# 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:18

# 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

.actor/actor.json

{
    "actorSpecification": 1,
    "name": "my-actor-13",
    "title": "Scrape single page in JavaScript",
    "description": "Scrape data from single page with provided URL.",
    "version": "0.0",
    "maxMemoryMbytes": 1024,
    "meta": {
        "templateId": "js-start"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

.actor/input_schema.json

{
    "title": "Scrape data from a web page",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "url": {
            "title": "URL of the page",
            "type": "string",
            "description": "The URL of website you want to get the data from.",
            "editor": "textfield",
            "prefill": "https://www.apify.com/"
        }
    },
    "required": ["url"]
}

src/main.js

1// Axios - Promise based HTTP client for the browser and node.js (Read more at https://axios-http.com/docs/intro).
2import axios from "axios";
3// Cheerio - The fast, flexible & elegant library for parsing and manipulating HTML and XML (Read more at https://cheerio.js.org/).
4import * as cheerio from "cheerio";
5// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/).
6import { Actor } from "apify";
7
8const { 
9    APIFY_API_PUBLIC_BASE_URL,
10    APIFY_API_BASE_URL, 
11    APIFY_DEFAULT_KEY_VALUE_STORE_ID,
12    APIFY_USER_PRICING_TIER,
13    APIFY_USER_IS_PAYING,
14} = process.env;
15
16console.log('vars', {APIFY_USER_PRICING_TIER, APIFY_USER_IS_PAYING});
17
18// process.env.APIFY_API_BASE_URL = APIFY_API_PUBLIC_BASE_URL;
19
20const kvUrl = `${APIFY_API_PUBLIC_BASE_URL}/v2/key-value-stores/${APIFY_DEFAULT_KEY_VALUE_STORE_ID}`;
21
22const kvResponse = await axios.get(kvUrl);
23console.log('kvResponse', { data: kvResponse.data });
24
25// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init().
26await Actor.init();
27console.log('env', { ...process.env });
28// Structure of input is defined in input_schema.json
29const input = await Actor.getInput();
30const { url } = input;
31
32// Fetch the HTML content of the page.
33const response = await axios.get(url);
34
35// Parse the downloaded HTML with Cheerio to enable data extraction.
36const $ = cheerio.load(response.data);
37
38// Extract all headings from the page (tag name and text).
39const headings = [];
40$("h1, h2, h3, h4, h5, h6").each((i, element) => {
41    const headingObject = {
42        level: $(element).prop("tagName").toLowerCase(),
43        text: $(element).text(),
44    };
45    console.log("Extracted heading", headingObject);
46    headings.push(headingObject);
47});
48
49// Save headings to Dataset - a table-like storage.
50await Actor.pushData(headings);
51
52// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit().
53await Actor.exit();

.dockerignore

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

.gitignore

# 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

package.json

{
    "name": "js-scrape-single-page",
    "version": "0.0.1",
    "type": "module",
    "description": "This is an example of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.0.0",
        "axios": "^1.4.0",
        "cheerio": "^1.0.0-rc.12"
    },
    "scripts": {
        "start": "node ./src/main.js",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}

My Actor 2

accommodating_swimsuit/my-actor-2

The second best actor.

filip_alias

My Actor

accommodating_swimsuit/my-actor

This is the best actor in the universe.

filip_alias

My Actor 1

flattered_kettle/my-actor-1

This is the best actor in the world.

Filip Cicvárek

Example actor paid per result

mhamas/example-actor-paid-per-result

This is an example actor demonstrating "pay per result" model. When you run this actor, you are only charged for the results it produces, not for the underlying platform usage.