jq integration

# Specify the base Docker image. You can read more about
# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:20

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
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 --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version \
    && rm -r ~/.npm

# 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 . ./


# Run the image.
CMD npm start --silent

{
	"actorSpecification": 1,
	"name": "jq-actor",
	"title": "Transform dataset with jq JSON manipulation tool",
	"description": "Allows passing jq command which manipulates given dataset and returns new one.",
	"version": "0.0",
	"input": "./input_schema.json",
	"dockerfile": "./Dockerfile"
}

{
    "title": "Scrape data from a web page",
    "description": "This is actor input schema",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "filter": {
            "title": "jq filter",
            "type": "string",
            "description": "jq filter as documented at https://jqlang.github.io/jq/manual/#basic-filters",
            "default": ".",
            "editor": "textfield"
        },
        "sort": {
            "title": "Sort keys",
            "type": "boolean",
            "description": "Sort output keys alphabetically",
            "default": false,
            "editor": "checkbox"
        },
        "datasetId": {
            "title": "Dataset ID",
            "type": "string",
            "description": "Platform dataset ID when Actor not set up as integration",
            "editor": "textfield"
        }
    },
    "required": [
        "filter"
    ]
}

1import jq from 'node-jq';
2import { Actor } from 'apify';
3
4// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init().
5await Actor.init();
6
7// Structure of input is defined in input_schema.json
8const { filter, sort, ...actorInput } = await Actor.getInput();
9
10
11const datasetId = actorInput.datasetId || actorInput.payload?.resource?.defaultDatasetId;
12
13
14const dataset = await Actor.openDataset(datasetId);
15
16// Use node-jq to filter and sort the input JSON
17const output = await jq.run(filter, dataset, { input: 'json', sort });
18
19
20await Actor.pushData(output);
21
22// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit().
23await Actor.exit();

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

# This file tells Git which files shouldn't be added to source control
.DS_Store
.idea
dist
node_modules
apify_storage
storage/*
!storage/key_value_stores
storage/key_value_stores/*
!storage/key_value_stores/default
storage/key_value_stores/default/*
!storage/key_value_stores/default/INPUT.json

# Added by Apify CLI
storage
.venv

{
	"name": "jq-actor",
	"version": "0.0.1",
	"type": "module",
	"description": "Apify actor template for running JQ JSON manipulation tool.",
	"engines": {
		"node": ">=18.0.0"
	},
	"dependencies": {
		"apify": "^3.1.10",
		"axios": "^1.5.0",
		"cheerio": "^1.0.0-rc.12",
		"node-jq": "^6.0.1"
	},
	"scripts": {
		"start": "node ./src/main.js"
	},
	"author": "Jan Turon",
	"license": "ISC"
}