os.UserHomeDir()
+			library = filepath.Join(userHome, ".yoink")
+		}
+
+		port, _ := cmd.Flags().GetString("port")
+		addr := fmt.Sprintf(":%s", port)
+
+		if err := web.Listen(addr, library); err != nil {
+			log.Fatal(err)
+		}
+	},
+}
+
+func init() {
+	serveCmd.Flags().StringP("port", "p", "8080", "Port to listen on")
+	cli.AddCommand(serveCmd)
+}

comic/archive_test.go

@@ -0,0 +1,110 @@
+package comic
+
+import (
+	"archive/zip"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestArchiveError(t *testing.T) {
+	err := ArchiveError{Message: "archive failed", Code: 1}
+	if err.Error() != "archive failed" {
+		t.Errorf("Error() = %q, want %q", err.Error(), "archive failed")
+	}
+}
+
+func TestArchive(t *testing.T) {
+	t.Run("creates cbz with image files", func(t *testing.T) {
+		tmpDir := t.TempDir()
+		title := "TestComic"
+		comicDir := filepath.Join(tmpDir, title)
+		os.MkdirAll(comicDir, os.ModePerm)
+
+		// Create fake image files
+		for _, name := range []string{"TestComic 001.jpg", "TestComic 002.jpg", "TestComic 003.png"} {
+			os.WriteFile(filepath.Join(comicDir, name), []byte("fake image"), 0644)
+		}
+
+		c := &Comic{
+			Title:       title,
+			LibraryPath: tmpDir,
+		}
+
+		err := c.Archive()
+		if err != nil {
+			t.Fatalf("Archive() unexpected error: %v", err)
+		}
+
+		archivePath := filepath.Join(comicDir, title+".cbz")
+		if _, err := os.Stat(archivePath); os.IsNotExist(err) {
+			t.Fatalf("expected archive %s to exist", archivePath)
+		}
+
+		// Verify the zip contains the image files
+		reader, err := zip.OpenReader(archivePath)
+		if err != nil {
+			t.Fatalf("failed to open archive: %v", err)
+		}
+		defer reader.Close()
+
+		if len(reader.File) != 3 {
+			t.Errorf("archive contains %d files, want 3", len(reader.File))
+		}
+	})
+
+	t.Run("excludes non-image files from archive", func(t *testing.T) {
+		tmpDir := t.TempDir()
+		title := "TestComic"
+		comicDir := filepath.Join(tmpDir, title)
+		os.MkdirAll(comicDir, os.ModePerm)
+
+		// Create mixed files
+		os.WriteFile(filepath.Join(comicDir, "page-001.jpg"), []byte("image"), 0644)
+		os.WriteFile(filepath.Join(comicDir, "readme.txt"), []byte("text"), 0644)
+		os.WriteFile(filepath.Join(comicDir, "data.json"), []byte("json"), 0644)
+
+		c := &Comic{
+			Title:       title,
+			LibraryPath: tmpDir,
+		}
+
+		err := c.Archive()
+		if err != nil {
+			t.Fatalf("Archive() unexpected error: %v", err)
+		}
+
+		archivePath := filepath.Join(comicDir, title+".cbz")
+		reader, err := zip.OpenReader(archivePath)
+		if err != nil {
+			t.Fatalf("failed to open archive: %v", err)
+		}
+		defer reader.Close()
+
+		if len(reader.File) != 1 {
+			t.Errorf("archive contains %d files, want 1 (only .jpg)", len(reader.File))
+		}
+	})
+
+	t.Run("handles empty directory", func(t *testing.T) {
+		tmpDir := t.TempDir()
+		title := "EmptyComic"
+		comicDir := filepath.Join(tmpDir, title)
+		os.MkdirAll(comicDir, os.ModePerm)
+
+		c := &Comic{
+			Title:       title,
+			LibraryPath: tmpDir,
+		}
+
+		err := c.Archive()
+		if err != nil {
+			t.Fatalf("Archive() unexpected error: %v", err)
+		}
+
+		archivePath := filepath.Join(comicDir, title+".cbz")
+		if _, err := os.Stat(archivePath); os.IsNotExist(err) {
+			t.Fatalf("expected archive %s to exist even if empty", archivePath)
+		}
+	})
+}

