如何抓取 Goodreads：2025 终极网络抓取指南

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    # 对于 Cloudflare/JS 页面，必须启动浏览器
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    page.goto('https://www.goodreads.com/search?q=fantasy')
    # 等待特定的 data 属性渲染完成
    page.wait_for_selector('[data-testid="bookTitle"]')
    
    books = page.query_selector_all('.bookTitle')
    for book in books:
        print(book.inner_text().strip())
    
    browser.close()

import scrapy

class GoodreadsSpider(scrapy.Spider):
    name = 'goodreads_spider'
    start_urls = ['https://www.goodreads.com/list/show/1.Best_Books_Ever']

    def parse(self, response):
        # 针对 schema.org 标记以获得更稳定的选择器
        for book in response.css('tr[itemtype="http://schema.org/Book"]'):
            yield {
                'title': book.css('.bookTitle span::text').get(),
                'author': book.css('.authorName span::text').get(),
                'rating': book.css('.minirating::text').get(),
            }
        
        # 标准分页处理
        next_page = response.css('a.next_page::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();
  // Goodreads 使用现代 JS，因此我们需要等待特定组件加载
  await page.goto('https://www.goodreads.com/book/show/1.Harry_Potter');
  await page.waitForSelector('[data-testid="bookTitle"]');
  
  const data = await page.evaluate(() => ({
    title: document.querySelector('[data-testid="bookTitle"]').innerText,
    author: document.querySelector('[data-testid="name"]').innerText,
    rating: document.querySelector('.RatingStatistics__rating').innerText
  }));
  
  console.log(data);
  await browser.close();
})();