Fix space in workflows dir

.github/workflows/docker-image.yml

@@ -0,0 +1,43 @@
+name: Docker Image CI
+
+on:
+  push:
+    branches: [ "release" ]
+  pull_request:
+    branches: [ "release" ]
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@f054a8b539a109f9f41c372932f1ae047eff08c9
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@98669ae865ea3cffbcbaa878cf57c20bbf1c6c38
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@ad44023a93711e3deb337508980b4b5e9bcdc5dc
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

Dockerfile

@@ -0,0 +1,25 @@
+FROM python:3-bookworm
+
+LABEL maintainer=LasseR15
+LABEL email=lasse.roth@lasse-it.de
+
+
+RUN apt update
+RUN apt install -y tesseract-ocr tesseract-ocr-deu ghostscript
+
+
+COPY /src /app/src
+COPY /requirements.txt /app/requirements.txt
+
+WORKDIR /app
+
+RUN pip3 install -r requirements.txt
+
+
+RUN python -m playwright install-deps chromium
+RUN python -m playwright install chromium
+
+ENV PYTHONPATH=/app/src/
+ENV BASE_OUTPUT_PATH=/app/output
+
+ENTRYPOINT ["python3", "/app/src/main.py"]

README.md

@@ -0,0 +1,156 @@
+<a name="readme-top"></a>
+
+[![Stargazers][stars-shield]][stars-url]
+[![Issues][issues-shield]][issues-url]
+[![GPL-3.0 License][license-shield]][license-url]
+
+
+
+<!-- PROJECT LOGO -->
+<br />
+<div align="center">
+  <h3 align="center">BiBox to PDF</h3>
+
+  <p align="center">
+    CLI tool to download a book from BiBox as a OCR PDF
+    <br />
+    <br />
+    <a href="https://github.com/LasseR15/bibox-to-pdf/issues">Report Bug</a>
+    ·
+    <a href="https://github.com/LasseR15/bibox-to-pdf/issues">Request Feature</a>
+  </p>
+</div>
+
+
+<!-- DISCLAIMER -->
+<div align="center">
+  <h3>DISCLAIMER: THIS PROJECT IS FOR EDUCATIONAL PURPOSES ONLY</h3>
+</div>
+<br />
+
+<!-- TABLE OF CONTENTS -->
+<details>
+  <summary>Table of Contents</summary>
+  <ol>
+    <li>
+      <a href="#about-the-project">About The Project</a>
+    </li>
+    <li>
+      <a href="#getting-started">Getting Started</a>
+      <ul>
+        <li><a href="#prerequisites-for-manual-setup">Prerequisites for manual setup</a></li>
+      </ul>
+    </li>
+    <li>
+      <a href="#usage">Usage</a>
+      <ul>
+        <li><a href="#usage-with-Docker">Usage with Docker</a></li>
+        <li><a href="#usage-with-manual-setup">Usage with manual setup</a></li>
+      </ul>
+    </li>
+    <li><a href="#license">License</a></li>
+  </ol>
+</details>
+
+
+
+<!-- ABOUT THE PROJECT -->
+## About The Project
+
+This cli script allows you to download and ocr books from [BiBox](https://www.bibox.schule/).
+
+You need valid login credentials as well as access to the books you want to download.
+
+
+<p align="right">(<a href="#readme-top">back to top</a>)</p>
+
+
+
+<!-- GETTING STARTED -->
+## Getting Started
+
+You can currently only run the script via Docker.
+
+In the future there will be a described way to run it manually.
+
+<p align="right">(<a href="#readme-top">back to top</a>)</p>
+
+<!-- USAGE EXAMPLES -->
+## Usage
+
+### Usage with Docker
+
+To run the image via Docker you can either do it directly via the Docker cli or the recommended way Docker compose.
+
+There are two variants/tags available:
+1. `latest`: The latest ocr version Docker image (larger image than the non-ocr verison)
+2. `latest-non-ocr`: The latest non-ocr version. This image has no support for pdf ocr and is therefore smaller than the ocr version (Currently not available)
+
+#### Docker Compose
+
+To use the ocr version of the script with Docker Compose run the following command:
+```bash
+docker compose --rm -it run bibox-to-cli \
+    '{USERNAME}' '{PASSWORD}' {BOOK_ID}
+```
+<!-- CURRENTLY NOT AVAILABLE
+If you want to run the non-ocr version run the following command.
+
+You can also simply add `--no-ocr` before the username in the above command.
+```bash
+docker compose -f ./docker-compose.non-ocr.yml --rm -it run bibox-to-cli \
+    '{USERNAME}' '{PASSWORD}' {BOOK_ID}
+```
+-->
+#### Docker CLI
+
+To use the script with ocr via Docker run the following command:
+```bash
+Docker run --rm -it \
+    -v ./books:/app/output/books \
+    ghcr.io/lasser15/bibox-to-pdf:latest \
+    '{USERNAME}' '{PASSWORD}' {book_id}
+```
+<!-- CURRENTLY NOT AVAILABLE
+To use it without ocr, run the following command.
+
+You can also simply add `--no-ocr` before the username in the above command.
+```bash
+Docker run --rm -it \
+    -v ./books:/app/output/books \
+    ghcr.io/lasser15/bibox-to-pdf:latest-non-ocr \
+    '{USERNAME}' '{PASSWORD}' {book_id}
+```
+-->
+
+<p align="right">(<a href="#readme-top">back to top</a>)</p>
+
+
+### Usage with manual setup
+
+The manual setup is currently not supported. Please use Docker instead.
+
+
+<p align="right">(<a href="#readme-top">back to top</a>)</p>
+
+
+
+
+<!-- LICENSE -->
+## License
+
+Distributed under the GPL 3.0 License. See `LICENSE` for more information.
+
+<p align="right">(<a href="#readme-top">back to top</a>)</p>
+
+
+
+
+<!-- MARKDOWN LINKS & IMAGES -->
+<!-- https://www.markdownguide.org/basic-syntax/#reference-style-links -->
+[stars-shield]: https://img.shields.io/github/stars/LasseR15/bibox-to-pdf.svg?style=for-the-badge
+[stars-url]: https://github.com/LasseR15/bibox-to-pdf/stargazers
+[issues-shield]: https://img.shields.io/github/issues/LasseR15/bibox-to-pdf.svg?style=for-the-badge
+[issues-url]: https://github.com/LasseR15/bibox-to-pdf/issues
+[license-shield]: https://img.shields.io/github/license/LasseR15/bibox-to-pdf.svg?style=for-the-badge
+[license-url]: https://github.com/LasseR15/bibox-to-pdf/blob/release/LICENSE

