如何抓取 GOV.UK | 英国政府网站爬虫指南

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    try:
        page.goto('https://www.gov.uk/search/all?keywords=data+protection')
        page.wait_for_selector('.gem-c-document-list__item')
        titles = page.locator('.gem-c-document-list__item-title').all_text_contents()
        for t in titles:
            print(f'已提取: {t.strip()}')
    finally:
        browser.close()

import scrapy

class GovSpider(scrapy.Spider):
    name = 'gov_spider'
    start_urls = ['https://www.gov.uk/search/news-and-communications']
    
    def parse(self, response):
        for article in response.css('.gem-c-document-list__item'):
            yield {
                'title': article.css('.gem-c-document-list__item-title::text').get().strip(),
                'link': response.urljoin(article.css('a::attr(href)').get())
            }
        next_page = response.css('a[rel="next"]::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();
    try {
        await page.goto('https://www.gov.uk/search/news-and-communications', { waitUntil: 'networkidle2' });
        const results = await page.evaluate(() => 
            Array.from(document.querySelectorAll('.gem-c-document-list__item-title'))
            .map(el => el.innerText.trim())
        );
        console.log(results);
    } finally {
        await browser.close();
    }
})();