xkcdコミックのスクレイピング方法：APIとウェブスクレイピングガイド

from playwright.sync_api import sync_playwright

def scrape_with_playwright(comic_id):
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto(f'https://xkcd.com/{comic_id}/')
        
        # コミック要素がロードされるのを待機
        page.wait_for_selector('#comic img')
        
        title = page.inner_text('#ctitle')
        img_src = page.get_attribute('#comic img', 'src')
        alt_text = page.get_attribute('#comic img', 'title')
        
        print(f'Comic {comic_id}: {title}')
        print(f'Alt Text: {alt_text}')
        
        browser.close()

scrape_with_playwright(2500)

import scrapy

class XkcdSpider(scrapy.Spider):
    name = 'xkcd_spider'
    start_urls = ['https://xkcd.com/1/']

    def parse(self, response):
        yield {
            'num': response.url.split('/')[-2],
            'title': response.css('#ctitle::text').get(),
            'img_url': response.urljoin(response.css('#comic img::attr(src)').get()),
            'alt': response.css('#comic img::attr(title)').get()
        }

        # 「Next」ボタンを辿ってアーカイブ全体をクロールする
        next_page = response.css('a[rel="next"]::attr(href)').get()
        if next_page and 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://xkcd.com/614/');

  const comicData = await page.evaluate(() => {
    const img = document.querySelector('#comic img');
    return {
      title: document.querySelector('#ctitle').innerText,
      imgUrl: img.src,
      altText: img.title
    };
  });

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