feat: add web crawling management functionality

- Introduced a new crawling management feature allowing users to configure, execute, and log web crawls.
- Added CRUD operations for crawl configurations, including URL analysis and preview capabilities.
- Implemented a new service for handling crawling logic and scheduling tasks.
- Integrated cheerio for HTML parsing and axios for HTTP requests.
- Created a sample HTML page for testing crawling functionality.

This commit enhances the application's data collection capabilities from external websites.

backend-node/src/controllers/crawlController.ts

@@ -0,0 +1,124 @@
+import { Request, Response } from "express";
+import { CrawlService } from "../services/crawlService";
+import { logger } from "../utils/logger";
+
+interface AuthenticatedRequest extends Request {
+  user?: { companyCode: string; userId: string };
+}
+
+// 설정 목록 조회
+export async function getCrawlConfigs(req: AuthenticatedRequest, res: Response) {
+  try {
+    const companyCode = req.user?.companyCode || "*";
+    const configs = await CrawlService.getConfigs(companyCode);
+    return res.json({ success: true, data: configs });
+  } catch (error: any) {
+    logger.error("크롤링 설정 조회 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}
+
+// 설정 상세 조회
+export async function getCrawlConfig(req: AuthenticatedRequest, res: Response) {
+  try {
+    const config = await CrawlService.getConfigById(req.params.id);
+    if (!config) return res.status(404).json({ success: false, message: "설정을 찾을 수 없습니다." });
+    return res.json({ success: true, data: config });
+  } catch (error: any) {
+    logger.error("크롤링 설정 상세 조회 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}
+
+// 설정 생성
+export async function createCrawlConfig(req: AuthenticatedRequest, res: Response) {
+  try {
+    const data = {
+      ...req.body,
+      company_code: req.user?.companyCode || req.body.company_code,
+      writer: req.user?.userId,
+    };
+    const config = await CrawlService.createConfig(data);
+    return res.json({ success: true, data: config });
+  } catch (error: any) {
+    logger.error("크롤링 설정 생성 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}
+
+// 설정 수정
+export async function updateCrawlConfig(req: AuthenticatedRequest, res: Response) {
+  try {
+    const config = await CrawlService.updateConfig(req.params.id, req.body);
+    if (!config) return res.status(404).json({ success: false, message: "설정을 찾을 수 없습니다." });
+    return res.json({ success: true, data: config });
+  } catch (error: any) {
+    logger.error("크롤링 설정 수정 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}
+
+// 설정 삭제
+export async function deleteCrawlConfig(req: AuthenticatedRequest, res: Response) {
+  try {
+    await CrawlService.deleteConfig(req.params.id);
+    return res.json({ success: true });
+  } catch (error: any) {
+    logger.error("크롤링 설정 삭제 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}
+
+// 미리보기
+export async function previewCrawl(req: AuthenticatedRequest, res: Response) {
+  try {
+    const { url, row_selector, column_mappings, method, headers, request_body } = req.body;
+    if (!url) return res.status(400).json({ success: false, message: "URL은 필수입니다." });
+
+    const result = await CrawlService.preview(url, row_selector, column_mappings || [], method, headers, request_body);
+    return res.json({ success: true, data: result });
+  } catch (error: any) {
+    logger.error("크롤링 미리보기 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}
+
+// URL 자동 분석 — 페이지의 테이블/리스트 구조를 감지
+export async function analyzeUrl(req: AuthenticatedRequest, res: Response) {
+  try {
+    const { url } = req.body;
+    if (!url) return res.status(400).json({ success: false, message: "URL은 필수입니다." });
+
+    const result = await CrawlService.analyzeUrl(url);
+    return res.json({ success: true, data: result });
+  } catch (error: any) {
+    logger.error("URL 분석 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}
+
+// 수동 실행
+export async function executeCrawl(req: AuthenticatedRequest, res: Response) {
+  try {
+    const config = await CrawlService.getConfigById(req.params.id);
+    if (!config) return res.status(404).json({ success: false, message: "설정을 찾을 수 없습니다." });
+
+    const result = await CrawlService.executeCrawl(config);
+    return res.json({ success: true, data: result });
+  } catch (error: any) {
+    logger.error("크롤링 수동 실행 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}
+
+// 실행 로그 조회
+export async function getCrawlLogs(req: AuthenticatedRequest, res: Response) {
+  try {
+    const limit = parseInt(req.query.limit as string) || 20;
+    const logs = await CrawlService.getLogs(req.params.id, limit);
+    return res.json({ success: true, data: logs });
+  } catch (error: any) {
+    logger.error("크롤링 로그 조회 실패:", error);
+    return res.status(500).json({ success: false, message: error.message });
+  }
+}