Checkpoint first-party source parser pilot

scraper/plugins/client.js

@@ -0,0 +1,20 @@
+'use strict';
+
+const { parse } = require('./registry');
+
+async function parseSource(plugin, operation, input) {
+  const endpoint = process.env.SOURCE_PLUGIN_URL;
+  if (!endpoint) return parse(plugin, operation, input);
+  const url = new URL('/v1/parse', endpoint);
+  if (!['http:', 'https:'].includes(url.protocol)) throw new Error('Invalid source plugin endpoint');
+  const response = await fetch(url, {
+    method: 'POST',
+    headers: { 'content-type': 'application/json' },
+    body: JSON.stringify({ plugin, operation, input }),
+    signal: AbortSignal.timeout(10000),
+  });
+  if (!response.ok) throw new Error(`Source parser unavailable (${response.status}); checkpoint preserved`);
+  return response.json();
+}
+
+module.exports = { parseSource };

scraper/plugins/manifest.js

@@ -0,0 +1,15 @@
+'use strict';
+
+// This list is shipped with MangaCircus. Neither the admin UI nor a remote
+// source may add executable modules at runtime.
+const manifests = Object.freeze({
+  weebcentral: Object.freeze({
+    id: 'weebcentral', version: 1, label: 'WeebCentral', status: 'pilot',
+    sourceHosts: Object.freeze(['weebcentral.com']),
+    implementation: 'first-party',
+    provenance: 'MangaCircus existing WeebCentral adapter; no Uchiyomi code copied',
+    operations: Object.freeze(['series', 'catalog', 'chapter', 'pages']),
+  }),
+});
+
+module.exports = { manifests };

scraper/plugins/registry.js

@@ -0,0 +1,20 @@
+'use strict';
+
+// Reviewed first-party modules only. No filesystem scanning or runtime installs.
+const { manifests } = require('./manifest');
+const plugins = Object.freeze({ weebcentral: require('./weebcentral') });
+
+function parse(plugin, operation, input) {
+  const manifest = manifests[plugin];
+  const handler = manifest?.operations.includes(operation) ? plugins[plugin]?.[operation] : null;
+  if (typeof handler !== 'function') throw new Error('Unknown source plugin or operation');
+  if (!input || typeof input !== 'object' || typeof input.html !== 'string' || typeof input.url !== 'string') {
+    throw new Error('Invalid parser input');
+  }
+  const url = new URL(input.url);
+  if (!['https:', 'http:'].includes(url.protocol)) throw new Error('Invalid source URL');
+  if (!manifest.sourceHosts.includes(url.hostname)) throw new Error('Source URL does not belong to plugin');
+  return handler({ html: input.html, url: url.href });
+}
+
+module.exports = { parse, manifests };

scraper/plugins/weebcentral.js

@@ -0,0 +1,50 @@
+'use strict';
+
+// First-party, pure parsing functions. This module never fetches remote content.
+const decode = value => value.replace(/&amp;/g, '&').replace(/&#39;/g, "'").replace(/&quot;/g, '"').replace(/<[^>]+>/g, '').trim();
+const absolute = (base, value) => new URL(value, base).href;
+
+function series({ html, url }) {
+  const title = decode(html.match(/<h1\b[^>]*>([\s\S]*?)<\/h1>/i)?.[1] || 'Untitled');
+  const listUrl = html.match(/hx-get="([^"]+\/full-chapter-list)"/i)?.[1];
+  return { title, listUrl: listUrl ? absolute(url, listUrl) : null };
+}
+
+function catalog({ html, url }) {
+  const found = [];
+  const re = /<a\b[^>]*href="([^"]*\/chapters\/([A-Z0-9]+)[^"]*)"[^>]*>([\s\S]*?)<\/a>/gi;
+  for (const match of html.matchAll(re)) {
+    const text = decode(match[3]).replace(/\s+/g, ' ');
+    const season = Number(text.match(/^S(\d+)\s*-/i)?.[1] || 0) || null;
+    const regular = text.match(/\b(?:Chapter|Rating|Episode|Night|Log|Act)\s*[.:]?\s*([0-9]+(?:\.[0-9]+)?)/i)?.[1];
+    const prologue = text.match(/Prologue(?:\s+([0-9]+))?/i)?.[1];
+    const number = regular || (prologue ? `0.${prologue.padStart(2, '0')}` : /Prologue/i.test(text) ? '0' : null);
+    if (number) found.push({
+      id: match[2], number, title: regular ? '' : `Prologue ${prologue || ''}`.trim(),
+      ...(season ? { book: { number: season, title: `Season ${season}` } } : {}),
+      url: absolute(url, match[1]), raw: text,
+    });
+  }
+  const chapters = [...new Map(found.map(chapter => [chapter.id, chapter])).values()];
+  const chapterLinks = [...html.matchAll(/<a\b[^>]*href="[^"]*\/chapters\/[A-Z0-9]+[^"]*"/gi)].length;
+  return { chapters, chapterLinks };
+}
+
+function chapter({ html, url }) {
+  return {
+    manifestUrl: html.match(/['"](https?:\/\/weebcentral\.com\/chapters\/[^'"]+\/images\?is_prev=[^'"]+)['"]/i)?.[1]
+      || `${url}/images?is_prev=False`,
+    added: html.match(/datetime="([^"]+)"/i)?.[1],
+  };
+}
+
+function pages({ html, url }) {
+  const urls = [];
+  for (const match of html.matchAll(/<img\b[^>]*(?:src|data-src)="([^"]+)"/gi)) {
+    const pageUrl = absolute(url, match[1].replace(/&amp;/g, '&'));
+    if (!pageUrl.startsWith('data:')) urls.push(pageUrl);
+  }
+  return { pages: [...new Set(urls)] };
+}
+
+module.exports = { series, catalog, chapter, pages };

scraper/plugins/worker.js

@@ -0,0 +1,48 @@
+'use strict';
+
+const http = require('node:http');
+const { parse } = require('./registry');
+const MAX_BODY_BYTES = 2 * 1024 * 1024;
+
+function createServer() {
+  return http.createServer((request, response) => {
+    if (request.method === 'GET' && request.url === '/health') {
+      response.writeHead(200, { 'content-type': 'application/json' });
+      response.end(JSON.stringify({ ok: true }));
+      return;
+    }
+    if (request.method !== 'POST' || request.url !== '/v1/parse') {
+      response.writeHead(404).end();
+      return;
+    }
+    let bytes = 0;
+    const chunks = [];
+    request.on('data', chunk => {
+      bytes += chunk.length;
+      if (bytes > MAX_BODY_BYTES) {
+        response.writeHead(413).end();
+        request.destroy();
+        return;
+      }
+      chunks.push(chunk);
+    });
+    request.on('end', () => {
+      if (bytes > MAX_BODY_BYTES) return;
+      try {
+        const { plugin, operation, input } = JSON.parse(Buffer.concat(chunks).toString('utf8'));
+        const output = parse(plugin, operation, input);
+        response.writeHead(200, { 'content-type': 'application/json' });
+        response.end(JSON.stringify(output));
+      } catch (error) {
+        response.writeHead(400, { 'content-type': 'application/json' });
+        response.end(JSON.stringify({ error: error.message }));
+      }
+    });
+  });
+}
+
+if (require.main === module) {
+  createServer().listen(Number(process.env.SOURCE_PLUGIN_PORT || 8094), process.env.SOURCE_PLUGIN_HOST || '127.0.0.1');
+}
+
+module.exports = { createServer };