Sanaa picture catch.

# 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 AS builder

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY package*.json ./

# Install all dependencies. Don't audit to speed up the installation.
RUN npm install --include=dev --audit=false

# Next, copy the source files using the user set
# in the base image.
COPY . ./

# Install all dependencies and build the project.
# Don't audit to speed up the installation.
RUN npm run build

# Create final image
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

# Copy built JS files from builder image
COPY --from=builder /usr/src/app/dist ./dist

# 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 run start:prod --silent

{
    "actorSpecification": 1,
    "name": "my-actor-1",
    "title": "Scrape single page in TypeScript",
    "description": "Scrape data from single page with provided URL.",
    "version": "0.0",
    "meta": {
        "templateId": "ts-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

# dist folder
dist

storage
apify_storage
crawlee_storage
node_modules
dist
tsconfig.tsbuildinfo
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": "ts-start",
    "version": "0.0.1",
    "type": "module",
    "description": "This is an example of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.1.10",
        "axios": "^1.5.0",
        "cheerio": "^1.0.0-rc.12"
    },
    "devDependencies": {
        "@apify/tsconfig": "^0.1.0",
        "tsx": "^4.6.2",
        "typescript": "^5.3.3"
    },
    "scripts": {
        "start": "npm run start:dev",
        "start:prod": "node dist/main.js",
        "start:dev": "tsx src/main.ts",
        "build": "tsc",
        "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
8// this is ESM project, and as such, it requires you to specify extensions in your relative imports
9// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
10// note that we need to use `.js` even when inside TS files
11// import { router } from './routes.js';
12
13// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init().
14await Actor.init();
15
16interface Input {
17    url: string;
18}
19// Structure of input is defined in input_schema.json
20const input = await Actor.getInput<Input>();
21if (!input) throw new Error("Input is missing!");
22const { url } = input;
23
24// Fetch the HTML content of the page.
25const response = await axios.get(url);
26
27// Parse the downloaded HTML with Cheerio to enable data extraction.
28const $ = cheerio.load(response.data);
29
30// Extract all headings from the page (tag name and text).
31const headings: { level: string, text: string }[] = [];
32$("h1, h2, h3, h4, h5, h6").each((_i, element) => {
33    const headingObject = {
34        level: $(element).prop("tagName").toLowerCase(),
35        text: $(element).text(),
36    };
37    console.log("Extracted heading", headingObject);
38    headings.push(headingObject);
39});
40
41// Save headings to Dataset - a table-like storage.
42await Actor.pushData(headings);
43
44// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit().
45await Actor.exit();

{
    "extends": "@apify/tsconfig",
    "compilerOptions": {
        "module": "NodeNext",
        "moduleResolution": "NodeNext",
        "target": "ES2022",
        "outDir": "dist",
        "noUnusedLocals": false,
        "skipLibCheck": true,
        "lib": ["DOM"]
    },
    "include": [
        "./src/**/*"
    ]
}