Dockerfile

FROM python:3.10-slim

# Install system dependencies
RUN apt-get update && apt-get install -y \
    wget \
    gnupg \
    tesseract-ocr \
    libtesseract-dev \
    chromium \
    chromium-driver \
    libglib2.0-0 \
    libnss3 \
    libgconf-2-4 \
    libfontconfig1 \
    libxss1 \
    libappindicator3-1 \
    libasound2 \
    libatk-bridge2.0-0 \
    libgtk-3-0 \
    libx11-xcb1 \
    libxcb-dri3-0 \
    libdrm2 \
    libgbm1 \
    libxshmfence1 \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy requirements first for better caching
COPY requirements.txt .

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Install playwright and its browsers with proper permissions
ENV PLAYWRIGHT_BROWSERS_PATH=/app/playwright-browsers
RUN mkdir -p /app/playwright-browsers && \
    playwright install chromium && \
    playwright install-deps chromium

# Copy application code
COPY main.py .

# Create directory for scraped files with proper permissions
RUN mkdir -p /app/data && chmod 777 /app/data

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV PLAYWRIGHT_BROWSERS_PATH=/app/playwright-browsers

# Expose port 7860 (default for Hugging Face Spaces)
EXPOSE 7860

# Run the application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]