* imdb ( 영화 사이트 ) 스크래핑

 

출처 : www.youtube.com/watch?v=4q9CNtwdawA

 

 

스크래핑 대상 : www.imdb.com/title/tt0111161/?ref=nv_sr_1

The Shawshank Redemption (1994) - IMDb

 

 

타이틀 

css
<h1 class="">The Shawshank Redemption&nbsp;<span id="titleYear">
(<a href="/year/1994/?ref_=tt_ov_inf">1994</a>)</span>            </h1>

selector
#title-overview-widget > div.vital > div.title_block > div > div.titleBar > div.title_wrapper > h1

console 확인
document.querySelector('div[class="title_wrapper"] > h1').innerText
>>> The Shawshank Redemption (1994)

 

 

등급 

css 
<span itemprop="ratingValue">9.3</span>

selector
#title-overview-widget > div.vital > div.title_block > div > div.ratings_wrapper > 
div.imdbRating > div.ratingValue > strong > span

console 확인
document.querySelector('span[itemprop="ratingValue"]').innerText
>>> 9.3

 

 

리뷰 카운트

css 
<span class="small" itemprop="ratingCount">2,304,514</span>

selector
#title-overview-widget > div.vital > div.title_block > div > div.ratings_wrapper > 
div.imdbRating > a > span

console 확인
document.querySelector('span[itemprop="ratingCount"]').innerText
>>> 2,304,514

 

 

 

전체 소스

const puppeteer = require("puppeteer");

(async () => {
	let movieUrl = "https://www.imdb.com/title/tt0111161/?ref=nv_sr_1";

	//	 브라우저를 보기 원할때
    //	let browser = await puppeteer.launch({ headless: false });
    
    let browser = await puppeteer.launch();

	let page = await browser.newPage();

	await page.goto(movieUrl, { waitUntil: "networkidle2" });

	let data = await page.evaluate(() => {
		let title = document.querySelector('div[class="title_wrapper"] > h1').innerText;
		let rating = document.querySelector('span[itemprop="ratingValue"]').innerText;
		let ratingCount = document.querySelector('span[itemprop="ratingCount"]').innerText;

		return {
			title,
			rating,
			ratingCount,
		};
	});

	console.log(data);

	await browser.close();
})();