前提条件#
- Java 17+ 和 Spring Boot 3+
- 一个 Firecrawl API 密钥——免费获取
添加依赖#
dependencies { implementation("com.firecrawl:firecrawl-java:1.2.0")}<dependency> <groupId>com.firecrawl</groupId> <artifactId>firecrawl-java</artifactId> <version>1.2.0</version></dependency>配置#
将您的 API 密钥添加到 application.properties 中：
firecrawl.api-key=${FIRECRAWL_API_KEY}或者将其设为环境变量：
export FIRECRAWL_API_KEY=fc-YOUR-API-KEY创建配置 Bean#
创建 FirecrawlConfig.java：
import com.firecrawl.client.FirecrawlClient;import org.springframework.beans.factory.annotation.Value;import org.springframework.context.annotation.Bean;import org.springframework.context.annotation.Configuration;@Configurationpublic class FirecrawlConfig { @Bean public FirecrawlClient firecrawlClient( @Value("${firecrawl.api-key}") String apiKey) { return FirecrawlClient.builder() .apiKey(apiKey) .build(); }}创建 REST 控制器#
创建 FirecrawlController.java：
import com.firecrawl.client.FirecrawlClient;import com.firecrawl.models.Document;import com.firecrawl.models.SearchData;import com.firecrawl.models.SearchOptions;import com.firecrawl.models.ScrapeOptions;import com.firecrawl.models.BrowserExecuteResponse;import org.springframework.web.bind.annotation.*;import java.util.List;import java.util.Map;@RestController@RequestMapping("/api")public class FirecrawlController { private final FirecrawlClient firecrawl; public FirecrawlController(FirecrawlClient firecrawl) { this.firecrawl = firecrawl; } @PostMapping("/search") public SearchData search(@RequestBody Map<String, Object> body) { return firecrawl.search( (String) body.get("query"), SearchOptions.builder() .limit((int) body.getOrDefault("limit", 5)) .build() ); } @PostMapping("/scrape") public Map<String, Object> scrape(@RequestBody Map<String, String> body) { Document doc = firecrawl.scrape(body.get("url")); return Map.of( "markdown", doc.getMarkdown(), "metadata", doc.getMetadata() ); } @PostMapping("/interact") public Map<String, Object> interact(@RequestBody Map<String, String> body) { Document doc = firecrawl.scrape(body.get("url"), ScrapeOptions.builder().formats(List.of((Object) "markdown")).build()); String scrapeId = (String) doc.getMetadata().get("scrapeId"); BrowserExecuteResponse response = firecrawl.interact(scrapeId, body.getOrDefault("code", "const title = await page.title(); console.log(title);")); firecrawl.stopInteractiveBrowser(scrapeId); return Map.of("result", response.getStdout()); }}运行#
./gradlew bootRun进行测试#
# 进行网页搜索curl -X POST http://localhost:8080/api/search \ -H "Content-Type: application/json" \ -d '{"query": "firecrawl web scraping"}'# 抓取页面curl -X POST http://localhost:8080/api/scrape \ -H "Content-Type: application/json" \ -d '{"url": "https://example.com"}'# 与页面交互curl -X POST http://localhost:8080/api/interact \ -H "Content-Type: application/json" \ -d '{"url": "https://www.amazon.com", "code": "const title = await page.title(); console.log(title);"}'