? ????? ?????? ???? ???? ?? ??? ?????. Google? Node.js? ???? ???? ?????? Puppeteer? ???? ??? ?? ??? ????? ??? ??, ?? ??, ?? ?? ????? ???? ? ????. ? ???? Puppeteer? ??? ? ????? ?? ??? ???? ???? ?? ??? ???? ?????.

????? ??????

Puppeteer? Google Chrome(?? Chromium)? ???? ??? ??? ? ?? Node.js ????????. ???? ????? ??? ??? ?????(GUI) ?? ????? ????? ?? ??? ??? ? ??? ?????. ??? Puppeteer? ????? ?? ?? ???? ??? ???? ?? ?? ?? ???? ???? ??? ?? ????.

? ????? ?? Puppeteer? ???? ??? ??????

???: Puppeteer? ?? ????? ?? ??? ??????(SPA)? ?? ?????.
JavaScript ??: ?? ? ?? ?????? ? ???? ????? JavaScript? ?????.
??? ??: ?? ??, ?? ??, ???? ?? ?? ??? ??? ? ????.

Puppeteer? ?? ??? ??

????? ???? ? IP ??? ??? ????? ??? ???? ?????? ???? ??????. ???? ?????? ?? ???? ??? ??? ??? ?? ?? IP ??? ??????. Puppeteer? ?? ???? ?? ??? ???? ?? ??? ? ????.

??????
?? ??
const ???? = puppeteer.launch({
? ?????. ??: ['--proxy-server=your-proxy-server:port']
});
???? ???? ??? ???? ? ?? ?????. ?? ???? ? ??? ?? IP?? ??? ???? ?? ???? ????. ????? ??? ??? ???? ? ??? ???? ? ??? ??, ??? ?? ???? ? ??? ?????. ??? ???? ?? ??? ?? ??? ???? ?? ??? ????? ???? ?????.

??? ??

????? ???? ?? Puppeteer? ???? ???. ??? ????? ???????.
1??: Node.js ? Puppeteer ??
Node.js ??: ?? ?????? Node.js? ?????? ?????.
Puppeteer ??: ???? ?? ?? ??? ??????.
??
?? ??
npm ?? ???

??? ?? ???? ??????? Puppeteer? Chromium? ?????.
2??: ? ??? ???? ??
??? JavaScript ??? scraper.js? ????. ???? ???? ??? ?????. ????? ?? ??? ???? ??? ????? ??? ?????.
??????
?? ??
const puppeteer = require('puppeteer');

(??? () => {
const ???? = puppeteer.launch()? ?????;
const ??? = browser.newPage()? ?????;

// ????? ??
page.goto('https://example.com')? ?????.

//?? ??
const title = ???? ?????.??();
console.log(??? ??: ${title});

browser.close()? ?????.
})();

??? ???? ????? ?????.
??
?? ??
?? scraper.js

? ?? Puppeteer ?????? ???????!

????? ?? ?? ??? ??

?? ?? ??? ????? ????? ??? ? ?? ?? Puppeteer ??? ???????.

1. ??? ??
   page.goto(url) ???? ???? ?? URL? ? ? ????. ??? ?? ?? ?? ??? ?? ??? ?????.
   ??????
   ?? ??
   wait page.goto('https://example.com', { timeout: 60000 });

2. ?? ??
   CSS ???? ???? ???? ??? ?????. Puppeteer? ??? ?? ??? ?????.
   ? ?? ??? ?? page.$(selector)
   ?? ?? ??? ?? page.$$(selector)
   ?:
   ??????
   ?? ??
   const ?? = ???? ?????.$('h1');
   const text = ???? ?????.evaluate(el => el.textContent, element);
   console.log(??: ${text});

3. ???? ????
   ??, ?? ?? ??? ?? ??? ????????.
   ??????
   ?? ??
   ???? ?????.click('#submit-button');
   wait page.type('#search-box', 'Puppeteer scraping');

4. ??? ???? ?
   ????? ??? ??? ?????. Puppeteer? ???? ???? ?? ??? ??? ? ????.
   ??????
   ?? ??
   ???? ?????.waitForSelector('#dynamic-content');

5. ???? ??
   ???? ????? ???? ???? ???? ?? ????.
   ??????
   ?? ??
   wait page.screenshot({ ??: 'screenshot.png', fullPage: true });

?? ??? ??

