38 lines
1.1 KiB
Docker
38 lines
1.1 KiB
Docker
FROM python:3.11-slim-bookworm
|
|
|
|
ENV TZ=Asia/Shanghai \
|
|
PYTHONUNBUFFERED=1 \
|
|
PIP_NO_CACHE_DIR=1 \
|
|
PIP_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple \
|
|
DQD_CONFIG_PATH=/app/config/settings.yaml \
|
|
DQD_TASKS_FILE=/app/config/crawler_tasks.yaml \
|
|
DQD_LOCK_DIR=/app/data/locks
|
|
|
|
WORKDIR /app
|
|
|
|
RUN apt-get update \
|
|
&& apt-get install -y --no-install-recommends \
|
|
bash \
|
|
ca-certificates \
|
|
cron \
|
|
curl \
|
|
gcc \
|
|
g++ \
|
|
tzdata \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
COPY requirements.txt /app/requirements.txt
|
|
RUN python -m pip install --upgrade pip setuptools wheel \
|
|
&& python -m pip install -r /app/requirements.txt
|
|
|
|
# API 型采集任务不依赖 Chromium。浏览器型采集需要时再在镜像内单独安装，
|
|
# 避免本地首次构建因浏览器下载通道不可达而阻塞整个调度器。
|
|
|
|
COPY . /app
|
|
|
|
RUN sed -i 's/\r$//' /app/docker/entrypoint.sh \
|
|
&& mkdir -p /app/logs /app/data/locks /etc/sport-era-crawler \
|
|
&& chmod +x /app/docker/entrypoint.sh
|
|
|
|
ENTRYPOINT ["/app/docker/entrypoint.sh"]
|