# This is a template for a Dockerfile used to run acts in Actor system.
# The base image name below is set during the act build, based on user settings.
# IMPORTANT: The base image must set a correct working directory, such as /usr/src/app or /home/user
FROM apify/actor-node

# Second, copy just package.json and package-lock.json since it should be
# the only file that affects "npm install" in the next step, to speed up the build
COPY package*.json ./

# 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 npm --quiet set progress=false \
 &amp;&amp; npm install --only=prod --no-optional \
 &amp;&amp; echo "Installed NPM packages:" \
 &amp;&amp; (npm list --all || true) \
 &amp;&amp; echo "Node.js version:" \
 &amp;&amp; node --version \
 &amp;&amp; echo "NPM version:" \
 &amp;&amp; npm --version

# Copy source code to container
# Do this in the last step, to have fast build if only the source code changed
COPY . ./

# NOTE: The CMD is already defined by the base image.
# Uncomment this for local node inspector debugging:
# CMD [ "node", "--inspect=0.0.0.0:9229", "main.js" ]

Dockerfile

{
 "title": "XMLS To Dataset input",
 "description": "Enter the XML URLs you want to be downloaded.",
 "type": "object",
 "schemaVersion": 1,
 "properties": {
 "sources": {
 "title": "URLs of XML files",
 "type": "array",
 "description": "Enter the XML URLs you want to be downloaded.",
 "prefill": [
 {
 "url": "https://www.w3schools.com/xml/plant_catalog.xml"
 },
 {
 "url": "https://www.w3schools.com/xml/cd_catalog.xml"
 }
 ],
 "editor": "requestListSources"
 },
 "proxy": {
 "title": "Proxy configuration",
 "type": "object",
 "description": "Select proxies to be used to download XML files.",
 "prefill": { "useApifyProxy": true },
 "editor": "proxy"
 }
 },
 "required": ["sources", "proxy"]
}

INPUT_SCHEMA.json

This actor simply takes URLs of XML files hosted elsewhere, downloads them, and saves their contents into the dataset.

README.md

main.js

{
 "name": "apify-project",
 "version": "0.0.1",
 "description": "",
 "author": "It's not you it's me",
 "license": "ISC",
 "dependencies": {
 "apify": "latest",
 "xml2js": "latest",
 "underscore": "latest"
 },
 "scripts": {
 "start": "node main.js"
 }
}

package.json

# This is a template for a Dockerfile used to run acts in Actor system.
# The base image name below is set during the act build, based on user settings.
# IMPORTANT: The base image must set a correct working directory, such as /usr/src/app or /home/user
FROM apify/actor-node

# Second, copy just package.json and package-lock.json since it should be
# the only file that affects "npm install" in the next step, to speed up the build
COPY package*.json ./

# 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 npm --quiet set progress=false \
 && npm install --only=prod --no-optional \
 && echo "Installed NPM packages:" \
 && (npm list --all || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

# Copy source code to container
# Do this in the last step, to have fast build if only the source code changed
COPY  . ./

# NOTE: The CMD is already defined by the base image.
# Uncomment this for local node inspector debugging:
# CMD [ "node", "--inspect=0.0.0.0:9229", "main.js" ]


Enter the XML URLs you want to be downloaded.

Select proxies to be used to download XML files.

Proxy configuration

URLs of XML files

XMLS To Dataset input

apify-project

Go to actor anytime you need to download XML files and store them in the dataset.

XMLs To Dataset

Industries

Manufacturing

Where next?