Dockerfile

# Base stage with system dependencies
FROM python:3.11

# Thiết lập thư mục làm việc
WORKDIR /code
# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    curl \
    wget \
    gnupg \
    git \
    cmake \
    pkg-config \
    python3-dev \
    libjpeg-dev \
    libpng-dev \
    && rm -rf /var/lib/apt/lists/*

# Playwright system dependencies for Linux
RUN apt-get update && apt-get install -y --no-install-recommends \
    libglib2.0-0 \
    libnss3 \
    libnspr4 \
    libatk1.0-0 \
    libatk-bridge2.0-0 \
    libcups2 \
    libdrm2 \
    libdbus-1-3 \
    libxcb1 \
    libxkbcommon0 \
    libx11-6 \
    libxcomposite1 \
    libxdamage1 \
    libxext6 \
    libxfixes3 \
    libxrandr2 \
    libgbm1 \
    libpango-1.0-0 \
    libcairo2 \
    libasound2 \
    libatspi2.0-0 \
    && rm -rf /var/lib/apt/lists/*
    
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1 \
    PIP_DEFAULT_TIMEOUT=100 \
    DEBIAN_FRONTEND=noninteractive


# Cài đ?t các bi?n môi trư?ng
ENV HOME=/code
ENV XDG_CACHE_HOME=/code/.cache


USER root
ENV PATH="/home/user/.local/bin:$PATH"

# T?o thư m?c cache và c?p quy?n
RUN mkdir -p /code/.cache && chmod -R 777 /code
# Cài đặt môi trường ảo Python

# Sao chép mã nguồn
COPY ./requirements.txt /code/requirements.txt
RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
RUN pip install playwright
RUN playwright install
RUN playwright install-deps
RUN playwright install chromium
RUN pip install --upgrade --ignore-installed playwright
RUN playwright install --with-deps chromium


# Sao chép mã nguồn vào container
COPY . .
RUN pip install crawl4ai

EXPOSE 7860 9222


# Khởi động ứng dụng
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]