comic/cleanup_test.go

@@ -0,0 +1,93 @@
+package comic
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestCleanup(t *testing.T) {
+	t.Run("keeps cover image 001 and removes others", func(t *testing.T) {
+		tmpDir := t.TempDir()
+		title := "TestComic"
+		comicDir := filepath.Join(tmpDir, title)
+		os.MkdirAll(comicDir, os.ModePerm)
+
+		files := map[string]bool{
+			"TestComic 001.jpg": true,  // should be kept
+			"TestComic 002.jpg": false, // should be removed
+			"TestComic 003.jpg": false, // should be removed
+		}
+
+		for name := range files {
+			os.WriteFile(filepath.Join(comicDir, name), []byte("fake"), 0644)
+		}
+
+		c := &Comic{
+			Title:       title,
+			LibraryPath: tmpDir,
+		}
+
+		err := c.Cleanup()
+		if err != nil {
+			t.Fatalf("Cleanup() unexpected error: %v", err)
+		}
+
+		for name, shouldExist := range files {
+			path := filepath.Join(comicDir, name)
+			_, err := os.Stat(path)
+			exists := !os.IsNotExist(err)
+
+			if shouldExist && !exists {
+				t.Errorf("expected %s to be kept, but it was removed", name)
+			}
+			if !shouldExist && exists {
+				t.Errorf("expected %s to be removed, but it still exists", name)
+			}
+		}
+	})
+
+	t.Run("keeps non-image files", func(t *testing.T) {
+		tmpDir := t.TempDir()
+		title := "TestComic"
+		comicDir := filepath.Join(tmpDir, title)
+		os.MkdirAll(comicDir, os.ModePerm)
+
+		os.WriteFile(filepath.Join(comicDir, "TestComic.cbz"), []byte("archive"), 0644)
+		os.WriteFile(filepath.Join(comicDir, "metadata.json"), []byte("data"), 0644)
+
+		c := &Comic{
+			Title:       title,
+			LibraryPath: tmpDir,
+		}
+
+		err := c.Cleanup()
+		if err != nil {
+			t.Fatalf("Cleanup() unexpected error: %v", err)
+		}
+
+		for _, name := range []string{"TestComic.cbz", "metadata.json"} {
+			path := filepath.Join(comicDir, name)
+			if _, err := os.Stat(path); os.IsNotExist(err) {
+				t.Errorf("expected non-image file %s to be kept", name)
+			}
+		}
+	})
+
+	t.Run("handles empty directory", func(t *testing.T) {
+		tmpDir := t.TempDir()
+		title := "EmptyComic"
+		comicDir := filepath.Join(tmpDir, title)
+		os.MkdirAll(comicDir, os.ModePerm)
+
+		c := &Comic{
+			Title:       title,
+			LibraryPath: tmpDir,
+		}
+
+		err := c.Cleanup()
+		if err != nil {
+			t.Fatalf("Cleanup() unexpected error for empty dir: %v", err)
+		}
+	})
+}

comic/comic.go

@@ -26,21 +26,52 @@ type Comic struct {
 // Returns the extracted title as a string.
 func extractTitleFromMarkup(c Comic) string {
 	yearFormat := `^(.*?)\s+\(\d{4}(?:\s+.+)?\)`
-	selection := c.Markup.Find("title")
-
-	if selection.Length() == 0 {
-		return "Untitled"
-	}
-
-	content := selection.First().Text()
 	regex := regexp.MustCompile(yearFormat)
-	matches := regex.FindStringSubmatch(content)
 
-	if len(matches) != 2 {
+	extractFrom := func(text string) string {
-		return "Untitled"
+		matches := regex.FindStringSubmatch(text)
+		if len(matches) != 2 {
+			return ""
+		}
+		return strings.ReplaceAll(matches[1], ":", "")
 	}
 
-	return strings.ReplaceAll(matches[1], ":", "")
+	title := extractFrom(c.Markup.Find("title").First().Text())
+
+	if strings.HasPrefix(title, "#") {
+		if h1 := extractFrom(c.Markup.Find("h1").First().Text()); h1 != "" && !strings.HasPrefix(h1, "#") {
+			return h1
+		}
+		if slug := titleFromSlug(c.URL); slug != "" {
+			return slug
+		}
+	}
+
+	if title != "" {
+		return title
+	}
+
+	return "Untitled"
+}
+
+// titleFromSlug derives a comic title from the last path segment of a URL.
+// It strips a trailing year (-YYYY), replaces hyphens with spaces, and title-cases the result.
+func titleFromSlug(url string) string {
+	slug := strings.TrimRight(url, "/")
+	if i := strings.LastIndex(slug, "/"); i >= 0 {
+		slug = slug[i+1:]
+	}
+	slug = regexp.MustCompile(`-\d{4}$`).ReplaceAllString(slug, "")
+	if slug == "" {
+		return ""
+	}
+	words := strings.Split(slug, "-")
+	for i, w := range words {
+		if len(w) > 0 {
+			words[i] = strings.ToUpper(w[:1]) + w[1:]
+		}
+	}
+	return strings.Join(words, " ")
 }
 
 // NewComic creates a new Comic instance from the provided URL and library path.
@@ -61,13 +92,21 @@ func NewComic(
 		LibraryPath: libraryPath,
 	}
 
-	go Markup(c.URL, markupChannel)
+	if strings.Contains(url, "batcave.biz") {
+		go BatcaveBizMarkup(url, markupChannel)
+	} else {
+		go Markup(url, markupChannel)
+	}
 
 	markup := <-markupChannel
 	c.Markup = markup
 	c.Title = extractTitleFromMarkup(*c)
 
-	go ParseImageLinks(markup, imageChannel)
+	if strings.Contains(url, "batcave.biz") {
+		go ParseBatcaveBizImageLinks(markup, imageChannel)
+	} else {
+		go ParseImageLinks(markup, imageChannel)
+	}
 	links := <-imageChannel
 
