Add first-party MangaPill source and distinct volume releases

scraper/plugins/broker.js

@@ -22,6 +22,10 @@ function publicAddress(address) {
 }
 
 function validateWeebRequest(value, options = {}) {
+  return validateHostRequest(value, 'weebcentral.com', options);
+}
+
+function validateHostRequest(value, sourceHost, options = {}) {
   const url = new URL(value);
   const host = url.hostname.toLowerCase();
   if (url.protocol !== 'https:' || url.username || url.password || url.port
@@ -29,8 +33,8 @@ function validateWeebRequest(value, options = {}) {
     || host.endsWith('.local') || !host.includes('.')) {
     throw new Error('Source request URL is not public HTTPS');
   }
-  if (options.accept === 'text/html' && host !== 'weebcentral.com') {
-    throw new Error('WeebCentral catalog request left its source host');
+  if (options.accept === 'text/html' && host !== sourceHost) {
+    throw new Error('Source catalog request left its source host');
   }
   return url;
 }
@@ -88,4 +92,9 @@ function createWeebHttp(options = {}) {
   return new SlowHttp({ ...options, transport: pinnedFetch, validateUrl: validateWeebRequest });
 }
 
-module.exports = { publicAddress, validateWeebRequest, pinnedLookup, pinnedFetch, createWeebHttp };
+function createHostHttp(sourceHost, options = {}) {
+  return new SlowHttp({ ...options, transport: pinnedFetch,
+    validateUrl: (value, requestOptions) => validateHostRequest(value, sourceHost, requestOptions) });
+}
+
+module.exports = { publicAddress, validateWeebRequest, validateHostRequest, pinnedLookup, pinnedFetch, createWeebHttp, createHostHttp };

scraper/plugins/mangapill.js

@@ -0,0 +1,32 @@
+'use strict';
+
+// First-party parser; inputs are fetched by the paced source broker, not here.
+const decode = value => String(value).replace(/&/g, '&').replace(/'|'/gi, "'")
+  .replace(/&quot;/g, '"').replace(/<[^>]+>/g, '').trim();
+
+function catalog({ html, url }) {
+  const sourceId = new URL(url).pathname.split('/')[2];
+  const title = decode(html.match(/<h1\b[^>]*>([\s\S]*?)<\/h1>/i)?.[1] || 'Untitled');
+  const chapters = [];
+  const re = /<a\b[^>]*href="(\/chapters\/(\d+-\d+)\/[^"?#]+)"[^>]*>([\s\S]*?)<\/a>/gi;
+  for (const match of html.matchAll(re)) {
+    if (match[2].split('-')[0] !== sourceId) continue;
+    const label = decode(match[3]);
+    const number = label.match(/^Chapter\s+([0-9]+(?:\.[0-9]+)?)(?:\b|$)/i)?.[1];
+    if (!number) continue;
+    chapters.push({ id: match[2], number, title: '', url: new URL(match[1], url).href, raw: label });
+  }
+  return { title, chapters: [...new Map(chapters.map(ref => [ref.id, ref])).values()],
+    chapterLinks: [...html.matchAll(/href="\/chapters\/\d+-\d+\//gi)].length };
+}
+
+function pages({ html }) {
+  const images = [];
+  for (const match of html.matchAll(/<img\b[^>]*class="[^"]*\bjs-page\b[^"]*"[^>]*>/gi)) {
+    const url = match[0].match(/\bdata-src="([^"]+)"/i)?.[1];
+    if (url) images.push(url.replace(/&amp;/g, '&'));
+  }
+  return { pages: [...new Set(images)] };
+}
+
+module.exports = { catalog, pages };

scraper/plugins/manifest.js

@@ -17,6 +17,12 @@ const manifests = Object.freeze({
     provenance: 'MangaCircus existing MangaDex adapter; no Uchiyomi code copied',
     operations: Object.freeze(['metadata', 'feed', 'catalog', 'atHome']),
   }),
+  mangapill: Object.freeze({
+    id: 'mangapill', version: 1, label: 'MangaPill', status: 'in-process',
+    sourceHosts: Object.freeze(['mangapill.com']), implementation: 'first-party',
+    provenance: 'MangaCircus implementation; upstream extension reviewed, no code copied',
+    operations: Object.freeze(['catalog', 'pages']),
+  }),
 });
 
