update dependencies and add CI worfkflow for automated build

.github/workflows/build-and-push.yml

@@ -0,0 +1,43 @@
+name: Docker Build and Push
+
+on:
+  push:
+    branches: [ "master", "main" ]
+  pull_request:
+    branches: [ "master", "main" ]
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

Dockerfile

@@ -1,9 +1,9 @@
-FROM debian:sid-slim
+FROM debian:bookworm-slim
 
 ENTRYPOINT ["bash"]
 
 RUN apt-get update && \
-    apt-get --no-install-recommends -y install file less bash coreutils gawk sed grep calibre p7zip-full tesseract-ocr tesseract-ocr-osd tesseract-ocr-eng python-lxml poppler-utils catdoc djvulibre-bin locales curl ca-certificates && \
+    apt-get --no-install-recommends -y install file less bash coreutils gawk sed grep calibre p7zip-full tesseract-ocr tesseract-ocr-osd tesseract-ocr-eng python3-lxml poppler-utils catdoc djvulibre-bin locales curl ca-certificates && \
     rm -rf /var/lib/apt/lists/* && \
     localedef -i en_US -c -f UTF-8 en_US.UTF-8 && \
     useradd -mUs /usr/bin/bash -u 1000 user && \
@@ -16,8 +16,8 @@ ENV LANG="en_US.UTF-8" PATH="${PATH}:/ebook-tools"
 
 USER user
 
-RUN curl 'https://www.mobileread.com/forums/attachment.php?attachmentid=163537' > goodreads.zip && \
-    sha256sum 'goodreads.zip' | grep -q 'c44f88222017aaad0aa1a674e69f46b309198269c7f13ebd671ae942052d45a8' && \
+RUN curl 'https://www.mobileread.com/forums/attachment.php?attachmentid=208844' > goodreads.zip && \
+    sha256sum 'goodreads.zip' | grep -q '7201fd243958ff91960998ac1f9b70bea196d6f386b1e2acf5ba42184c3b9821' && \
     calibre-customize --add-plugin goodreads.zip && \
     rm goodreads.zip && \
     curl -L 'https://github.com/na--/calibre-worldcat-xisbn-metadata-plugin/archive/0.1.zip' > worldcat.zip && \

README.md

@@ -53,14 +53,14 @@ You need recent versions of:
 
 The scripts are only tested on linux, though they should work on any *nix system that has the needed dependencies. You can install everything needed with this command in Arch Linux:
   ```bash
-  pacman -S file less bash coreutils gawk sed grep calibre p7zip tesseract tesseract-data-eng python2-lxml poppler catdoc djvulibre
+  pacman -S file less bash coreutils gawk sed grep calibre p7zip tesseract tesseract-data-eng python-lxml poppler catdoc djvulibre
   ```
 
 *Note: you can probably get much better OCR results by using the unstable 4.0 version of Tesseract. It is present in the [AUR](https://aur.archlinux.org/packages/tesseract-git/) or you can easily make a package like [this](https://github.com/na--/custom-archlinux-packages/blob/master/tesseract-4-bundle-git/PKGBUILD) yourself.*
 
 Here is how to install the packages on Debian (and Debian-based distributions like Ubuntu):
   ```bash
-  apt-get install file less bash coreutils gawk sed grep calibre p7zip-full tesseract-ocr tesseract-ocr-osd tesseract-ocr-eng python-lxml poppler-utils catdoc djvulibre-bin
+  apt-get install file less bash coreutils gawk sed grep calibre p7zip-full tesseract-ocr tesseract-ocr-osd tesseract-ocr-eng python3-lxml poppler-utils catdoc djvulibre-bin
   ```
 *Keep in mind that a lot of debian-based distributions do not have up-to-date packages and the scripts work best when calibre's version is at least 2.84. For earlier versions you have to set `ISBN_METADATA_FETCH_ORDER` and `ORGANIZE_WITHOUT_ISBN_SOURCES` to empty strings.*
 

rename-calibre-library.sh

@@ -24,7 +24,7 @@ if [[ "$#" == "0" ]]; then
 fi
 
 gm() {
-	python2 -c "from lxml.etree import parse; from sys import stdin; print((u'\\n'.join(parse(stdin).xpath('$2'))).encode('utf-8'))" < "$1"
+	python3 -c "from lxml.etree import parse; from sys import stdin; print('\n'.join(parse(stdin.buffer).xpath('$2')))" < "$1"
 }
 
 find "$@" -type f ! -name "*.opf" ! -name "cover.jpg" -print0 | sort -z ${FILE_SORT_FLAGS[@]:+"${FILE_SORT_FLAGS[@]}"} | while IFS= read -r -d '' book_path