 	c.Filelist = links

comic/comic_test.go

@@ -0,0 +1,170 @@
+package comic
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/PuerkitoBio/goquery"
+)
+
+func newDocFromHTML(html string) *goquery.Document {
+	doc, _ := goquery.NewDocumentFromReader(strings.NewReader(html))
+	return doc
+}
+
+func TestExtractTitleFromMarkup(t *testing.T) {
+	tests := []struct {
+		name     string
+		html     string
+		url      string
+		expected string
+	}{
+		{
+			name:     "standard title with year",
+			html:     `<html><head><title>Ultraman X Avengers 001 (2024)</title></head></html>`,
+			expected: "Ultraman X Avengers 001",
+		},
+		{
+			name:     "title with year and extra text",
+			html:     `<html><head><title>Batman 042 (2023 Digital)</title></head></html>`,
+			expected: "Batman 042",
+		},
+		{
+			name:     "title with colon removed",
+			html:     `<html><head><title>Spider-Man: No Way Home 001 (2022)</title></head></html>`,
+			expected: "Spider-Man No Way Home 001",
+		},
+		{
+			name:     "no title tag",
+			html:     `<html><head></head></html>`,
+			expected: "Untitled",
+		},
+		{
+			name:     "title without year pattern",
+			html:     `<html><head><title>Some Random Page</title></head></html>`,
+			expected: "Untitled",
+		},
+		{
+			name:     "empty title",
+			html:     `<html><head><title></title></head></html>`,
+			expected: "Untitled",
+		},
+		{
+			name:     "title starts with # falls back to h1",
+			html:     `<html><head><title>#018 (2026)</title></head><body><h1>Absolute Batman #018 (2026)</h1></body></html>`,
+			expected: "Absolute Batman #018",
+		},
+		{
+			name:     "title starts with # but h1 also starts with #, falls back to slug",
+			html:     `<html><head><title>#018 (2026)</title></head><body><h1>#018 (2026)</h1></body></html>`,
+			url:      "https://readallcomics.com/absolute-batman-018-2026/",
+			expected: "Absolute Batman 018",
+		},
+		{
+			name:     "title starts with # falls back to slug when no h1",
+			html:     `<html><head><title>#018 (2026)</title></head></html>`,
+			url:      "https://readallcomics.com/absolute-batman-018-2026/",
+			expected: "Absolute Batman 018",
+		},
+		{
+			name:     "title starts with # no h1 no url",
+			html:     `<html><head><title>#018 (2026)</title></head></html>`,
+			expected: "#018",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			doc := newDocFromHTML(tt.html)
+			c := Comic{Markup: doc, URL: tt.url}
+			result := extractTitleFromMarkup(c)
+			if result != tt.expected {
+				t.Errorf("extractTitleFromMarkup() = %q, want %q", result, tt.expected)
+			}
+		})
+	}
+}
+
+func TestTitleFromSlug(t *testing.T) {
+	tests := []struct {
+		name     string
+		url      string
+		expected string
+	}{
+		{
+			name:     "standard comic URL",
+			url:      "https://readallcomics.com/absolute-batman-018-2026/",
+			expected: "Absolute Batman 018",
+		},
+		{
+			name:     "no trailing slash",
+			url:      "https://readallcomics.com/absolute-batman-018-2026",
+			expected: "Absolute Batman 018",
+		},
+		{
+			name:     "no year in slug",
+			url:      "https://readallcomics.com/absolute-batman-018/",
+			expected: "Absolute Batman 018",
+		},
+		{
+			name:     "single word slug",
+			url:      "https://readallcomics.com/batman/",
+			expected: "Batman",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := titleFromSlug(tt.url)
+			if result != tt.expected {
+				t.Errorf("titleFromSlug() = %q, want %q", result, tt.expected)
+			}
+		})
+	}
+}
+
+func TestCover(t *testing.T) {
+	tests := []struct {
+		name        string
+		filelist    []string
+		wantSuffix  string
+		expectErr   bool
+	}{
+		{
+			name:       "finds cover ending in 001.jpg",
+			filelist:   []string{"https://example.com/image-002.jpg", "https://example.com/image-001.jpg", "https://example.com/image-003.jpg"},
+			wantSuffix: "image-001.jpg",
+		},
+		{
+			name:       "finds cover ending in 000.jpg",
+			filelist:   []string{"https://example.com/image-000.jpg", "https://example.com/image-001.jpg"},
+			wantSuffix: "image-000.jpg",
+		},
+		{
+			name:      "returns error when no cover found",
+			filelist:  []string{"https://example.com/image-002.jpg", "https://example.com/image-003.jpg"},
+			expectErr: true,
+		},
+		{
+			name:      "returns error for empty filelist",
+			filelist:  []string{},
+			expectErr: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			c := &Comic{Filelist: tt.filelist}
+			cover, err := c.Cover()
+			if tt.expectErr && err == nil {
+				t.Error("Cover() expected error, got nil")
+			}
+			if !tt.expectErr && err != nil {
+				t.Errorf("Cover() unexpected error: %v", err)
+			}
+			if tt.wantSuffix != "" && !strings.HasSuffix(cover, tt.wantSuffix) {
+				t.Errorf("Cover() = %q, want path ending in %q", cover, tt.wantSuffix)
+			}
+		})
+	}
+}

