Checkpoint first-party source parser pilot

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 };