.actor

# Specify the base Docker image. You can read more about
# the available images at https://crawlee.dev/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node-playwright-chrome:16

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


# Run the image. If you know you won't need headful browsers,
# you can remove the XVFB start script for a micro perf gain.
CMD ./start_xvfb_and_run_cmd.sh && npm start --silent


.actor/Dockerfile

Scrapes a given Tiktok username's profile for basic counts (followers, likes, following).

tiktok-profile-scraper

TikTok Profile Scraper

.actor/actor.json

Overview

.actor/dataset_schema.json

TikTok usernames (pure username, don't include the URL or @ symbol).

Usernames

TikTik Profile Scraper

.actor/input_schema.json

import { Actor } from 'apify';
import { PlaywrightCrawler } from 'crawlee';
import { router } from './routes.js';

await Actor.init();

const proxyConfiguration = await Actor.createProxyConfiguration();

const crawler = new PlaywrightCrawler({
    proxyConfiguration,
    requestHandler: router,
});

const input = await Actor.getInput();
await crawler.run(
    input.usernames.map(username => (
        { url: `https://www.tiktok.com/@${username}`, label: username }
    ))
);

await Actor.exit();


src/main.js

import { Dataset, createPlaywrightRouter } from 'crawlee';

const convertNumber = (value) => {
  var base = parseFloat(value);

  if (value.toLowerCase().match(/k/)) return Math.round(base * 1000);

  if (value.toLowerCase().match(/m/)) return Math.round(base * 1000000);
  
  if (value.toLowerCase().match(/b/)) return Math.round(base * 1000000000);
  
  return parseInt(value);
}

export const router = createPlaywrightRouter();

router.addDefaultHandler(async ({ request, page, log }) => {
    log.info(`Processing ${request.url}`);

    const titleElement = await page.locator("[data-e2e='user-title']")
    const titleElementCount = await titleElement.count()

    if (titleElementCount === 0) {
        return await Dataset.pushData({
            url: request.url,
            username: request.userData.label,
            error: 'Failed to load profile, check username is correct'
        });
    }

    const targets = [
        { selector: '[data-e2e="user-subtitle"]', attr: 'tagline' },
        { selector: '[data-e2e="following-count"]', attr: 'following', formatter: convertNumber },
        { selector: '[data-e2e="followers-count"]', attr: 'followers', formatter: convertNumber },
        { selector: '[data-e2e="likes-count"]', attr: 'likes', formatter: convertNumber },
        { selector: '[data-e2e="user-bio"]', attr: 'bio' },
        { selector: '[data-e2e="user-link"]', child: 'span', attr: 'link' },
        { imageSelector: '[data-e2e="user-avatar"]', child: '[data-e2e=""] > img', attr: 'image' },
    ];

    const scrapedData = {};
    const promises = await Promise.all(targets.map(async t => {
        let elm = await page.locator(t.selector || t.imageSelector);
        const elmCount = await elm.count()
        if (elmCount > 0 && t.child) {
            const child = await elm.locator(t.child);
            const childCount = await child.count();
            if (childCount > 0) {
                elm = child
            }
        }
        if (elmCount > 0) {
            const textValue = (t.imageSelector ? await elm.getAttribute('src') : await elm.textContent());
            const value = textValue.trim()
            log.debug(`${t.attr}: ${value}`)

            scrapedData[t.attr] = typeof t.formatter === 'function' ? {
                raw: value,
                formatted: t.formatter(value)
            } : value;

        } else {
            log.debug(`Could not find ${t.attr} element, using selector: ${t.selector}`);
            scrapedData[t.attr] = null;
        }
    }));
    
    await Dataset.pushData({
        url: request.url,
        username: request.userData.label,
        ...scrapedData,
    });
});


src/routes.js

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git


.dockerignore

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf


.editorconfig

{
    "extends": "@apify",
    "root": true
}


.eslintrc

# This file tells Git which files shouldn't be added to source control

.DS_Store
.idea
dist
node_modules
apify_storage
storage


.gitignore

package.json

Scrapes basic profile information from a TikTok page for a given username(s). Info includes name, tagline, bio, image URL, link and counts for followers, following & likes. Since we are not fetching videos this works successfully on both public & private profiles.

TikTok Profile Scraper · Apify

Input · TikTok Profile Scraper · Apify

API · TikTok Profile Scraper · Apify

Related Actors · TikTok Profile Scraper · Apify

Scrapes basic profile information from a TikTok page for a given username(s). Info includes name, tagline, bio, image URL, link and counts for followers, following & likes. Since we are not fetchin...

Where next?