comic/download_test.go

@@ -0,0 +1,145 @@
+package comic
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestComicDownloadError(t *testing.T) {
+	err := ComicDownloadError{Message: "download failed", Code: 1}
+	if err.Error() != "download failed" {
+		t.Errorf("Error() = %q, want %q", err.Error(), "download failed")
+	}
+}
+
+func TestHandleRequest(t *testing.T) {
+	t.Run("successful request", func(t *testing.T) {
+		server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			if r.Header.Get("User-Agent") == "" {
+				t.Error("expected User-Agent header to be set")
+			}
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte("image data"))
+		}))
+		defer server.Close()
+
+		resp, err := handleRequest(server.URL)
+		if err != nil {
+			t.Fatalf("handleRequest() unexpected error: %v", err)
+		}
+		defer resp.Body.Close()
+
+		if resp.StatusCode != http.StatusOK {
+			t.Errorf("handleRequest() status = %d, want %d", resp.StatusCode, http.StatusOK)
+		}
+	})
+
+	t.Run("non-200 response", func(t *testing.T) {
+		server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.WriteHeader(http.StatusNotFound)
+		}))
+		defer server.Close()
+
+		_, err := handleRequest(server.URL)
+		if err == nil {
+			t.Error("handleRequest() expected error for 404 response, got nil")
+		}
+	})
+
+	t.Run("invalid URL", func(t *testing.T) {
+		_, err := handleRequest("http://invalid.localhost:0/bad")
+		if err == nil {
+			t.Error("handleRequest() expected error for invalid URL, got nil")
+		}
+	})
+}
+
+func TestDownloadFile(t *testing.T) {
+	t.Run("successful download", func(t *testing.T) {
+		server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte("fake image content"))
+		}))
+		defer server.Close()
+
+		tmpDir := t.TempDir()
+		c := &Comic{
+			Title:       "TestComic",
+			LibraryPath: tmpDir,
+		}
+
+		err := downloadFile(server.URL+"/image.jpg", 1, c)
+		if err != nil {
+			t.Fatalf("downloadFile() unexpected error: %v", err)
+		}
+
+		expectedPath := filepath.Join(tmpDir, "TestComic", "TestComic 001.jpg")
+		if _, err := os.Stat(expectedPath); os.IsNotExist(err) {
+			t.Errorf("expected file %s to exist", expectedPath)
+		}
+	})
+
+	t.Run("formats page number with leading zeros", func(t *testing.T) {
+		server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte("fake image content"))
+		}))
+		defer server.Close()
+
+		tmpDir := t.TempDir()
+		c := &Comic{
+			Title:       "TestComic",
+			LibraryPath: tmpDir,
+		}
+
+		err := downloadFile(server.URL+"/image.jpg", 42, c)
+		if err != nil {
+			t.Fatalf("downloadFile() unexpected error: %v", err)
+		}
+
+		expectedPath := filepath.Join(tmpDir, "TestComic", "TestComic 042.jpg")
+		if _, err := os.Stat(expectedPath); os.IsNotExist(err) {
+			t.Errorf("expected file %s to exist", expectedPath)
+		}
+	})
+
+	t.Run("server error returns error", func(t *testing.T) {
+		server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.WriteHeader(http.StatusInternalServerError)
+		}))
+		defer server.Close()
+
+		tmpDir := t.TempDir()
+		c := &Comic{
+			Title:       "TestComic",
+			LibraryPath: tmpDir,
+		}
+
+		err := downloadFile(server.URL+"/image.jpg", 1, c)
+		if err == nil {
+			t.Error("downloadFile() expected error for server error, got nil")
+		}
+	})
+
+	t.Run("empty response body returns error", func(t *testing.T) {
+		server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.WriteHeader(http.StatusOK)
+			// write nothing
+		}))
+		defer server.Close()
+
+		tmpDir := t.TempDir()
+		c := &Comic{
+			Title:       "TestComic",
+			LibraryPath: tmpDir,
+		}
+
+		err := downloadFile(server.URL+"/image.jpg", 1, c)
+		if err == nil {
+			t.Error("downloadFile() expected error for empty body, got nil")
+		}
+	})
+}

comic/parser.go

@@ -3,6 +3,9 @@ package comic
 import (
 	"io"
 	"net/http"
+	"net/http/cookiejar"
+	"net/url"
+	"regexp"
 	"strings"
 
 	"github.com/PuerkitoBio/goquery"
@@ -47,6 +50,143 @@ func Markup(url string, c chan *goquery.Document) *goquery.Document {
 	return markup
 }
 
+func BatcaveBizMarkup(referer string, c chan *goquery.Document) *goquery.Document {
+	jar, _ := cookiejar.New(nil)
+	client := &http.Client{
+		Jar: jar,
+		CheckRedirect: func(req *http.Request, via []*http.Request) error {
+			return nil
+		},
+	}
+
+	headers := map[string]string{
+		"User-Agent":      "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
+		"Accept-Language": "en-US,en;q=0.9",
+		"Accept":          "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
+	}
+
+	// GET the challange page to obtain cookies and any necessary tokens
+	req, err := http.NewRequest("GET", referer, nil)
+	if err != nil {
+		if c != nil {
+			c <- &goquery.Document{}
+		}
+		return &goquery.Document{}
+	}
+	for k, v := range headers {
+		req.Header.Set(k, v)
+	}
+
+	res, err := client.Do(req)
+	if err != nil {
+		if c != nil {
+			c <- &goquery.Document{}
+		}
+		return &goquery.Document{}
+	}
+	defer res.Body.Close()
+
+	body, err := io.ReadAll(res.Body)
+	if err != nil {
+		if c != nil {
+			c <- &goquery.Document{}
+		}
+		return &goquery.Document{}
+	}
+
+	tokenRegex := regexp.MustCompile(`token:\s*"([^"]+)"`)
+	matches := tokenRegex.FindSubmatch(body)
+
+	if matches == nil {
+		//  no challenge, parse directly
+		doc, err := goquery.NewDocumentFromReader(strings.NewReader(string(body)))
+		if err != nil {
+			if c != nil {
+				c <- &goquery.Document{}
+			}
+			return &goquery.Document{}
+		}
+		if c != nil {
+			c <- doc
+		}
+		return doc
+	}
+
+	encodedToken := string(matches[1])
+	token, err := url.QueryUnescape(encodedToken)
+	if err != nil {
+		token = encodedToken
+	}
+
+	// Step 3: POST to /_v with fake browser metrics
+	params := url.Values{}
+	params.Set("token", token)
+	params.Set("mode", "modern")
+	params.Set("workTime", "462")
+	params.Set("iterations", "183")
+	params.Set("webdriver", "0")
+	params.Set("touch", "0")
+	params.Set("screen_w", "1920")
+	params.Set("screen_h", "1080")
+	params.Set("screen_cd", "24")
+
+	postReq, err := http.NewRequest("POST", "https://batcave.biz/_v", strings.NewReader(params.Encode()))
+	if err != nil {
+		if c != nil {
+			c <- &goquery.Document{}
+		}
+		return &goquery.Document{}
+	}
+	for k, v := range headers {
+		postReq.Header.Set(k, v)
+	}
+	postReq.Header.Set("Content-Type", "application/x-www-form-urlencoded")
+	postReq.Header.Set("Referer", referer)
+
+	postRes, err := client.Do(postReq)
+	if err != nil {
+		if c != nil {
+			c <- &goquery.Document{}
+		}
+		return &goquery.Document{}
+	}
+	defer postRes.Body.Close()
+	io.ReadAll(postRes.Body)
+
+	// GET the real page with the set cookie
+	realReq, err := http.NewRequest("GET", referer, nil)
+	if err != nil {
+		if c != nil {
+			c <- &goquery.Document{}
+		}
+		return &goquery.Document{}
+	}
+	for k, v := range headers {
+		realReq.Header.Set(k, v)
+	}
+
+	realRes, err := client.Do(realReq)
+	if err != nil {
+		if c != nil {
+			c <- &goquery.Document{}
+		}
+		return &goquery.Document{}
+	}
+	defer realRes.Body.Close()
+
+	doc, err := goquery.NewDocumentFromReader(realRes.Body)
+	if err != nil {
+		if c != nil {
+			c <- &goquery.Document{}
+		}
+		return &goquery.Document{}
+	}
+	if c != nil {
+		c <- doc
+	}
+	return doc
+}
+
 // ParseImageLinks parses a goquery document to extract image links.
 //
 // markup is the goquery document to parse for image links.
@@ -69,3 +209,55 @@ func ParseImageLinks(markup *goquery.Document, c chan []string) ([]string, error
 
