GitHub のスクレイピング

npm install firecrawl zod

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

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

const result = await firecrawl.scrape('https://github.com/firecrawl/firecrawl', {
    formats: [{
        type: 'json',
        schema: z.object({
            name: z.string(),
            description: z.string(),
            stars: z.number(),
            forks: z.number(),
            language: z.string(),
            topics: z.array(z.string())
        })
    }]
});

console.log(result.json);

import { Firecrawl } from 'firecrawl';

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

const searchResult = await firecrawl.search('machine learning site:github.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 results = await firecrawl.research.searchGithub(
    'how to handle rate limit retries with exponential backoff',
    { k: 10 }
);

console.log(results);

import { Firecrawl } from 'firecrawl';

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

const searchResult = await firecrawl.search('exponential backoff retry', {
    categories: ['github'],
    limit: 10
});

console.log(searchResult);

import { Firecrawl } from 'firecrawl';

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

const result = await firecrawl.scrape('https://github.com/firecrawl/firecrawl', {
    formats: ['markdown'] // 例: html, links など
});

console.log(result);

import { Firecrawl } from 'firecrawl';

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

const mapResult = await firecrawl.map('https://github.com/vercel/next.js/tree/canary/docs');

console.log(mapResult.links);
// コンテンツなしの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://github.com/facebook/react/wiki', {
    limit: 10,
    scrapeOptions: {
        formats: ['markdown']
    }
});

console.log(crawlResult.data);

import { Firecrawl } from 'firecrawl';

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

// 完了を待機
const job = await firecrawl.batchScrape([
    'https://github.com/vercel/next.js',
    'https://github.com/facebook/react',
    'https://github.com/microsoft/typescript'],
    {
        options: {
            formats: ['markdown']
        },
        pollInterval: 2,
        timeout: 120
    }
);


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

console.log(job);

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

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

// 完了を待機
const job = await firecrawl.batchScrape([
    'https://github.com/vercel/next.js',
    'https://github.com/facebook/react'],
    {
        options: {
            formats: [{
                type: 'json',
                schema: z.object({
                    name: z.string(),
                    description: z.string(),
                    stars: z.number(),
                    language: z.string()
                })
            }]
        },
        pollInterval: 2,
        timeout: 120
    }
);


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

console.log(job);