??? ?? ??????? JavaScript? ???? ???? ???? ?????. Puppeteer? JavaScript? ???? ??? ??? ???? ?? ? ?? ???? ???? ? ??? ??? ?? ????.
?: ?? ??? ??
??????
?? ??
page.goto('https://news.ycombinator.com')? ?????;
???? ?????.waitForSelector('.storylink');

const headlines = ???? ?????.$$eval('.storylink',links =>links.map(link=>link.textContent));
console.log('Headlines:', headlines);

CAPTCHA ? ? ?? ??

?? ?????? ?? ???? ??? ???? ????. Puppeteer? ??? ??? ???? ? ??? ? ? ????.
??? ?? ??: puppeteer-extra ???? ??:
??
?? ??
npm install puppeteer-extra puppeteer-extra-plugin-stealth
????? ?????:
??????
?? ??
const puppeteer = require('puppeteer-extra');
const StealthPlugin = require('puppeteer-extra-plugin-stealth');
puppeteer.use(StealthPlugin());

?? ?? ??: ??? ???, ??? ?? ?? ??? ???? ???? ?? ????? ???? ???.
??? ???? ??: ??? ?? ??? ????? ??? ????? ?????.
??????
?? ??
wait page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64)');

???? ??? ??

???? ??? ??? ???? ?? ????. ??? ? ?? ???? ?????.
JSON:
??????
?? ??
const fs = require('fs');
const data = { ??: 'Puppeteer', ??: 'library' };
fs.writeFileSync('data.json', JSON.stringify(data, null, 2));

CSV: csv-writer? ?? ????? ??:
??
?? ??
npm csv-writer ??
??????
?? ??
const createCsvWriter = require('csv-writer').createObjectCsvWriter;

const csvWriter = createCsvWriter({
??: 'data.csv',
??: [
{ id: '??', title: '??' },
{ id: '??', ??: '??' }
]
});

const records = [{ ??: 'Puppeteer', ??: 'library' }];
csvWriter.writeRecords(records).then(() => console.log('CSV ??? ???????.'));
???? ? ???? ??
????? ????? ?? ?? ??? ??? ??? ????.
??? ??? ?????. ?????? ????? ????? ?? ?????.
?? ?? ??: ?? ??? ?? ?? ??? ??? ????. setTimeout ?? Puppeteer? page.waitForTimeout()? ???? ?? ??? ?????.
??????
?? ??
???? ?????.waitForTimeout(2000); // 2?? ??

??? ??? ??: ?? ??? ??? ??? ?? ????? ???.

???? ?? ??

???? ??? ???? ????. ?? ??? ? ?? ????? ?? ???? ??? ???? ???.
??????
?? ??
const ???? = puppeteer.launch({ headless: false });

? ?????.

???? ???? ??: ???? ??? ??(Ctrl Shift C)? ???? ????? ???? ???? ?????.
CAPTCHA? ?? ???: ??? ????? ???? ??? ??? ?????.

?? ?? ??(FAQ)

1. Puppeteer? ?????? ?, Puppeteer? ?? ???? ??? ??? ? ????.
2. Puppeteer? JavaScript? ?? ????? ???? ? ???? ????! Puppeteer? JavaScript? ????? ?? ???? ????? ? ?????.
3. ? ????? ?????? ??? ?? ????. ????? ?? ?? ????? ??? ??? ?????.
4. Puppeteer? CAPTCHA? ??? ? ???? Puppeteer? ???? ?? ?? ??? ??? ? ??? ?? ?? ???? ?? ??? ??? ? ????.

? ??? Puppeteer? ? ????? ??: ????? ??? ???? ?? ?????. ??? ??? PHP ??? ????? ?? ?? ??? ?????!