Dockerfile

FROM ubuntu:20.04

# Install dependencies
RUN apt-get update && apt-get install -y \
    wget build-essential cmake git g++ pkg-config libfontforge-dev \
    fontforge libpoppler-glib-dev poppler-utils \
    libpng-dev libjpeg-dev libtiff-dev \
    zlib1g-dev libfreetype6-dev libxrender-dev \
    libxml2-dev libspiro-dev python3 python3-pip && \
    apt-get clean

# Clone and build pdf2htmlEX
RUN git clone https://github.com/coolwanglu/pdf2htmlEX.git && \
    cd pdf2htmlEX && \
    cmake . && \
    make && \
    make install

# Install Python dependencies
COPY requirements.txt .
RUN pip3 install -r requirements.txt

# Copy app
COPY app.py .

CMD ["python3", "app.py"]