 module.exports = { manifests };

scraper/plugins/registry.js

@@ -6,6 +6,7 @@ const { validate } = require('./validation');
 const plugins = Object.freeze({
   weebcentral: require('./weebcentral'),
   mangadex: require('./mangadex'),
+  mangapill: require('./mangapill'),
 });
 
 function parse(plugin, operation, input) {

scraper/plugins/validation.js

@@ -33,8 +33,20 @@ function mangaDexUrl(value, kind) {
   return url.href;
 }
 
+function mangaPillUrl(value, kind) {
+  const url = new URL(value);
+  if (url.protocol !== 'https:' || url.username || url.password || url.port) throw new Error('Invalid MangaPill plugin URL');
+  if (kind === 'chapter' && (url.hostname !== 'mangapill.com' || !/^\/chapters\/\d+-\d+\//.test(url.pathname))) {
+    throw new Error('Unexpected MangaPill chapter URL');
+  }
+  if (kind === 'page' && (url.hostname !== 'cdn.readdetectiveconan.com' || !url.pathname.startsWith('/file/mangap/'))) {
+    throw new Error('Unexpected MangaPill page host');
+  }
+  return url.href;
+}
+
 function validate(plugin, operation, output) {
-  if (!['weebcentral', 'mangadex'].includes(plugin) || !output || typeof output !== 'object' || Array.isArray(output)) {
+  if (!['weebcentral', 'mangadex', 'mangapill'].includes(plugin) || !output || typeof output !== 'object' || Array.isArray(output)) {
     throw new Error('Invalid source plugin output');
   }
   if (plugin === 'mangadex') {
@@ -51,6 +63,21 @@ function validate(plugin, operation, output) {
     } else throw new Error('Unknown source plugin operation');
     return output;
   }
+  if (plugin === 'mangapill') {
+    if (operation === 'catalog') {
+      if (typeof output.title !== 'string' || !Array.isArray(output.chapters)
+        || !Number.isInteger(output.chapterLinks) || output.chapterLinks < 0) throw new Error('Invalid MangaPill catalog');
+      for (const chapter of output.chapters) {
+        if (typeof chapter?.id !== 'string' || !/^\d+-\d+$/.test(chapter.id)
+          || !/^\d+(?:\.\d+)?$/.test(chapter.number)) throw new Error('Invalid MangaPill chapter');
+        mangaPillUrl(chapter.url, 'chapter');
+      }
+    } else if (operation === 'pages') {
+      if (!Array.isArray(output.pages)) throw new Error('Invalid MangaPill pages');
+      for (const page of output.pages) mangaPillUrl(page, 'page');
+    } else throw new Error('Unknown MangaPill operation');
+    return output;
+  }
   if (operation === 'series') {
     if (typeof output.title !== 'string' || typeof output.listUrl !== 'string' && output.listUrl !== null) throw new Error('Invalid series parse');
     if (output.listUrl !== null) sourceUrl(output.listUrl, '/series/');

scraper/plugins/weebcentral.js

@@ -1,4 +1,5 @@
 'use strict';
+const { volumeKey } = require('../../chapter-identity');
 
 // 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();
@@ -17,6 +18,7 @@ function catalog({ html, url }) {
     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|Scene|Kapitel|File|Battle)\s*[.:]?\s*([0-9]+(?:\.[0-9]+)?)/i)?.[1];
+    const volume = !regular ? text.match(/^Volume\s+([0-9]+(?:\.[0-9]+)?)(?!\d)/i)?.[1] : null;
     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({
@@ -24,6 +26,12 @@ function catalog({ html, url }) {
       ...(season ? { book: { number: season, title: `Season ${season}` } } : {}),
       url: absolute(url, match[1]), raw: text,
     });
+    else if (volume) found.push({
+      id: match[2], number: volumeKey(match[2]), title: '', special: true,
+      label: `Volume ${volume}`, releaseKind: 'volume', volume,
+      book: { number: Number(volume), title: `Volume ${volume}` },
+      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;