批量抓取

from firecrawl import Firecrawl

firecrawl = Firecrawl(api_key="fc-YOUR-API-KEY")

# 异步：启动批量任务并立即返回任务 ID
start = firecrawl.start_batch_scrape([
    "https://firecrawl.dev",
    "https://docs.firecrawl.dev",
], formats=["markdown"])

status = firecrawl.get_batch_scrape_status(start.id)

# 或同步：启动批量任务并等待完成
job = firecrawl.batch_scrape([
    "https://firecrawl.dev",
    "https://docs.firecrawl.dev",
], formats=["markdown"], poll_interval=2, wait_timeout=120)

print(job.status, job.completed, job.total)

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: "fc-YOUR-API-KEY" });

// 异步：启动批量任务并立即返回任务 ID
const { id } = await firecrawl.startBatchScrape([
  'https://firecrawl.dev',
  'https://docs.firecrawl.dev'
], {
  options: { formats: ['markdown'] },
});

const status = await firecrawl.getBatchScrapeStatus(id);

// 或同步：启动批量任务并等待完成
const job = await firecrawl.batchScrape([
  'https://firecrawl.dev',
  'https://docs.firecrawl.dev'
], { options: { formats: ['markdown'] }, pollInterval: 2, timeout: 120 });

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

curl -s -X POST "https://api.firecrawl.dev/v2/batch/scrape" \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "urls": ["https://firecrawl.dev", "https://docs.firecrawl.dev"],
    "formats": ["markdown"]
  }'

from firecrawl import Firecrawl

firecrawl = Firecrawl(api_key="fc-YOUR_API_KEY")

# 抓取多个站点：
batch_scrape_result = firecrawl.batch_scrape(
    ['https://docs.firecrawl.dev', 'https://docs.firecrawl.dev/sdks/overview'], 
    formats=[{
        'type': 'json',
        'prompt': '提取页面的标题和描述。',
        'schema': {
            'type': 'object',
            'properties': {
                'title': {'type': 'string'},
                'description': {'type': 'string'}
            },
            'required': ['title', 'description']
        }
    }]
)
print(batch_scrape_result)

# 或者可以使用 start 方法：
batch_scrape_job = firecrawl.start_batch_scrape(
    ['https://docs.firecrawl.dev', 'https://docs.firecrawl.dev/sdks/overview'], 
    formats=[{
        'type': 'json',
        'prompt': '提取页面的标题和描述。',
        'schema': {
            'type': 'object',
            'properties': {
                'title': {'type': 'string'},
                'description': {'type': 'string'}
            },
            'required': ['title', 'description']
        }
    }]
)
print(batch_scrape_job)

# 然后可使用作业 ID 查询批量抓取的状态：
batch_scrape_status = firecrawl.get_batch_scrape_status(batch_scrape_job.id)
print(batch_scrape_status)

import { Firecrawl, ScrapeResponse } from 'firecrawl';

const firecrawl = new Firecrawl({apiKey: "fc-YOUR_API_KEY"});

// 定义用于提取内容的 schema
const schema = {
  type: "object",
  properties: {
    title: { type: "string" },
    description: { type: "string" }
  },
  required: ["title", "description"]
};

// 抓取多个网站（同步）：
const batchScrapeResult = await firecrawl.batchScrape(['https://docs.firecrawl.dev', 'https://docs.firecrawl.dev/sdks/overview'], { 
  formats: [
    {
      type: "json",
      prompt: "Extract the title and description from the page.",
      schema: schema
    }
  ]
});

// 输出本次批量抓取的所有结果：
console.log(batchScrapeResult)

// 或者可以使用 start 方法：
const batchScrapeJob = await firecrawl.startBatchScrape(['https://docs.firecrawl.dev', 'https://docs.firecrawl.dev/sdks/overview'], { 
  formats: [
    {
      type: "json",
      prompt: "Extract the title and description from the page.",
      schema: schema
    }
  ]
});
console.log(batchScrapeJob)

// 然后可使用作业 ID 检查批量抓取的状态：
const batchScrapeStatus = await firecrawl.getBatchScrapeStatus(batchScrapeJob.id);
console.log(batchScrapeStatus)

curl -X POST https://api.firecrawl.dev/v2/batch/scrape \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer YOUR_API_KEY' \
    -d '{
      "urls": ["https://docs.firecrawl.dev", "https://docs.firecrawl.dev/sdks/overview"],
      "formats" : [{
        "type": "json",
        "prompt": "提取页面的标题和描述。",
        "schema": {
          "type": "object",
          "properties": {
            "title": {
              "type": "string"
            },
            "description": {
              "type": "string"
            }
          },
          "required": [
            "title",
            "description"
          ]
        }
      }]
    }'