update docker setup and dependencies

Dockerfile

@@ -1,84 +1,77 @@
-# This Dockerfile for ArchiveBox installs the following in a container:
-#     - curl, wget, python3, youtube-dl, google-chrome-beta
-#     - ArchiveBox
+# This is the Dockerfile for ArchiveBox, it includes the following major pieces:
+#     git, curl, wget, python3, youtube-dl, google-chrome-stable, ArchiveBox
 # Usage:
-#     docker build github.com/pirate/ArchiveBox -t archivebox
-#     echo 'https://example.com' | docker run -i --mount type=bind,source=./data,target=/data archivebox /bin/archive
-#     docker run --mount type=bind,source=./data,target=/data archivebox /bin/archive 'https://example.com/some/rss/feed.xml'
+#     docker build . -t archivebox:latest
+#     docker run -v=./data:/data archivebox:latest init
+#     docker run -v=./data:/data archivebox:latest add 'https://example.com'
 # Documentation:
 #     https://github.com/pirate/ArchiveBox/wiki/Docker#docker
 
-FROM node:13-slim
-LABEL maintainer="Nick Sweeting <[email protected]>"
+FROM python:3.8-slim-buster
+LABEL name="archivebox" \
+      maintainer="Nick Sweeting <[email protected]>" \
+      version="0.4.3" \
+      description="All-in-one personal internet archiving container"
 
-RUN apt-get update \
-    && apt-get install -yq --no-install-recommends \
-        jq git zlib1g-dev wget curl youtube-dl gnupg2 libgconf-2-4 python3 python3-pip \
-    && rm -rf /var/lib/apt/lists/*
+ENV LANG=C.UTF-8 \
+    LANGUAGE=en_US:en \
+    LC_ALL=C.UTF-8 \
+    PYTHONIOENCODING=UTF-8 \
+    PYTHONUNBUFFERED=1 \
+    APT_KEY_DONT_WARN_ON_DANGEROUS_USAGE=1 \
+    CODE_PATH=/app \
+    VENV_PATH=/venv \
+    DATA_PATH=/data
 
 # Install latest chrome package and fonts to support major charsets (Chinese, Japanese, Arabic, Hebrew, Thai and a few others)
-RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - \
-    && sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google.list' \
+RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selections \
+    && apt-get update -qq \
+    && apt-get install -qq -y --no-install-recommends \
+       apt-transport-https ca-certificates apt-utils gnupg gnupg2 libgconf-2-4 zlib1g-dev dumb-init \
+       wget curl youtube-dl jq git ffmpeg avconv \
+    && curl -sSL https://dl.google.com/linux/linux_signing_key.pub | apt-key add - \
+    && echo "deb https://dl.google.com/linux/chrome/deb/ stable main" > /etc/apt/sources.list.d/google-chrome.list \
     && apt-get update \
-    && apt-get install -y google-chrome-beta fonts-ipafont-gothic fonts-wqy-zenhei fonts-thai-tlwg fonts-kacst ttf-freefont \
-      --no-install-recommends \
-    && rm -rf /var/lib/apt/lists/* \
-    && rm -rf /src/*.deb
-
-# It's a good idea to use dumb-init to help prevent zombie chrome processes.
-ADD https://github.com/Yelp/dumb-init/releases/download/v1.2.0/dumb-init_1.2.0_amd64 /usr/local/bin/dumb-init
-RUN chmod +x /usr/local/bin/dumb-init
-
-# Uncomment to skip the chromium download when installing puppeteer. If you do,
-# you'll need to launch puppeteer with:
-#     browser.launch({executablePath: 'google-chrome-beta'})
-ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD true
-
-# Install puppeteer so it's available in the container.
-RUN npm install puppeteer
-
-# Add user so we don't need --no-sandbox.
-RUN groupadd -r pptruser && useradd -r -g pptruser -G audio,video pptruser \
-    && mkdir -p /home/pptruser/Downloads \
-    && chown -R pptruser:pptruser /home/pptruser \
-    && chown -R pptruser:pptruser /node_modules
+    && apt-get install -qq -y --no-install-recommends \
+       google-chrome-stable \
+       fontconfig \
+       fonts-ipafont-gothic \
+       fonts-wqy-zenhei \
+       fonts-thai-tlwg \
+       fonts-kacst \
+       fonts-symbola \
+       fonts-noto \
+       fonts-freefont-ttf \
+    && rm -rf /var/lib/apt/lists/*
 
-WORKDIR /home/pptruser/app
+# Add user so we don't need --no-sandbox to run chrome
+RUN groupadd -r archivebox && useradd -r -g archivebox -G audio,video archivebox \
+    && mkdir -p /home/archivebox/Downloads \
+    && chown -R archivebox:archivebox /home/archivebox
 
