Test TikTok Top 10 TikTok Videos of the Day:

# 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

{
    "actorSpecification": 1,
    "name": "my-actor-1",
    "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"]
}

const axios = require('axios');
const cheerio = require('cheerio');

async function scrapeTopTikTokVideos() {
  try {
    const response = await axios.get('https://hypothetical-tiktok-website.com/top-videos');
    const $ = cheerio.load(response.data);

    const topVideos = [10];

    // Replace the selectors below with the appropriate ones for the hypothetical website's video elements
    $('div.video-item').each((index, element) => {
      const title = $(element).find('h2.title').text().trim();
      const url = $(element).find('a.video-link').attr('href');
      const timestamp = $(element).find('span.timestamp').text().trim();

      topVideos.push({
        title,
        url,
        timestamp,
      });

      // Limit to the top 10 videos
      if (topVideos.length === 10) {
        return false; // Exit the .each() loop
      }
    });

    return topVideos;
  } catch (error) {
    console.error('Error occurred during scraping:', error.message);
    return [];
  }
}

// Call the function to scrape the top 10 TikTok videos
scrapeTopTikTokVideos()
  .then((topVideos) => {
    console.log('Top 10 TikTok Videos of the Day:');
    topVideos.forEach((video, index) => {
      console.log(`${index + 1}. ${video.title}`);
      console.log(`   Posted At: ${video.timestamp}`);
      console.log(`   URL: ${video.url}`);
      console.log('-------------------------');
    });
  })
  .catch((error) => {
    console.error('Error occurred:', error.message);
  });

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// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init().
9await Actor.init();
10
11// Structure of input is defined in input_schema.json
12const input = await Actor.getInput();
13const { url } = input;
14
15// Fetch the HTML content of the page.
16const response = await axios.get(url);
17
18// Parse the downloaded HTML with Cheerio to enable data extraction.
19const $ = cheerio.load(response.data);
20
21// Extract all headings from the page (tag name and text).
22const headings = [];
23$("h1, h2, h3, h4, h5, h6").each((i, element) => {
24    const headingObject = {
25        level: $(element).prop("tagName").toLowerCase(),
26        text: $(element).text(),
27    };
28    console.log("Extracted heading", headingObject);
29    headings.push(headingObject);
30});
31
32// Save headings to Dataset - a table-like storage.
33await Actor.pushData(headings);
34
35// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit().
36await 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": "^3.0.0",
        "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"
}