trayv/my-actor

# 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

# Check preinstalled packages
RUN npm ls crawlee apify puppeteer playwright

# 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 . ./

# Create and run as a non-root user.
RUN adduser -h /home/apify -D apify && \
    chown -R apify:apify ./
USER apify

# Run the image.
CMD npm start --silent

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

{
    "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"]
}

# 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

{
    "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": "^3.2.6",
        "axios": "^1.5.0",
        "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"
}

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// this is ESM project, and as such, it requires you to specify extensions in your relative imports
8// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
9// import { router } from './routes.js';
10
11// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init().
12await Actor.init();
13
14// Structure of input is defined in input_schema.json
15const input = await Actor.getInput();
16const { url } = input;
17
18// Fetch the HTML content of the page.
19const response = await axios.get(url);
20
21// Parse the downloaded HTML with Cheerio to enable data extraction.
22const $ = cheerio.load(response.data);
23
24// Extract all headings from the page (tag name and text).
25const headings = [];
26$("h1, h2, h3, h4, h5, h6").each((i, element) => {
27    const headingObject = {
28        level: $(element).prop("tagName").toLowerCase(),
29        text: $(element).text(),
30    };
31    console.log("Extracted heading", headingObject);
32    headings.push(headingObject);
33});
34
35// Save headings to Dataset - a table-like storage.
36await Actor.pushData(headings);
37
38// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit().
39await Actor.exit();