如何爬取 Bilregistret.ai：瑞典车辆数据提取指南

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        # Launching browser with headless=True for performance
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto("https://www.bilregistret.ai/biluppgifter/ABC123")
        
        # Wait for the main vehicle info container to render
        page.wait_for_selector("h1")
        
        # Extract the model title from the page
        data = page.evaluate("() => { return document.querySelector('h1').innerText; }")
        print(f"Extracted Model: {data}")
        
        browser.close()

run()

import scrapy
import json

class BilregistretSpider(scrapy.Spider):
    name = 'bilregistret'
    start_urls = ['https://www.bilregistret.ai/biluppgifter/ABC123']

    def parse(self, response):
        # Extracting data from the Next.js state script tag for reliability
        json_data = response.xpath('//script[@id="__NEXT_DATA__"]/text()').get()
        if json_data:
            data = json.loads(json_data)
            # Yielding the pageProps as an item
            yield data['props']['pageProps']['initialData']
        
        # Example of discovering more cars via links
        for car_link in response.css('a[href*="/biluppgifter/"]::attr(href)').getall():
            yield response.follow(car_link, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  
  // Navigate to a specific vehicle page
  await page.goto('https://www.bilregistret.ai/biluppgifter/ABC123');
  
  // Handle Next.js rendering by waiting for the h1 element
  await page.waitForSelector('h1');
  
  const vehicleData = await page.evaluate(() => {
    return {
      title: document.querySelector('h1').innerText,
      specs: Array.from(document.querySelectorAll('td')).map(td => td.innerText)
    };
  });
  
  console.log(vehicleData);
  await browser.close();
})();