 	return links, ImageParseError{Message: "No images found", Code: 1}
 }
+
+func ParseReadAllComicsLinks(markup *goquery.Document, c chan []string) ([]string, error) {
+	var links []string
+	markup.Find("img").Each(func(_ int, image *goquery.Selection) {
+		link, _ := image.Attr("src")
+		if !strings.Contains(link, "logo") && (strings.Contains(link, "bp.blogspot.com") || strings.Contains(link, "blogger.googleusercontent") || strings.Contains(link, "covers")) {
+			links = append(links, link)
+		}
+	})
+
+	c <- links
+
+	if len(links) > 0 {
+		return links, nil
+	}
+
+	return links, ImageParseError{Message: "No images found", Code: 1}
+}
+
+// ParseBatcaveBizImageLinks extracts image URLs from the __DATA__.images JavaScript
+// variable embedded in a batcave.biz page.
+func ParseBatcaveBizImageLinks(markup *goquery.Document, c chan []string) ([]string, error) {
+	var links []string
+
+	markup.Find("script").Each(func(_ int, s *goquery.Selection) {
+		text := s.Text()
+		if !strings.Contains(text, "__DATA__") {
+			return
+		}
+
+		arrayRegex := regexp.MustCompile(`"images"\s*:\s*\[([^\]]+)\]`)
+		arrayMatch := arrayRegex.FindStringSubmatch(text)
+		if len(arrayMatch) < 2 {
+			return
+		}
+
+		urlRegex := regexp.MustCompile(`"([^"]+)"`)
+		for _, m := range urlRegex.FindAllStringSubmatch(arrayMatch[1], -1) {
+			if len(m) >= 2 {
+				links = append(links, m[1])
+			}
+		}
+	})
+
+	c <- links
+
+	if len(links) > 0 {
+		return links, nil
+	}
+
+	return links, ImageParseError{Message: "No images found", Code: 1}
+}

