AgentQL Demo

# 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-6",
    "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 using AgentQL",
    "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://news.ycombinator.com/"
        }
    },
    "required": ["url"]
}

1import { Actor } from 'apify';
2// this is ESM project, and as such, it requires you to specify extensions in your relative imports
3// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
4// import { router } from './routes.js';
5
6// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init().
7await Actor.init();
8
9// Structure of input is defined in input_schema.json
10const input = await Actor.getInput();
11const { url } = input;
12
13// Fetch the HTML content of the page.
14const response = await fetch('https://api.agentql.com/v1/query-data', {
15    method: 'POST',
16    headers: {
17        'X-API-Key': process.env.AGENTQL_API_KEY,
18        'Content-Type': 'application/json'
19    },
20    body: JSON.stringify({
21        query: "{ articles[] { title upvotes } }",
22        url,
23        params: {
24            wait_for: 0,
25            is_scroll_to_bottom_enabled: false,
26            mode: "fast",
27            is_screenshot_enabled: false
28        }
29    })
30});
31const data = await response.json();
32
33// Save headings to Dataset - a table-like storage.
34await Actor.pushData(data);
35
36// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit().
37await 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

{
    "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"
}