データ抽出ツールの選び方

from firecrawl import Firecrawl
from pydantic import BaseModel, Field
from typing import List, Optional

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

class Founder(BaseModel):
    name: str = Field(description="Full name of the founder")
    role: Optional[str] = Field(None, description="Role or position")
    background: Optional[str] = Field(None, description="Professional background")

class FoundersSchema(BaseModel):
    founders: List[Founder] = Field(description="List of founders")

result = app.agent(
    prompt="Find the founders of Firecrawl",
    schema=FoundersSchema,
    model="spark-1-mini",
    max_credits=100
)

print(result.data)

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

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

const result = await firecrawl.agent({
  prompt: "Find the founders of Firecrawl",
  schema: z.object({
    founders: z.array(z.object({
      name: z.string().describe("Full name of the founder"),
      role: z.string().describe("Role or position").optional(),
      background: z.string().describe("Professional background").optional()
    })).describe("List of founders")
  }),
  model: "spark-1-mini",
  maxCredits: 100
});

console.log(result.data);

curl -X POST "https://api.firecrawl.dev/v2/agent" \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Find the founders of Firecrawl",
    "model": "spark-1-mini",
    "maxCredits": 100,
    "schema": {
      "type": "object",
      "properties": {
        "founders": {
          "type": "array",
          "description": "List of founders",
          "items": {
            "type": "object",
            "properties": {
              "name": { "type": "string", "description": "Full name" },
              "role": { "type": "string", "description": "Role or position" },
              "background": { "type": "string", "description": "職歴" }
            },
            "required": ["name"]
          }
        }
      },
      "required": ["founders"]
    }
  }'

from firecrawl import Firecrawl

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

schema = {
    "type": "object",
    "properties": {"description": {"type": "string"}},
    "required": ["description"],
}

res = firecrawl.extract(
    urls=["https://docs.firecrawl.dev"],
    prompt="ページの説明を抽出",
    schema=schema,
)

print(res.data["description"])

import { Firecrawl } from 'firecrawl';

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

const schema = {
  type: 'object',
  properties: {
    title: { type: 'string' }
  },
  required: ['title']
};

const res = await firecrawl.extract({
  urls: ['https://docs.firecrawl.dev'],
  prompt: 'Extract the page title',
  schema,
  scrapeOptions: { formats: [{ type: 'json', prompt: 'Extract', schema }] }
});

console.log(res.status || res.success, res.data);

curl -s -X POST "https://api.firecrawl.dev/v2/extract" \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "urls": ["https://docs.firecrawl.dev"],
    "prompt": "ページタイトルを抽出してください",
    "schema": {
      "type": "object",
      "properties": {"title": {"type": "string"}},
      "required": ["title"]
    },
    "scrapeOptions": {
      "formats": [{"type": "json", "prompt": "抽出してください", "schema": {"type": "object"}}]
    }
  }'

from firecrawl import Firecrawl
from pydantic import BaseModel

app = Firecrawl(
  # 始めるのにAPIキーは不要です — より高いRate Limitsを得るには追加してください:
  # api_key="fc-YOUR-API-KEY",
)

class CompanyInfo(BaseModel):
    company_mission: str
    supports_sso: bool
    is_open_source: bool
    is_in_yc: bool

result = app.scrape(
    'https://firecrawl.dev',
    formats=[{
      "type": "json",
      "schema": CompanyInfo.model_json_schema()
    }],
    only_main_content=False,
    timeout=120000
)

print(result)

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

const app = new Firecrawl({
  // 始めるのにAPIキーは不要です — より高いレート制限が必要な場合は追加してください:
  // apiKey: "fc-YOUR_API_KEY",
});

// Define schema to extract contents into
const schema = z.object({
  company_mission: z.string(),
  supports_sso: z.boolean(),
  is_open_source: z.boolean(),
  is_in_yc: z.boolean()
});

const result = await app.scrape("https://firecrawl.dev", {
  formats: [{
    type: "json",
    schema: schema
  }],
});

console.log(result);

# 開始するにAPIキーは不要です — レート制限を引き上げるには -H "Authorization: Bearer YOUR_API_KEY" を追加してください:
curl -X POST https://api.firecrawl.dev/v2/scrape \
    -H 'Content-Type: application/json' \
    -d '{
      "url": "https://firecrawl.dev",
      "formats": [ {
        "type": "json",
        "schema": {
          "type": "object",
          "properties": {
            "company_mission": {
                      "type": "string"
            },
            "supports_sso": {
                      "type": "boolean"
            },
            "is_open_source": {
                      "type": "boolean"
            },
            "is_in_yc": {
                      "type": "boolean"
            }
          },
          "required": [
            "company_mission",
            "supports_sso",
            "is_open_source",
            "is_in_yc"
          ]
        }
      } ]
    }'