{"id":3379,"date":"2022-09-21T18:44:02","date_gmt":"2022-09-21T13:44:02","guid":{"rendered":"https:\/\/www.edopedia.com\/blog\/?p=3379"},"modified":"2022-09-21T18:44:02","modified_gmt":"2022-09-21T13:44:02","slug":"how-to-scrape-youtube-video-using-node-js-express-puppeteer","status":"publish","type":"post","link":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/","title":{"rendered":"How To Scrape YouTube Video Using Node.js Express Puppeteer"},"content":{"rendered":"\n

Install Dependencies<\/h2>\n\n\n\n
npm init -y<\/pre><\/div>\n\n\n\n
npm i express<\/pre><\/div>\n\n\n\n
npm i puppeteer<\/pre><\/div>\n\n\n\n
npm i ejs<\/pre><\/div>\n\n\n\n
npm i google-search-results-nodejs<\/pre><\/div>\n\n\n\n
npm i puppeteer-extra<\/pre><\/div>\n\n\n\n
npm i puppeteer-extra-plugin-stealth<\/pre><\/div>\n\n\n\n
\n\n\n\n
code.js<\/h2>\n\n\n\n
const puppeteer = require("puppeteer-extra");\nconst StealthPlugin = require("puppeteer-extra-plugin-stealth");\npuppeteer.use(StealthPlugin());\nconst videoLink = "https:\/\/www.youtube.com\/watch?v=6qpXszX_ixw"; \/\/ link to video page\nasync function scrollPage(page, scrollContainer) {\n  let lastHeight = await page.evaluate(`document.querySelector("${scrollContainer}").scrollHeight`);\n  while (true) {\n    await page.evaluate(`window.scrollTo(0, document.querySelector("${scrollContainer}").scrollHeight)`);\n    await page.waitForTimeout(2000);\n    let newHeight = await page.evaluate(`document.querySelector("${scrollContainer}").scrollHeight`);\n    if (newHeight === lastHeight) {\n      break;\n    }\n    lastHeight = newHeight;\n  }\n}\nasync function fillDataFromPage(page, newDesign) {\n  const dataFromPage = await page.evaluate((newDesign) => {\n    const date = document\n      .querySelector(newDesign ? "#description-inline-expander > yt-formatted-string span:nth-child(3)" : "#info-strings yt-formatted-string")\n      ?.textContent.trim();\n    const views = document\n      .querySelector(newDesign ? "#description-inline-expander > yt-formatted-string span:nth-child(1)" : "#info-text #count")\n      ?.textContent.trim();\n    return {\n      title: document.querySelector(`${newDesign ? "#title >" : "#info-contents"} h1`)?.textContent.trim(),\n      likes: parseInt(\n        document\n          .querySelector(`${newDesign ? "#top-row" : "#menu"} #top-level-buttons-computed > ytd-toggle-button-renderer:first-child #text`)\n          ?.getAttribute("aria-label")\n          .replace(",", "")\n      ),\n      channel: {\n        name: document.querySelector(`${newDesign ? "#owner" : "ytd-video-owner-renderer"} #channel-name #text > a`)?.textContent.trim(),\n        link: `https:\/\/www.youtube.com${document.querySelector(`${newDesign ? "#owner" : ""} ytd-video-owner-renderer > a`)?.getAttribute("href")}`,\n        thumbnail: document.querySelector(`${newDesign ? "#owner" : "ytd-video-owner-renderer"} #avatar #img`)?.getAttribute("src"),\n      },\n      date,\n      views: views && parseInt(views.replace(",", "")),\n      description: newDesign\n        ? document.querySelector("#description-inline-expander > yt-formatted-string")?.textContent.replace(date, "").replace(views, "").trim()\n        : document.querySelector("#meta #description")?.textContent.trim(),\n      duration: document.querySelector(".ytp-time-duration")?.textContent.trim(),\n      hashtags: Array.from(document.querySelectorAll(`${newDesign ? "#super-title" : "#info-contents .super-title"} a`)).map((el) =>\n        el.textContent.trim()\n      ),\n      suggestedVideos: Array.from(document.querySelectorAll("ytd-compact-video-renderer")).map((el) => ({\n        title: el.querySelector("#video-title")?.textContent.trim(),\n        link: `https:\/\/www.youtube.com${el.querySelector("#thumbnail")?.getAttribute("href")}`,\n        channelName: el.querySelector("#channel-name #text")?.textContent.trim(),\n        date: el.querySelector("#metadata-line span:nth-child(2)")?.textContent.trim(),\n        views: el.querySelector("#metadata-line span:nth-child(1)")?.textContent.trim(),\n        duration: el.querySelector("#overlays #text")?.textContent.trim(),\n        thumbnail: el.querySelector("#img")?.getAttribute("src"),\n      })),\n      comments: Array.from(document.querySelectorAll("#contents > ytd-comment-thread-renderer")).map((el) => ({\n        author: el.querySelector("#author-text")?.textContent.trim(),\n        link: `https:\/\/www.youtube.com${el.querySelector("#author-text")?.getAttribute("href")}`,\n        date: el.querySelector(".published-time-text")?.textContent.trim(),\n        likes: el.querySelector("#vote-count-middle")?.textContent.trim(),\n        comment: el.querySelector("#content-text")?.textContent.trim(),\n        avatar: el.querySelector("#author-thumbnail #img")?.getAttribute("src"),\n      })),\n    };\n  }, newDesign);\n  return dataFromPage;\n}\nasync function getYoutubeVideoPageResults() {\n  const browser = await puppeteer.launch({\n    headless: false,\n    args: ["--no-sandbox", "--disable-setuid-sandbox"],\n  });\n  const page = await browser.newPage();\n  await page.setDefaultNavigationTimeout(60000);\n  await page.goto(videoLink);\n  await page.waitForSelector("#contents");\n  const isDesign1 = await page.$("#title > h1");\n  if (isDesign1) {\n    await page.click("#description-inline-expander #expand");\n  } else {\n    await page.click("#meta #more");\n  }\n  const scrollContainer = "ytd-app";\n  await scrollPage(page, scrollContainer);\n  await page.waitForTimeout(10000);\n  const infoFromVideoPage = await fillDataFromPage(page, isDesign1);\n  await browser.close();\n  return infoFromVideoPage;\n}\ngetYoutubeVideoPageResults().then((result) => console.dir(result, { depth: null }));<\/pre><\/div>\n","protected":false},"excerpt":{"rendered":"
Install Dependencies code.js<\/p>\n","protected":false},"author":1,"featured_media":1762,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[112],"tags":[],"class_list":["post-3379","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tutorials"],"yoast_head":"\nHow To Scrape YouTube Video Using Node.js Express Puppeteer<\/title>\n<meta name=\"description\" content=\"Install Dependencies npm init -y npm i express npm i puppeteer npm i ejs npm i google-search-results-nodejs npm i puppeteer-extra npm i\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How To Scrape YouTube Video Using Node.js Express Puppeteer\" \/>\n<meta property=\"og:description\" content=\"Install Dependencies npm init -y npm i express npm i puppeteer npm i ejs npm i google-search-results-nodejs npm i puppeteer-extra npm i\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/\" \/>\n<meta property=\"og:site_name\" content=\"Edopedia\" \/>\n<meta property=\"article:author\" content=\"trulyfurqan\" \/>\n<meta property=\"article:published_time\" content=\"2022-09-21T13:44:02+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.edopedia.com\/blog\/wp-content\/uploads\/2022\/02\/default_featured_image.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"880\" \/>\n\t<meta property=\"og:image:height\" content=\"495\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Furqan\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Furqan\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"How To Scrape YouTube Video Using Node.js Express Puppeteer","description":"Install Dependencies npm init -y npm i express npm i puppeteer npm i ejs npm i google-search-results-nodejs npm i puppeteer-extra npm i","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/","og_locale":"en_US","og_type":"article","og_title":"How To Scrape YouTube Video Using Node.js Express Puppeteer","og_description":"Install Dependencies npm init -y npm i express npm i puppeteer npm i ejs npm i google-search-results-nodejs npm i puppeteer-extra npm i","og_url":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/","og_site_name":"Edopedia","article_author":"trulyfurqan","article_published_time":"2022-09-21T13:44:02+00:00","og_image":[{"width":880,"height":495,"url":"https:\/\/www.edopedia.com\/blog\/wp-content\/uploads\/2022\/02\/default_featured_image.jpg","type":"image\/jpeg"}],"author":"Furqan","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Furqan","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/#article","isPartOf":{"@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/"},"author":{"name":"Furqan","@id":"https:\/\/www.edopedia.com\/blog\/#\/schema\/person\/3951cb19e3aa56df09e408c98aa02339"},"headline":"How To Scrape YouTube Video Using Node.js Express Puppeteer","datePublished":"2022-09-21T13:44:02+00:00","mainEntityOfPage":{"@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/"},"wordCount":14,"commentCount":0,"publisher":{"@id":"https:\/\/www.edopedia.com\/blog\/#organization"},"image":{"@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/#primaryimage"},"thumbnailUrl":"https:\/\/www.edopedia.com\/blog\/wp-content\/uploads\/2022\/02\/default_featured_image.jpg","articleSection":["Tutorials"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/","url":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/","name":"How To Scrape YouTube Video Using Node.js Express Puppeteer","isPartOf":{"@id":"https:\/\/www.edopedia.