# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git


.dockerignore

.env.copy

.gitignore

youtube-channel

package.json

# Specify the base Docker image. You can read more about
# the available images at https://sdk.apify.com/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 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


.actor/Dockerfile

Youtube Channels
================

# Description

Get the videos id, title and links from a Youtube page. Multiple Youtube urls in one run.

# Input

Urls array input format : https://www.youtube.com/@page

# Result


    [
        {
            "title": "Channel1 - YouTube",
            "videos": [
                {
                    "id": "RfTgYhUU791",
                    "url": "https://www.youtube.com/watch?v=RfTgYhUU791",
                    "title": "Video one of page"
                },
                {
                    "id": "RfTgYhUU792",
                    "url": "https://www.youtube.com/watch?v=RfTgYhUU792",
                    "title": "Video two of page"
                },
                {
                    "id": "RfTgYhUU793",
                    "url": "https://www.youtube.com/watch?v=RfTgYhUU793",
                    "title": "Video three of page"
                },
                {
                    "id": "RfTgYhUU794",
                    "url": "https://www.youtube.com/watch?v=RfTgYhUU794",
                    "title": "Video four of page"
                },
                
                ...
            ]
        },
        {
            "title": "Channel2 - YouTube",
            "videos": [
                {
                    "id": "RfTgYhUU791",
                    "url": "https://www.youtube.com/watch?v=RfTgYhUU791",
                    "title": "Video one of page"
                },
                {
                    "id": "RfTgYhUU792",
                    "url": "https://www.youtube.com/watch?v=RfTgYhUU792",
                    "title": "Video two of page"
                },
                {
                    "id": "RfTgYhUU793",
                    "url": "https://www.youtube.com/watch?v=RfTgYhUU793",
                    "title": "Video three of page"
                },
                {
                    "id": "RfTgYhUU794",
                    "url": "https://www.youtube.com/watch?v=RfTgYhUU794",
                    "title": "Video four of page"
                },
                
                ...
            ]
        }
    ]

.actor/README.md

Get the videos id, title and links from a Youtube channel. Multiple Youtube urls in one run.

Youtube Channels

.actor/actor.json

Youtube

Youtube Page

.actor/dataset_schema.json

Youtube page url, format : https://www.youtube.com/@page

urls

data

.actor/input_schema.json

actor
=====

https://docs.apify.com/cli/

https://docs.apify.com/platform/actors/development/input-schema

https://blog.apify.com/how-to-scrape-the-web-with-playwright-ece1ced75f73/

# start

    npx apify-cli run
    npx apify-cli login
    
https://console.apify.com/account/integrations
    
    npx apify-cli push
    
# create

    npx apify-cli create

# build

    npx playwright codegen https://www.youtube.com/@yvessaintlaurent
    


doc/DEV.md

import dotenv from "dotenv";
dotenv.config();
const dev =
  typeof process.env.APP_ENVIRONMENT !== "undefined"
    ? process.env.APP_ENVIRONMENT
    : false;

import { Actor } from "apify";
import { PlaywrightCrawler, Configuration, Dataset } from "crawlee";

await Actor.init();

// For more information, see https://sdk.apify.com/

const input = await Actor.getInput();
//let { urls } = input;
let urls;
//urls = typeof (input?.urls) == 'undefined' ? ["https://www.youtube.com/@yvessaintlaurent"] : input?.urls
// urls =
//   (typeof input == "undefined" || null)
//     ? ["https://www.youtube.com/@yvessaintlaurent"]
//     : input?.urls;

if (input == null) urls = [
  "https://www.youtube.com/@yvessaintlaurent",
  "https://www.youtube.com/@chanel"
];
else urls = input?.urls;

console.log("----");
console.log("urls: ", urls);
console.log("----");

if (dev) Configuration.set("headless", false); // dev

const crawler = new PlaywrightCrawler({
  requestHandler: async ({ request, page, infiniteScroll, enqueueLinks }) => {
    if (dev) page.setViewportSize({ width: 900, height: 400 }); // dev

    if (dev) await page.waitForTimeout(1000);

    if (dev) await page.click("button");

    const title = await page.title();
    console.log(title);
    console.log("----");

    await infiniteScroll({
      //buttonSelector: '',
      stopScrollCallback: async () => {
        const links = await page.$$(".yt-simple-endpoint");
        return links.length >= 40;
      },
    });

    //await page.waitForTimeout(1000);

    // const element = await page.locator('ytd-button-renderer').click();
    // await element.scrollIntoViewIfNeeded();
    // await element.click();

    // const selector = 'ytd-button-renderer'
    // await page.waitFor(selector, { state: 'visible' })
    // await page.click(selector);

    const links = await page.$$eval("a", (links) => {
      return links.map((link) => {
        return {
          url: link.href,
          title: link.title,
        };
      });
    });

    const links_selected = [];
    let id;
    let data = [],
      array_index = null;

    for (let i = 0; i < links.length; i++) {
      id = links[i].url.replace("https://www.youtube.com/watch?v=", "");
      if (
        links[i].url.includes("watch?") &&
        !links[i].url.includes("list=") &&
        !links_selected.includes(id)
      ) {
        //console.log('--hit--')
        // video link, keep id
        links_selected.push(id);
        data.push({
          id: id,
          url: links[i].url,
          title: links[i].title,
        });
      } else if (links_selected.includes(id)) {
        // id already exists, add title
        array_index = data.findIndex((x) => x.id === id);
        if (typeof data[array_index] !== "undefined")
          data[array_index].title = links[i].title;
      }
    }

    if (dev) console.log(data, links_selected.length);

    await Actor.pushData({
      title: title,
      videos: data,
    });

    //await enqueueLinks();
  },
});

// Process each URL
for (let url of urls) {
  await crawler.run([url]);
}

await Actor.exit();


src/main.js

Get the videos id, title and links from a Youtube page. Multiple Youtube urls in one fast run.

Fast Apify actor to get the videos from a Youtube channel.

Get Youtube videos from multiple @channels in one fast run

Where next?