Files
campus_spider/Dockerfile
T
2026-07-30 11:45:08 +08:00

51 lines
2.1 KiB
Docker

# 使用 Python 3.12 slim 镜像
FROM python:3.12-slim
ENV TZ=Asia/Shanghai
ENV ENV=prod
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
# Playwright 浏览器统一装到系统目录,避免落在 HOME 里
ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
# 浏览器下载走 npmmirror 镜像,国内构建更快(网络可直连时可去掉)
ENV PLAYWRIGHT_DOWNLOAD_HOST=https://cdn.npmmirror.com/binaries/playwright
# 时区 + 系统依赖(libgl1、libglib2.0-0 是 opencv-python 的运行时依赖)
RUN ln -sf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone \
&& rm -rf /etc/apt/sources.list.d/* \
&& echo "deb https://mirrors.aliyun.com/debian/ bookworm main non-free contrib" > /etc/apt/sources.list \
&& echo "deb https://mirrors.aliyun.com/debian-security/ bookworm-security main non-free contrib" >> /etc/apt/sources.list \
&& echo "deb https://mirrors.aliyun.com/debian/ bookworm-updates main non-free contrib" >> /etc/apt/sources.list \
&& apt-get clean \
&& apt-get update \
&& apt-get install -y --no-install-recommends curl libgl1 libglib2.0-0 \
&& rm -rf /var/lib/apt/lists/*
RUN mkdir -p /app/logs
WORKDIR /app
# 先拷贝依赖声明,利用 Docker 层缓存
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt \
-i https://mirrors.aliyun.com/pypi/simple/ \
--trusted-host mirrors.aliyun.com
# 安装 Chromium 及其系统依赖(供 app/tool/browser.py 使用)
RUN playwright install --with-deps chromium \
&& rm -rf /var/lib/apt/lists/*
# 预热 OCR 模型,避免首次采集时才去下载 onnx 模型
# 参数与 app/tool/ocr.py 保持一致,确保命中同一份模型缓存
RUN python -c "from rapidocr import RapidOCR; RapidOCR(params={'Global.use_cls': False, 'Global.text_score': 0.5})"
# 拷贝应用代码、一次性初始化脚本(含 init_xiaozhaoya 依赖的 doc/ 数据)和环境配置
COPY app/ ./app/
COPY doc/ ./doc/
COPY init_offershow.py init_offerqingbaoju.py init_xiaozhaoya.py ./
COPY .env.prod ./.env.prod
# 纯后台定时任务服务,无 HTTP 端口
CMD ["python", "-m", "app.main"]