Hacker News (news.ycombinator.com) のスクレイピング方法

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    page.goto('https://news.ycombinator.com/')
    
    # テーブルの読み込みを待機
    page.wait_for_selector('.athing')
    
    # すべてのストーリーのタイトルとリンクを抽出
    items = page.query_selector_all('.athing')
    for item in items:
        title_link = item.query_selector('.titleline > a')
        if title_link:
            print(title_link.inner_text(), title_link.get_attribute('href'))
            
    browser.close()

import scrapy

class HackerNewsSpider(scrapy.Spider):
    name = 'hn_spider'
    start_urls = ['https://news.ycombinator.com/']

    def parse(self, response):
        # 投稿が含まれるクラス '.athing' をループ処理
        for post in response.css('.athing'):
            yield {
                'id': post.attrib.get('id'),
                'title': post.css('.titleline > a::text').get(),
                'link': post.css('.titleline > a::attr(href)').get(),
            }
        
        # ページネーションの 'More' リンクを辿る
        next_page = response.css('a.morelink::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  await page.goto('https://news.ycombinator.com/');
  
  const results = await page.evaluate(() => {
    // 各投稿アイテムを抽出
    const items = Array.from(document.querySelectorAll('.athing'));
    return items.map(item => ({
      title: item.querySelector('.titleline > a').innerText,
      url: item.querySelector('.titleline > a').href
    }));
  });

  console.log(results);
  await browser.close();
})();