comic/parser_test.go

@@ -0,0 +1,183 @@
+package comic
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/PuerkitoBio/goquery"
+)
+
+func TestParseBatcaveBizImageLinks(t *testing.T) {
+	tests := []struct {
+		name        string
+		html        string
+		expectCount int
+		expectErr   bool
+		expectURLs  []string
+	}{
+		{
+			name: "extracts images from __DATA__",
+			html: `<html><body><script>
+				var __DATA__ = {"images":["https://cdn.batcave.biz/img/001.jpg","https://cdn.batcave.biz/img/002.jpg"]};
+			</script></body></html>`,
+			expectCount: 2,
+			expectErr:   false,
+			expectURLs:  []string{"https://cdn.batcave.biz/img/001.jpg", "https://cdn.batcave.biz/img/002.jpg"},
+		},
+		{
+			name: "extracts images with spaces around colon and bracket",
+			html: `<html><body><script>
+				var __DATA__ = {"images" : [ "https://cdn.batcave.biz/img/001.jpg" ]};
+			</script></body></html>`,
+			expectCount: 1,
+			expectErr:   false,
+			expectURLs:  []string{"https://cdn.batcave.biz/img/001.jpg"},
+		},
+		{
+			name: "no __DATA__ script",
+			html: `<html><body><script>
+				var foo = "bar";
+			</script></body></html>`,
+			expectCount: 0,
+			expectErr:   true,
+		},
+		{
+			name: "__DATA__ present but no images key",
+			html: `<html><body><script>
+				var __DATA__ = {"title":"Nightwing"};
+			</script></body></html>`,
+			expectCount: 0,
+			expectErr:   true,
+		},
+		{
+			name:        "no script tags",
+			html:        `<html><body><p>nothing here</p></body></html>`,
+			expectCount: 0,
+			expectErr:   true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			doc, _ := goquery.NewDocumentFromReader(strings.NewReader(tt.html))
+			ch := make(chan []string, 1)
+
+			links, err := ParseBatcaveBizImageLinks(doc, ch)
+
+			if tt.expectErr && err == nil {
+				t.Error("ParseBatcaveBizImageLinks() expected error, got nil")
+			}
+			if !tt.expectErr && err != nil {
+				t.Errorf("ParseBatcaveBizImageLinks() unexpected error: %v", err)
+			}
+			if len(links) != tt.expectCount {
+				t.Errorf("ParseBatcaveBizImageLinks() returned %d links, want %d", len(links), tt.expectCount)
+			}
+			for i, expected := range tt.expectURLs {
+				if i >= len(links) {
+					t.Errorf("missing link at index %d: want %q", i, expected)
+					continue
+				}
+				if links[i] != expected {
+					t.Errorf("links[%d] = %q, want %q", i, links[i], expected)
+				}
+			}
+
+			channelLinks := <-ch
+			if len(channelLinks) != tt.expectCount {
+				t.Errorf("channel received %d links, want %d", len(channelLinks), tt.expectCount)
+			}
+		})
+	}
+}
+
+func TestImageParseError(t *testing.T) {
+	err := ImageParseError{Message: "test error", Code: 1}
+	if err.Error() != "test error" {
+		t.Errorf("Error() = %q, want %q", err.Error(), "test error")
+	}
+}
+
+func TestParseImageLinks(t *testing.T) {
+	tests := []struct {
+		name        string
+		html        string
+		expectCount int
+		expectErr   bool
+	}{
+		{
+			name: "extracts blogspot images",
+			html: `<html><body>
+				<img src="https://bp.blogspot.com/page-001.jpg" />
+				<img src="https://bp.blogspot.com/page-002.jpg" />
+			</body></html>`,
+			expectCount: 2,
+			expectErr:   false,
+		},
+		{
+			name: "extracts blogger googleusercontent images",
+			html: `<html><body>
+				<img src="https://blogger.googleusercontent.com/page-001.jpg" />
+			</body></html>`,
+			expectCount: 1,
+			expectErr:   false,
+		},
+		{
+			name: "extracts covers images",
+			html: `<html><body>
+				<img src="https://example.com/covers/cover-001.jpg" />
+			</body></html>`,
+			expectCount: 1,
+			expectErr:   false,
+		},
+		{
+			name: "excludes logo images",
+			html: `<html><body>
+				<img src="https://bp.blogspot.com/logo-site.jpg" />
+				<img src="https://bp.blogspot.com/page-001.jpg" />
+			</body></html>`,
+			expectCount: 1,
+			expectErr:   false,
+		},
+		{
+			name: "excludes non-matching images",
+			html: `<html><body>
+				<img src="https://other-site.com/image.jpg" />
+				<img src="https://cdn.example.com/banner.png" />
+			</body></html>`,
+			expectCount: 0,
+			expectErr:   true,
+		},
+		{
+			name:        "no images at all",
+			html:        `<html><body><p>No images here</p></body></html>`,
+			expectCount: 0,
+			expectErr:   true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			doc, _ := goquery.NewDocumentFromReader(strings.NewReader(tt.html))
+			ch := make(chan []string, 1)
+
+			links, err := ParseImageLinks(doc, ch)
+
+			if tt.expectErr && err == nil {
+				t.Error("ParseImageLinks() expected error, got nil")
+			}
+			if !tt.expectErr && err != nil {
+				t.Errorf("ParseImageLinks() unexpected error: %v", err)
+			}
+			if len(links) != tt.expectCount {
+				t.Errorf("ParseImageLinks() returned %d links, want %d", len(links), tt.expectCount)
+			}
+
+			// Verify the channel also received the links
+			channelLinks := <-ch
+			if len(channelLinks) != tt.expectCount {
+				t.Errorf("channel received %d links, want %d", len(channelLinks), tt.expectCount)
+			}
+		})
+	}
+}

docker-compose.yml

@@ -0,0 +1,10 @@
+services:
+  yoink:
+    build: .
+    ports:
+      - "8080:8080"
+    volumes:
+      - ./library:/library
+    environment:
+      - YOINK_LIBRARY=/library
+    restart: unless-stopped

go.mod

@@ -5,6 +5,7 @@ go 1.22.3
 require (
 	github.com/DaRealFreak/cloudflare-bp-go v1.0.4
 	github.com/PuerkitoBio/goquery v1.9.2
+	github.com/andybalholm/brotli v1.2.0
 	github.com/spf13/cobra v1.8.1
 )
 

go.sum

@@ -4,6 +4,8 @@ github.com/EDDYCJY/fake-useragent v0.2.0 h1:Jcnkk2bgXmDpX0z+ELlUErTkoLb/mxFBNd2Y
 github.com/EDDYCJY/fake-useragent v0.2.0/go.mod h1:5wn3zzlDxhKW6NYknushqinPcAqZcAPHy8lLczCdJdc=
 github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4yPeE=
 github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=
+github.com/andybalholm/brotli v1.2.0 h1:ukwgCxwYrmACq68yiUqwIWnGY0cTPox/M94sVwToPjQ=
+github.com/andybalholm/brotli v1.2.0/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
 github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss=
 github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
 github.com/cpuguy83/go-md2man/v2 v2.0.4/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
@@ -20,6 +22,8 @@ github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
 github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
 github.com/stretchr/testify v1.4.0 h1:2E4SXV/wtOkTonXsotYi4li6zVWxYlZuYNCXe9XRJyk=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
+github.com/xyproto/randomstring v1.0.5 h1:YtlWPoRdgMu3NZtP45drfy1GKoojuR7hmRcnhZqKjWU=
+github.com/xyproto/randomstring v1.0.5/go.mod h1:rgmS5DeNXLivK7YprL0pY+lTuhNQW3iGxZ18UQApw/E=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=

