.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

Crawlee and Playwright project in JavaScript.

my-actor

Project Playwright Crawler JavaScript

.actor/actor.json

target Threads URLs

PlaywrightCrawler Template

.actor/input_schema.json

/**
 * This template is a production ready boilerplate for developing with `PlaywrightCrawler`.
 * Use this to bootstrap your projects using the most up-to-date code.
 * If you're looking for examples or want to learn more, see README.
 */

// For more information, see https://docs.apify.com/sdk/js
import { Actor } from 'apify';
// For more information, see https://crawlee.dev
import { PlaywrightCrawler, RequestQueue } from 'crawlee';

// Initialize the Apify SDK
await Actor.init();
const input = await Actor.getInput();
console.log(111, JSON.stringify(input))

const requestQueue = await RequestQueue.open();
await requestQueue.addRequest({ url: input.target || '' });
console.log(222)

const proxyConfiguration = await Actor.createProxyConfiguration();
const crawler = new PlaywrightCrawler({
    proxyConfiguration,
    requestQueue,
    async requestHandler({ request, page, log }) {
        log.info(`Processing ${request.url}...`);
        const title = await page.title();
        log.info(`${title}`, { url: request.loadedUrl });
        page.on('response', async req => {
            console.log(req.url())
            if (req.url() === 'https://www.threads.net/api/graphql') {
                const data = await req.json()
                log.info(JSON.stringify())
                await Actor.pushData(data.data.data)
                console.log('success, waiting to exit')
                await Actor.exit();
            }
        });
        await page.waitForTimeout(6000)
    },
});

await crawler.run();

// Exit successfully
await Actor.exit();


src/main.js

import { Dataset, createPlaywrightRouter } from 'crawlee';

export const router = createPlaywrightRouter();

router.addDefaultHandler(async ({ enqueueLinks, log }) => {
    log.info(`enqueueing new URLs`);
    await enqueueLinks({
        globs: ['https://apify.com/*'],
        label: 'detail',
    });
});

router.addHandler('detail', async ({ request, page, log }) => {
    const title = await page.title();
    log.info(`${title}`, { url: request.loadedUrl });

    await Dataset.pushData({
        url: request.loadedUrl,
        title,
    });
});


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

crawlee-playwright-javascript

package.json

Scrap a specific thread by input a thread url.  Such as "https://www.threads.net/t/CuZsgfWLyiI".

Meta Threads Scraper

Where next?