Amazonのスクレイピング

npm install firecrawl zod

import { Firecrawl } from 'firecrawl';
import { z } from 'zod';

// Zodスキーマを定義
const ProductSchema = z.object({
    title: z.string(),
    price: z.string(),
    rating: z.number(),
    availability: z.string(),
    features: z.array(z.string())
});

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const result = await firecrawl.scrape('https://www.amazon.com/dp/B0DZZWMB2L', {
    formats: [{
        type: 'json',
        schema: z.toJSONSchema(ProductSchema)
    }],
});

// Zodでパースして検証
const jsonData = typeof result.json === 'string' ? JSON.parse(result.json) : result.json;
const validated = ProductSchema.parse(jsonData);

console.log('✅ 検証済み商品データ:');
console.log(validated);

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const searchResult = await firecrawl.search('gaming laptop site:amazon.com', {
    limit: 10,
    sources: [{ type: 'web' }], // { type: 'news' }, { type: 'images' }
    scrapeOptions: {
        formats: ['markdown']
    }
});

console.log(searchResult);

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const result = await firecrawl.scrape('https://www.amazon.com/ASUS-ROG-Strix-Gaming-Laptop/dp/B0DZZWMB2L', {
    formats: ['markdown'], // 例: html、links など
    onlyMainContent: true
});

console.log(result);

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const mapResult = await firecrawl.map('https://www.amazon.com/Best-Sellers-Electronics/zgbs/electronics');

console.log(mapResult.links);
// コンテンツなしでURLの配列を返す

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

const crawlResult = await firecrawl.crawl('https://www.amazon.com/s?k=mechanical+keyboards', {
    limit: 10,
    scrapeOptions: {
        formats: ['markdown']
    }
});

console.log(crawlResult.data);

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });

// 完了を待つ
const job = await firecrawl.batchScrape([
    'https://www.amazon.com/ASUS-ROG-Strix-Gaming-Laptop/dp/B0DZZWMB2L',
    'https://www.amazon.com/Razer-Blade-Gaming-Laptop-Lightweight/dp/B0FP47DNFQ',
    'https://www.amazon.com/HP-2025-Omen-Gaming-Laptop/dp/B0FL4RMGSH'],
    {
        options: {
            formats: ['markdown']
        },
        pollInterval: 2,
        timeout: 120
    }
);


console.log(job.status, job.completed, job.total);

console.log(job);