web/server.go

@@ -0,0 +1,358 @@
+package web
+
+import (
+	"archive/zip"
+	"embed"
+	"encoding/json"
+	"fmt"
+	"io"
+	"io/fs"
+	"net/http"
+	"net/url"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/PuerkitoBio/goquery"
+	"yoink/comic"
+)
+
+//go:embed static
+var staticFiles embed.FS
+
+type JobStatus string
+
+const (
+	StatusPending  JobStatus = "pending"
+	StatusRunning  JobStatus = "running"
+	StatusComplete JobStatus = "complete"
+	StatusError    JobStatus = "error"
+)
+
+type Job struct {
+	ID        string    `json:"id"`
+	URL       string    `json:"url"`
+	Title     string    `json:"title"`
+	Status    JobStatus `json:"status"`
+	Error     string    `json:"error,omitempty"`
+	CreatedAt time.Time `json:"created_at"`
+}
+
+type ComicEntry struct {
+	Title        string    `json:"title"`
+	CoverURL     string    `json:"cover_url"`
+	FileURL      string    `json:"file_url"`
+	DownloadedAt time.Time `json:"downloaded_at"`
+}
+
+type Server struct {
+	libraryPath string
+	jobs        map[string]*Job
+	mu          sync.RWMutex
+}
+
+func NewServer(libraryPath string) *Server {
+	return &Server{
+		libraryPath: libraryPath,
+		jobs:        make(map[string]*Job),
+	}
+}
+
+func (s *Server) Handler() http.Handler {
+	mux := http.NewServeMux()
+
+	// Embedded static assets
+	staticFS, _ := fs.Sub(staticFiles, "static")
+	mux.Handle("/static/", http.StripPrefix("/static/", http.FileServer(http.FS(staticFS))))
+
+	// Library files: covers (inline) and cbz downloads (attachment)
+	mux.Handle("/covers/", http.StripPrefix("/covers/", http.FileServer(http.Dir(s.libraryPath))))
+	mux.Handle("/files/", http.StripPrefix("/files/", s.downloadHandler()))
+
+	// API
+	mux.HandleFunc("/api/download", s.handleDownload)
+	mux.HandleFunc("/api/upload", s.handleUpload)
+	mux.HandleFunc("/api/comics", s.handleComics)
+	mux.HandleFunc("/api/jobs", s.handleJobs)
+	mux.HandleFunc("/health", func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusOK)
+	})
+
+	// SPA root
+	mux.HandleFunc("/", func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path != "/" {
+			http.NotFound(w, r)
+			return
+		}
+		data, _ := staticFiles.ReadFile("static/index.html")
+		w.Header().Set("Content-Type", "text/html; charset=utf-8")
+		w.Write(data)
+	})
+
+	return mux
+}
+
+// downloadHandler wraps the library file server to force Content-Disposition: attachment.
+func (s *Server) downloadHandler() http.Handler {
+	fs := http.FileServer(http.Dir(s.libraryPath))
+	return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Disposition", "attachment")
+		fs.ServeHTTP(w, r)
+	})
+}
+
+func (s *Server) handleDownload(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+		return
+	}
+
+	var req struct {
+		URL string `json:"url"`
+	}
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil || strings.TrimSpace(req.URL) == "" {
+		http.Error(w, "invalid request", http.StatusBadRequest)
+		return
+	}
+
+	job := &Job{
+		ID:        fmt.Sprintf("%d", time.Now().UnixNano()),
+		URL:       req.URL,
+		Status:    StatusPending,
+		CreatedAt: time.Now(),
+	}
+
+	s.mu.Lock()
+	s.jobs[job.ID] = job
+	s.mu.Unlock()
+
+	go s.runJob(job)
+
+	w.Header().Set("Content-Type", "application/json")
+	json.NewEncoder(w).Encode(job)
+}
+
+func (s *Server) runJob(job *Job) {
+	s.mu.Lock()
+	job.Status = StatusRunning
+	s.mu.Unlock()
+
+	markupCh := make(chan *goquery.Document)
+	imageCh := make(chan []string)
+
+	c := comic.NewComic(job.URL, s.libraryPath, imageCh, markupCh)
+
+	s.mu.Lock()
+	job.Title = c.Title
+	s.mu.Unlock()
+
+	errs := c.Download(len(c.Filelist))
+	if len(errs) > 0 {
+		s.mu.Lock()
+		job.Status = StatusError
+		job.Error = errs[0].Error()
+		s.mu.Unlock()
+		return
+	}
+
+	if err := c.Archive(); err != nil {
+		s.mu.Lock()
+		job.Status = StatusError
+		job.Error = err.Error()
+		s.mu.Unlock()
+		return
+	}
+
+	c.Cleanup()
+
+	s.mu.Lock()
+	job.Status = StatusComplete
+	s.mu.Unlock()
+}
+
+func (s *Server) handleComics(w http.ResponseWriter, r *http.Request) {
+	w.Header().Set("Content-Type", "application/json")
+
+	entries := []ComicEntry{}
+
+	dirs, err := os.ReadDir(s.libraryPath)
+	if err != nil {
+		json.NewEncoder(w).Encode(entries)
+		return
+	}
+
+	for _, dir := range dirs {
