root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf


.editorconfig

.eslintrc

# This file tells Git which files shouldn't be added to source control

.idea
node_modules


.gitignore

# First, specify the base Docker image. You can read more about
# the available images at https://sdk.apify.com/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:16

# 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 --only=prod --no-optional --all || true) \
 &amp;&amp; echo "Node.js version:" \
 &amp;&amp; node --version \
 &amp;&amp; echo "NPM version:" \
 &amp;&amp; npm --version

# 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 . ./

# Optionally, specify how to launch the source code of your actor.
# By default, Apify's base Docker images define the CMD instruction
# that runs the Node.js source code using the command specified
# in the "scripts.start" section of the package.json file.
# In short, the instruction looks something like this:
#
# CMD npm start

Dockerfile

{
 "title": "LD JSON Schema scraper",
 "type": "object",
 "schemaVersion": 1,
 "properties": {
 "startUrls": {
 "title": "Start Urls",
 "type": "array",
 "description": "The URLs to extract all LD+JSON data",
 "default": [],
 "prefill": [{
 "url": "https://blog.apify.com/"
 }],
 "editor": "requestListSources"
 },
 "proxyConfiguration": {
 "title": "Proxy configuration",
 "description": "A proxy required for scraping",
 "type": "object",
 "default": { "useApifyProxy": true },
 "prefill": { "useApifyProxy": true },
 "editor": "proxy"
 },
 "customData": {
 "title": "Custom data",
 "description": "Provide some custom data to output",
 "type": "object",
 "default": {},
 "prefill": {},
 "editor": "json"
 }
 },
 "required": [
 "startUrls",
 "proxyConfiguration"
 ]
}

INPUT_SCHEMA.json

# LD+JSON scraper

Extract LD+JSON data from websites

README.md

{
 "env": { "npm_config_loglevel": "silent" }
}

apify.json

main.js

{
 "name": "project-empty",
 "version": "0.0.1",
 "description": "This is a boilerplate of an Apify actor.",
 "dependencies": {
 "apify": "^2.2.1"
 },
 "scripts": {
 "start": "node main.js",
 "lint": "./node_modules/.bin/eslint ./src --ext .js,.jsx",
 "lint:fix": "./node_modules/.bin/eslint ./src --ext .js,.jsx --fix",
 "test": "echo \"Error: oops, the actor has no tests yet, sad!\" &amp;&amp; exit 1"
 },
 "author": "It's not you it's me",
 "license": "ISC"
}

package.json

# First, specify the base Docker image. You can read more about
# the available images at https://sdk.apify.com/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:16

# 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 --only=prod --no-optional --all || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

# 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 . ./

# Optionally, specify how to launch the source code of your actor.
# By default, Apify's base Docker images define the CMD instruction
# that runs the Node.js source code using the command specified
# in the "scripts.start" section of the package.json file.
# In short, the instruction looks something like this:
#
# CMD npm start


Custom data

Proxy configuration

Start Urls

LD JSON Schema scraper

# LD+JSON scraper

Extract LD+JSON data from websites


{
    "env": { "npm_config_loglevel": "silent" }
}


LD+JSON Schema scraper

Industries

Manufacturing

Marketing & Media

Telecommunications

Where next?