[crawler_platform 삭제]

ontology_platform/web/frontend/src/lib/api/crawl.ts

@@ -0,0 +1,82 @@
+import { z } from "zod";
+import { apiClient } from "./client";
+
+const stringFromAny = z.union([z.string(), z.number()]).transform(String);
+
+export const crawlPageItemSchema = z
+  .object({
+    url: z.string().optional(),
+    status: z.string().optional(),
+    page_type: z.string().optional(),
+    title: z.string().nullable().optional(),
+    error: z.string().nullable().optional(),
+  })
+  .passthrough();
+
+export const crawlProgressSchema = z
+  .object({
+    seed_url: z.string().optional(),
+    visited_count: z.number().optional(),
+    analyzed_count: z.number().optional(),
+    queued_count: z.number().optional(),
+    skipped_count: z.number().optional(),
+    errors: z.array(z.string()).optional(),
+    pages: z.array(crawlPageItemSchema).optional(),
+    latest_page: crawlPageItemSchema.optional(),
+  })
+  .passthrough();
+
+export const crawlJobSchema = z.object({
+  job_id: stringFromAny,
+  status: z.string(),
+  url: z.string().nullable().optional(),
+  error: z.string().nullable().optional(),
+  scheduled_at: z.string().nullable().optional(),
+  started_at: z.string().nullable().optional(),
+  finished_at: z.string().nullable().optional(),
+  progress: crawlProgressSchema.default({}),
+  request: z.record(z.string(), z.unknown()).default({}),
+});
+
+export type CrawlJob = z.infer<typeof crawlJobSchema>;
+export type CrawlProgress = z.infer<typeof crawlProgressSchema>;
+
+export interface StartSiteCrawlRequest {
+  project_name: string;
+  source_name: string;
+  url: string;
+  max_depth?: number;
+  max_pages?: number;
+  same_domain_only?: boolean;
+  analyze_page_types?: string[];
+  extractor_provider?: string;
+  extractor_model?: string | null;
+  extractor_base_url?: string | null;
+  check_robots_txt?: boolean;
+  respect_robots_txt?: boolean | null;
+}
+
+export const TERMINAL_CRAWL_STATUSES = new Set([
+  "completed",
+  "failed",
+  "canceled",
+]);
+
+export function isCrawlTerminal(status: string): boolean {
+  return TERMINAL_CRAWL_STATUSES.has(status);
+}
+
+export const crawlApi = {
+  startByProject: (body: StartSiteCrawlRequest) =>
+    apiClient.post("/crawl-site/by-project", crawlJobSchema, body),
+  getJob: (jobId: string) =>
+    apiClient.get(
+      `/crawl-site/jobs/${encodeURIComponent(jobId)}`,
+      crawlJobSchema,
+    ),
+  cancel: (jobId: string) =>
+    apiClient.post(
+      `/crawl-site/jobs/${encodeURIComponent(jobId)}/cancel`,
+      crawlJobSchema,
+    ),
+};