+		if !dir.IsDir() {
+			continue
+		}
+
+		title := dir.Name()
+		dirPath := filepath.Join(s.libraryPath, title)
+
+		var coverURL, fileURL string
+		var downloadedAt time.Time
+
+		files, _ := os.ReadDir(dirPath)
+		for _, f := range files {
+			name := f.Name()
+
+			if strings.HasSuffix(name, ".cbz") {
+				fileURL = "/files/" + url.PathEscape(title) + "/" + url.PathEscape(name)
+				if info, err := f.Info(); err == nil {
+					downloadedAt = info.ModTime()
+				}
+			}
+
+			// Cover kept by Cleanup: "<Title> 001.jpg"
+			stripped := strings.TrimSpace(strings.TrimPrefix(name, title))
+			if strings.HasPrefix(strings.ToLower(stripped), "001") {
+				coverURL = "/covers/" + url.PathEscape(title) + "/" + url.PathEscape(name)
+			}
+		}
+
+		if fileURL != "" {
+			entries = append(entries, ComicEntry{
+				Title:        title,
+				CoverURL:     coverURL,
+				FileURL:      fileURL,
+				DownloadedAt: downloadedAt,
+			})
+		}
+	}
+
+	// Default: newest first
+	sort.Slice(entries, func(i, j int) bool {
+		return entries[i].DownloadedAt.After(entries[j].DownloadedAt)
+	})
+
+	json.NewEncoder(w).Encode(entries)
+}
+
+func (s *Server) handleJobs(w http.ResponseWriter, r *http.Request) {
+	s.mu.RLock()
+	jobs := make([]*Job, 0, len(s.jobs))
+	for _, j := range s.jobs {
+		jobs = append(jobs, j)
+	}
+	s.mu.RUnlock()
+
+	w.Header().Set("Content-Type", "application/json")
+	json.NewEncoder(w).Encode(jobs)
+}
+
+func (s *Server) handleUpload(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+		return
+	}
+
+	// 500 MB limit
+	if err := r.ParseMultipartForm(500 << 20); err != nil {
+		http.Error(w, "request too large", http.StatusRequestEntityTooLarge)
+		return
+	}
+
+	title := strings.TrimSpace(r.FormValue("title"))
+	if title == "" {
+		http.Error(w, "title required", http.StatusBadRequest)
+		return
+	}
+	// Sanitize: no path separators or shell-special characters
+	title = filepath.Base(title)
+	title = strings.Map(func(r rune) rune {
+		if strings.ContainsRune(`/\:*?"<>|`, r) {
+			return '_'
+		}
+		return r
+	}, title)
+
+	fileHeaders := r.MultipartForm.File["images"]
+	if len(fileHeaders) == 0 {
+		http.Error(w, "no images provided", http.StatusBadRequest)
+		return
+	}
+
+	// Sort by original filename so page order is preserved
+	sort.Slice(fileHeaders, func(i, j int) bool {
+		return fileHeaders[i].Filename < fileHeaders[j].Filename
+	})
+
+	dir := filepath.Join(s.libraryPath, title)
+	if err := os.MkdirAll(dir, 0o755); err != nil {
+		http.Error(w, "failed to create directory", http.StatusInternalServerError)
+		return
+	}
+
+	cbzPath := filepath.Join(dir, title+".cbz")
+	cbzFile, err := os.Create(cbzPath)
+	if err != nil {
+		http.Error(w, "failed to create archive", http.StatusInternalServerError)
+		return
+	}
+	defer cbzFile.Close()
+
+	zw := zip.NewWriter(cbzFile)
+	defer zw.Close()
+
+	imageExts := map[string]bool{".jpg": true, ".jpeg": true, ".png": true, ".webp": true}
+	idx := 1
+
+	for _, fh := range fileHeaders {
+		ext := strings.ToLower(filepath.Ext(fh.Filename))
+		if !imageExts[ext] {
+			continue
+		}
+		if ext == ".jpeg" {
+			ext = ".jpg"
+		}
+
+		entryName := fmt.Sprintf("%03d%s", idx, ext)
+
+		src, err := fh.Open()
+		if err != nil {
+			continue
+		}
+
+		// Save first image as cover: "<Title> 001.jpg"
+		if idx == 1 {
+			coverPath := filepath.Join(dir, title+" "+entryName)
+			if cf, err := os.Create(coverPath); err == nil {
+				io.Copy(cf, src)
+				cf.Close()
+				src.Close()
+				src, err = fh.Open()
+				if err != nil {
+					continue
+				}
+			}
+		}
+
+		ze, err := zw.Create(entryName)
+		if err != nil {
+			src.Close()
+			continue
+		}
+		io.Copy(ze, src)
+		src.Close()
+		idx++
+	}
+
+	if idx == 1 {
+		// Nothing was written — no valid images
+		os.RemoveAll(dir)
+		http.Error(w, "no valid images in upload", http.StatusBadRequest)
+		return
+	}
+
+	w.Header().Set("Content-Type", "application/json")
+	json.NewEncoder(w).Encode(map[string]string{"title": title, "status": "complete"})
+}
+
+func Listen(addr string, libraryPath string) error {
+	srv := NewServer(libraryPath)
+	fmt.Printf("Yoink web server listening on %s\n", addr)
+	return http.ListenAndServe(addr, srv.Handler())
+}