-RUN python3 -m pip install --upgrade pip setuptools && python3 -m pip install virtualenv \
-    && python3 -m virtualenv ".docker-venv"
-ENV PATH="/home/pttruser/app/.docker-venv/bin:${PATH}"
-COPY ./Pipfile.lock "/home/pttruser/app/Pipfile.lock"
-RUN jq -r \
-        '.default,.develop | to_entries[] | .key + .value.version' \
-        "/home/pttruser/app/Pipfile.lock" \
-    | /home/pttruser/app/.docker-venv/bin/python -m pip install --no-cache-dir -r /dev/stdin \
-    && rm "/home/pttruser/app/Pipfile.lock"
+WORKDIR "$CODE_PATH"
+ADD . "$CODE_PATH"
+VOLUME "$CODE_PATH"
+RUN chown -R archivebox:archivebox "$CODE_PATH"
 
-# Install the ArchiveBox repository and pip requirements
-# RUN git clone https://github.com/pirate/ArchiveBox /home/pptruser/app \
-ADD . /home/pptruser/app
-RUN mkdir -p /data \
-    && chown -R pptruser:pptruser /data \
-    && ln -s /data /home/pptruser/app/archivebox/output \
-    && ln -s /home/pptruser/app/bin/* /bin/ \
-    && ln -s /home/pptruser/app/bin/archivebox /bin/archive \
-    && chown -R pptruser:pptruser /home/pptruser/app/archivebox
+ENV PATH="$VENV_PATH/bin:${PATH}"
+RUN python --version \
+    && python -m venv "$VENV_PATH" \
+    && pip install --upgrade pip \
+    && pip install -e . \
+    && chown -R archivebox:archivebox "$VENV_PATH"
 
-VOLUME /data
-EXPOSE 8000
+WORKDIR "$DATA_PATH"
+VOLUME "$DATA_PATH"
+RUN chown -R archivebox:archivebox "$DATA_PATH"
 
-ENV LANG=C.UTF-8 \
-    LANGUAGE=en_US:en \
-    LC_ALL=C.UTF-8 \
-    PYTHONIOENCODING=UTF-8 \
+# Run everything from here on out as non-privileged user
+USER archivebox
+ENV CHROME_BINARY=google-chrome \
     CHROME_SANDBOX=False \
-    CHROME_BINARY=google-chrome-beta \
-    OUTPUT_DIR=/data
+    OUTPUT_DIR="$DATA_PATH"
 
-# Run everything from here on out as non-privileged user
-USER pptruser
-WORKDIR /home/pptruser/app
+RUN archivebox version
 
 ENTRYPOINT ["dumb-init", "--"]
-CMD ["/bin/archivebox"]
+CMD ["archivebox"]

docker-compose.yml

@@ -8,25 +8,26 @@
 # Documentation:
 #     https://github.com/pirate/ArchiveBox/wiki/Docker#docker-compose
 
-version: '3'
+version: '3.7'
 
 services:
     archivebox:
         build: .
+        image: archivebox:latest
+        command: archivebox server
         stdin_open: true
         tty: true
-        # env_file: path/to/your/ArchiveBox.conf
         environment:
-            - USE_COLOR=False
+            - USE_COLOR=True
             - SHOW_PROGRESS=False
         volumes:
             - ./data:/data
-        command: bash -c 'echo "https://github.com/pirate/ArchiveBox" | /bin/archive; tail -f /dev/null'
 
     nginx:
-        image: 'nginx'
+        image: nginx:alpine
         ports:
-            - '8098:80'
+            - 443:443
+            - 80:80
         volumes:
             - ./etc/nginx/nginx.conf:/etc/nginx/nginx.conf
             - ./data:/var/www

setup.py

@@ -14,13 +14,13 @@ with open(os.path.join(PYTHON_DIR, 'VERSION'), 'r') as f:
 setuptools.setup(
     name="archivebox",
     version=VERSION,
+    license='MIT',
     author="Nick Sweeting",
     author_email="[email protected]",
     description="The self-hosted internet archive.",
     long_description=README,
     long_description_content_type="text/markdown",
     url="https://github.com/pirate/ArchiveBox",
-    license='MIT',
     project_urls={
         'Donate': 'https://github.com/pirate/ArchiveBox/wiki/Donations',
         'Changelog': 'https://github.com/pirate/ArchiveBox/wiki/Changelog',
@@ -31,14 +31,14 @@ setuptools.setup(
         'Documentation': 'https://github.com/pirate/ArchiveBox/Wiki',
     },
     packages=setuptools.find_packages(),
-    python_requires='>=3.6',
+    python_requires='>=3.7',
     install_requires=[
         "dataclasses==0.6",
-        "mypy-extensions==0.4.1",
+        "mypy-extensions==0.4.3",
         "base32-crockford==0.3.0",
-        "django==2.2",
-        "django-extensions==2.1.6",
-        "python-crontab==2.3.6",
+        "django==3.0.7",
+        "django-extensions==2.2.9",
+        "python-crontab==2.5.1",
         "youtube-dl",
         "ipython",