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

# 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": "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"]
}

1import puppeteer from 'puppeteer';
2
3export const main = async (input) => {
4    const { loginUrl, chatbotUrl, username, password, url } = input;
5
6    if (!url) {
7        throw new Error('URL is required in the input.');
8    } else {
9        url = 'https://chatgpt.com/g/g-27hjeHzWx-motion-ai-chatbot-assistant'
10    }
11
12    const browser = await puppeteer.launch({ headless: true });
13    const page = await browser.newPage();
14    await page.goto(loginUrl, { waitUntil: 'networkidle0' });
15    await page.type('input[name="email"]', username);
16    await page.type('input[name="password"]', password);
17    await page.click('button[type="submit"]');
18    await page.waitForNavigation({ waitUntil: 'networkidle0' });
19    await page.goto(chatbotUrl, { waitUntil: 'networkidle0' });
20    const content = await page.content();
21    await browser.close();
22    return { content };
23};

# 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": "my-actor",
  "version": "1.0.0",
  "description": "My custom actor",
  "main": "src/main.js",
  "scripts": {
    "start": "node src/main.js"
  },
  "dependencies": {
    "puppeteer": "^19.0.0"
  },
  "type": "module"
}