docker-compose.yml

@@ -0,0 +1,9 @@
+version: '3.9'
+
+services:
+  bibox-to-pdf:
+    image: ghcr.io/lasser15/bibox-to-pdf:latest
+    build:
+      context: .
+    volumes:
+      - ./books:/app/output/books

bibox_to_pdf/bibox/BiboxImageDownloader.py → src/bibox_to_pdf/bibox/BiboxImageDownloader.py

@@ -13,8 +13,10 @@ def get_bibox_images(access_token: str, book_id: int):
     response = requests.get(url, headers=headers)
 
     if response.status_code != 200:
-        print("Response code from server was not 200. Exiting!")
-        typer.Exit(1)
+        print(f"Response code from server was not 200. "
+              f"Either the book id '{book_id}' doesn't exist or the login wasn't successful. "
+              f"Exiting!")
+        raise typer.Exit(1)
 
     return pages_to_image_array(response.json().get("pages", []))
 
@@ -52,7 +54,7 @@ def pages_to_image_array(pages: []):
         image = page["images"][0] if page.get("images") else None
         if image is None:
             print("At least one image was null. Maybe script needs updating. Exiting!")
-            typer.Exit(1)
+            raise typer.Exit(1)
         images.append(image)
 
     return images

bibox_to_pdf/bibox/BiboxLogin.py → src/bibox_to_pdf/bibox/BiboxLogin.py

@@ -25,7 +25,7 @@ def login_to_bibox(username: str, password: str) -> str:
             page.wait_for_selector(BiboxSelectors.logoutBtn, timeout=10000)
         except:
             print('Login credentials incorrect or a network error occurred.')
-            typer.Exit(1)
+            raise typer.Exit(1)
 
         access_token = page.evaluate('() => window.localStorage.getItem("oauth.accessToken")')
 

bibox_to_pdf/values/Constants.py → src/bibox_to_pdf/values/Constants.py

@@ -1,9 +1,12 @@
+import os
+
+
 class Constants:
     biboxLoginUrl = 'https://bibox2.westermann.de'
     biboxBookInfoUrl = 'https://backend.bibox2.westermann.de/v1/api/sync/{}?materialtypes[]=default&materialtypes[]=addon'
-    # biboxBookPageUrl = 'https://bibox2.westermann.de/book/{{bookId}}/page/{pageNumber}'
 
-    bookBaseOutputDir = '../books/{}'
+    baseOutputPath = os.getenv('BASE_OUTPUT_PATH', default='.')
+    bookBaseOutputDir = baseOutputPath + '/books/{}'
     imageOutputDir = bookBaseOutputDir + '/images/'
     imageOutputFile = imageOutputDir + '{}.png'
     pdfOutputDir = bookBaseOutputDir + '/pdfs/'