SPB Git forge

spb/rareindex

Public
54commits 1branches 0releases
7.1 MBsize
maindefault branch
10 days agolast push
TypeScript 61.9% HTML 37.2% SQL 0.7%
1.5 KB · 21 lines typescript
Raw Blame History
1/** Live smoke: pnpm tsx connectors/api/comicconnect/_smoke.ts  (CAPTURE=1 to save fixtures) */2import { createRouter, createCrawlContext, getConnectorMeta } from '@rareindex/connectors';3import { saveFixture } from '@rareindex/connectors/testing';4import { env } from '@rareindex/shared';5import createConnector from './index.js';67const e = env();8const meta = getConnectorMeta('comicconnect');9const connector = createConnector(meta);10const router = createRouter({ firecrawlApiKey: e.FIRECRAWL_API_KEY, scrapflyApiKey: e.SCRAPFLY_API_KEY });11const ctx = createCrawlContext({ router, meta, options: { mode: 'probe', limit: Number(process.env.LIMIT ?? 2) } });1213for await (const raw of connector.crawl(ctx)) {14  const recs = await connector.normalize({ ...raw, externalId: raw.externalId ?? null, fetchedAt: raw.fetchedAt ?? new Date() });15  const p = raw.payload as { page: number; totalResults: number | null; cards: unknown[] };16  console.log(`\n# page ${p.page} (${p.totalResults} total) — ${p.cards.length} cards → ${recs.length} sales`);17  for (const r of recs.slice(0, 3)) console.log(JSON.stringify(r).slice(0, 800));18  if (process.env.CAPTURE) saveFixture('comicconnect', `sold-comics-page-${p.page}`, { raw: { url: raw.url, externalId: raw.externalId ?? null, kind: raw.kind, engine: raw.engine, fetchedAt: raw.fetchedAt ?? new Date(), payload: raw.payload }, expect: { minCount: 10, kinds: ['sale'] }, note: `captured live from ${raw.url}` });19}20console.log('\nengine stats', ctx.engineStats, 'anomalies', ctx.anomalies);21