Dockerfile

Dockerfile

# Specify the base Docker image. You can read more about
# the available images at https://crawlee.dev/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node-playwright-chrome:16 AS builder

# Install pnpm
RUN wget -qO- https://get.pnpm.io/install.sh | ENV="$HOME/.bashrc" SHELL="$(which bash)" bash -

# Use the shell form of RUN to source the .bashrc file before running pnpm
SHELL ["/bin/bash", "-c", "source /home/myuser/.bashrc"]

# Copy just package.json and pnpm-lock.yaml
# to speed up the build using Docker layer cache.
COPY ./scraper/package.json ./scraper/
COPY ./scraper/pnpm-lock.yaml ./scraper/

# Install all dependencies. Don't audit to speed up the installation.
RUN cd ./scraper && pnpm install --include=dev --audit=false

COPY ./interface/package.json ./interface/
COPY ./interface/pnpm-lock.yaml ./interface/

RUN cd ./interface && pnpm install --include=dev --audit=false

# Next, copy the source files using the user set
# in the base image.
COPY ./scraper ./scraper

# Install all dependencies and build the project.
# Don't audit to speed up the installation.
RUN cd ./scraper && pnpm run build

COPY ./interface ./interface

RUN cd ./interface && pnpm run build

# Create final image
FROM apify/actor-node-playwright-chrome:16

# Install pnpm
RUN wget -qO- https://get.pnpm.io/install.sh | ENV="$HOME/.bashrc" SHELL="$(which bash)" bash -

# Use the shell form of RUN to source the .bashrc file before running pnpm
SHELL ["/bin/bash", "-c", "source /home/myuser/.bashrc"]

# Copy only built JS files and from builder image
COPY --from=builder /home/myuser/scraper/dist ./app/scraper/dist
COPY --from=builder /home/myuser/interface/dist ./app/interface/dist

# Copy just package.json and pnpm-lock.yaml
# to speed up the build using Docker layer cache.
COPY ./scraper/package.json ./app/scraper/
COPY ./scraper/pnpm-lock.yaml ./app/scraper/
COPY ./interface/package.json ./app/interface/
COPY ./interface/pnpm-lock.yaml ./app/interface/

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN cd ./app/scraper \
  && pnpm install --prod -s \
  && echo "Installed PNPM packages:" \
  && (pnpm list --prod || true) \
  && echo "Node.js version:" \
  && node --version \
  && echo "PNPM version:" \
  && pnpm --version

# Install python
RUN apt-get update && apt-get install -y python3 python3-pip

COPY stringNormalizers/verToSemVer/hardCodedApproach ./stringNormalizers/verToSemVer/hardCodedApproach

# Install python dependencies
RUN pip3 install -r ./stringNormalizers/verToSemVer/hardCodedApproach/requirements.txt

COPY stringNormalizers/nameToStdName ./stringNormalizers/nameToStdName

RUN pip3 install -r ./stringNormalizers/nameToStdName/requirements.txt

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY . ./app

# Change working directory to /usr/src/app/scraper
WORKDIR /home/myuser/app/scraper

VOLUME "/home/myuser/repository"

ENTRYPOINT ["bash"]
# CMD ["dist/main.js"]