Consolidate MangaCircus app, scraper, and Compose baseline

scraper/cli.js

@@ -0,0 +1,115 @@
+#!/usr/bin/env node
+'use strict';
+
+const fs = require('fs').promises;
+const path = require('path');
+const { publishManifest } = require('./lib/publisher');
+const { discoverWeebCentral } = require('./adapters/weebcentral');
+const { lookupAniList } = require('./metadata/anilist');
+const { runArchive } = require('./jobs/weebcentral-archive');
+const { runQueue } = require('./jobs/weebcentral-queue');
+
+function flag(args, name, fallback) {
+  const index = args.indexOf(name);
+  return index < 0 ? fallback : args[index + 1];
+}
+
+async function main() {
+  const args = process.argv.slice(2);
+  const command = args.shift();
+  if (command === 'publish') {
+    const file = args[0];
+    if (!file) throw new Error('Usage: publish <manifest.json> [--library path] [--metadata-search title] [--replace]');
+    const manifest = JSON.parse(await fs.readFile(path.resolve(file), 'utf8'));
+    const metadataSearch = flag(args, '--metadata-search');
+    if (metadataSearch) {
+      const metadata = await lookupAniList(metadataSearch);
+      manifest.series.metadata = { ...metadata, title: manifest.series.title };
+      manifest.series.scraper = { ...(manifest.series.scraper || {}), ids: { ...(manifest.series.scraper?.ids || {}), anilist: metadata['x-anilist']?.id } };
+    }
+    const result = await publishManifest(manifest, { libraryRoot: flag(args, '--library'), replace: args.includes('--replace') });
+    console.log(JSON.stringify(result, null, 2));
+    return;
+  }
+  if (command === 'discover-weebcentral') {
+    const url = args[0];
+    if (!url) throw new Error('Usage: discover-weebcentral <series-url> --out manifest.json [--limit 3]');
+    const manifest = await discoverWeebCentral(url, { limit: Number(flag(args, '--limit', 3)) });
+    const out = flag(args, '--out');
+    if (out) await fs.writeFile(path.resolve(out), JSON.stringify(manifest, null, 2) + '\n');
+    else console.log(JSON.stringify(manifest, null, 2));
+    return;
+  }
+  if (command === 'metadata-anilist') {
+    const search = args.join(' ');
+    if (!search) throw new Error('Usage: metadata-anilist <title>');
+    console.log(JSON.stringify(await lookupAniList(search), null, 2));
+    return;
+  }
+  if (command === 'archive-weebcentral') {
+    const url = args[0];
+    if (!url) throw new Error('Usage: archive-weebcentral <series-url> [--library path] [--metadata-search title]');
+    await runArchive({
+      seriesUrl: url,
+      libraryRoot: flag(args, '--library', 'library'),
+      metadataSearch: flag(args, '--metadata-search'),
+      minMs: Number(flag(args, '--min-ms', 8000)),
+      maxMs: Number(flag(args, '--max-ms', 15000)),
+      chapterMinMs: Number(flag(args, '--chapter-min-ms', 30000)),
+      chapterMaxMs: Number(flag(args, '--chapter-max-ms', 60000)),
+    });
+    return;
+  }
+  if (command === 'status-weebcentral') {
+    const url = args[0];
+    if (!url) throw new Error('Usage: status-weebcentral <series-url> [--library path]');
+    const sourceId = url.split('/series/')[1]?.split('/')[0];
+    if (!sourceId) throw new Error('Could not read WeebCentral series id');
+    const workRoot = path.resolve(flag(args, '--library', 'library'), `.mcscraper-work-${sourceId}`);
+    const state = JSON.parse(await fs.readFile(path.join(workRoot, 'job.json'), 'utf8'));
+    console.log(JSON.stringify({
+      status: state.status || 'unknown',
+      completed: state.completed?.length || 0,
+      total: state.total || null,
+      percent: state.total ? Math.round((state.completed?.length || 0) * 1000 / state.total) / 10 : null,
+      lastChapter: state.lastChapter || null,
+      current: state.current || null,
+      lastProblem: state.lastProblem || null,
+      lastError: state.lastError || null,
+      problemCount: state.problemCount || 0,
+      rate: state.rate || null,
+      updated: state.updated || null,
+      log: path.join(workRoot, 'job.log'),
+    }, null, 2));
+    return;
+  }
+  if (command === 'run-wishlist') {
+    const entries = [
+      ['The Gamer', '01J76XY9DYH4MH2HZG2PPF74A6', 'The-Gamer'],
+      ['Kanojo Okarishimasu', '01J76XYC7KP5M48JAY8S4ZNDX5', 'Kanojo-Okarishimasu'],
+      ['Toradora', '01J76XY7J4Z4G6E42GED6QEQXZ', 'Toradora'],
+      ['Solo Leveling', '01J76XYCPSY3C4BNPBRY8JMCBE', 'Solo-Leveling'],
+      ['Gantz', '01J76XY7EREQ4B1Q5Z5RJ749V6', 'Gantz'],
+      ['One Piece', '01J76XY7E9FNDZ1DBBM6PBJPFK', 'One-Piece'],
+    ].map(([title, id, slug]) => ({ id, title, url: `https://weebcentral.com/series/${id}/${slug}` }));
+    await runQueue({
+      entries,
+      waitForFolder: flag(args, '--wait-for', 'Berserk'),
+      libraryRoot: flag(args, '--library', 'library'),
+      minMs: Number(flag(args, '--min-ms', 3000)),
+      maxMs: Number(flag(args, '--max-ms', 7000)),
+      chapterMinMs: Number(flag(args, '--chapter-min-ms', 12000)),
+      chapterMaxMs: Number(flag(args, '--chapter-max-ms', 25000)),
+    });
+    return;
+  }
+  if (command === 'status-queue') {
+    const queueRoot = path.resolve(flag(args, '--library', 'library'), '.mcscraper-queue');
+    const state = JSON.parse(await fs.readFile(path.join(queueRoot, 'queue.json'), 'utf8'));
+    console.log(JSON.stringify({ ...state, log: path.join(queueRoot, 'queue.log') }, null, 2));
+    return;
+  }
+  console.log('Commands:\n  publish <manifest.json> [--library path] [--metadata-search title] [--replace]\n  discover-weebcentral <url> [--limit 3] [--out file]\n  archive-weebcentral <url> [--library path] [--metadata-search title]\n  status-weebcentral <url> [--library path]\n  run-wishlist [--library path] [--wait-for Berserk]\n  status-queue [--library path]\n  metadata-anilist <title>');
+}
+
+main().catch(error => { console.error(`[scraper] ${error.message}`); process.exitCode = 1; });