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/#primaryimage"},"image":{"@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/#primaryimage"},"thumbnailUrl":"https:\/\/www.edopedia.com\/blog\/wp-content\/uploads\/2022\/02\/default_featured_image.jpg","datePublished":"2022-09-21T13:44:02+00:00","description":"Install Dependencies npm init -y npm i express npm i puppeteer npm i ejs npm i google-search-results-nodejs npm i puppeteer-extra npm i","breadcrumb":{"@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/#primaryimage","url":"https:\/\/www.edopedia.com\/blog\/wp-content\/uploads\/2022\/02\/default_featured_image.jpg","contentUrl":"https:\/\/www.edopedia.com\/blog\/wp-content\/uploads\/2022\/02\/default_featured_image.jpg","width":880,"height":495,"caption":"Default Featured Image"},{"@type":"BreadcrumbList","@id":"https:\/\/www.edopedia.com\/blog\/how-to-scrape-youtube-video-using-node-js-express-puppeteer\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.edopedia.com\/blog\/"},{"@type":"ListItem","position":2,"name":"How To Scrape YouTube Video Using Node.js Express Puppeteer"}]},{"@type":"WebSite","@id":"https:\/\/www.edopedia.com\/blog\/#website","url":"https:\/\/www.edopedia.com\/blog\/","name":"Edopedia","description":"Coding\/Programming Blog","publisher":{"@id":"https:\/\/www.edopedia.com\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.edopedia.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.edopedia.com\/blog\/#organization","name":"Edopedia","url":"https:\/\/www.edopedia.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.edopedia.com\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.edopedia.com\/blog\/wp-content\/uploads\/2017\/10\/edopedia_icon_text_10.jpg","contentUrl":"https:\/\/www.edopedia.com\/blog\/wp-content\/uploads\/2017\/10\/edopedia_icon_text_10.jpg","width":400,"height":100,"caption":"Edopedia"},"image":{"@id":"https:\/\/www.edopedia.com\/blog\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/www.edopedia.com\/blog\/#\/schema\/person\/3951cb19e3aa56df09e408c98aa02339","name":"Furqan","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/e5e68aef3ad8f0b83d56f4953c512c8e57bd2e6dc64daec33b5d0495d9058f51?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/e5e68aef3ad8f0b83d56f4953c512c8e57bd2e6dc64daec33b5d0495d9058f51?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/e5e68aef3ad8f0b83d56f4953c512c8e57bd2e6dc64daec33b5d0495d9058f51?s=96&d=mm&r=g","caption":"Furqan"},"description":"Well. I've been working for the past three years as a web designer and developer. I have successfully created websites for small to medium sized companies as part of my freelance career. During that time I've also completed my bachelor's in Information Technology.","sameAs":["http:\/\/www.edopedia.com\/blog\/","trulyfurqan"],"url":"https:\/\/www.edopedia.com\/blog\/author\/furqan\/"}]}},"_links":{"self":[{"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/posts\/3379","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/comments?post=3379"}],"version-history":[{"count":1,"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/posts\/3379\/revisions"}],"predecessor-version":[{"id":3450,"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/posts\/3379\/revisions\/3450"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/media\/1762"}],"wp:attachment":[{"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/media?parent=3379"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/categories?post=3379"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.edopedia.com\/blog\/wp-json\/wp\/v2\/tags?post=3379"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}