Updated image URL parsing to latest iteratoin the site uses

Author: Fiddlekins

README.md

@@ -2,7 +2,7 @@
 
 It'll archive stories for you.
 
-If you have no idea what you're doing then just download [this zip](https://github.com/Fiddlekins/akun-story-scraper/releases/download/1.7.0/akun-story-scraper.1.7.0.zip) and extract it in a nice friendly location like your desktop.
+If you have no idea what you're doing then just download [this zip](https://github.com/Fiddlekins/akun-story-scraper/releases/download/1.8.0/akun-story-scraper.1.8.0.zip) and extract it in a nice friendly location like your desktop.
 
 Otherwise clone the project, do an npm install, it's pretty standard.
 

package-lock.json

@@ -1,6 +1,6 @@
 {
   "name": "akun-story-scraper",
-  "version": "1.7.0",
+  "version": "1.8.0",
   "description": "A tool to archive all quests on Akun",
   "type": "module",
   "main": "src/index.js",

package.json

@@ -2,6 +2,7 @@ import fs from 'fs-extra';
 import jsdom from 'jsdom';
 import path from 'path';
 import downloadImage from './downloadImage.js';
+import {imageURLParser} from "./imageURLParser.js";
 import Striver from './Striver.js';
 import Throttler from './Throttler.js';
 
@@ -299,13 +300,14 @@ export default class Scraper {
 			const throttler = new Throttler();
 			const promises = [];
 			Array.from(imageUrls).forEach(imageUrl => {
+				const parsedImageUrl = imageURLParser(imageUrl);
 				const promiseGenerator = () => {
-					return downloadImage(imageUrl, imagesPath).then(imagePath => {
+					return downloadImage(parsedImageUrl, imagesPath).then(imagePath => {
 						imageMap[imageUrl] = imagePath;
 					});
 				};
 				const promise = throttler.queue(promiseGenerator).catch(err => {
-					this._logger.error(`Unable to download image ${imageUrl} due to:\n${err}`);
+					this._logger.error(`Unable to download image ${imageUrl} (parsed: ${parsedImageUrl}) due to:\n${err}`);
 				});
 				promises.push(promise);
 			});

src/Scraper.js

@@ -0,0 +1,35 @@
+/**
+ * Code copied from akun site code, parameter meanings deduced
+ * @param e Input URL
+ * @param t Optional. Target location width
+ * @param n Optional. Target location height
+ * @param i Optional. Value can be "nocfill"
+ * @param r Optional. Value can be "storyCover"
+ * @returns {*}
+ */
+export function imageURLParser(e, t, n, i, r) {
+  function a() {
+    return 400 == t || 16 == t || 24 == t || 60 == t || 80 == t || 100 == t ? !0 : !1
+  }
+
+  function o(e) {
+    return e.split("?")[0]
+  }
+
+  if (e && "string" == typeof e) {
+    "object" == typeof e && (e = e[0]);
+    var s;
+    return r && (s = !0),
+      t && n ? (i && (s && (-1 != e.indexOf("filepicker.io") && (e = e.replace(/www\.filepicker\.io\/api\/file\/(\w+)/g, "cdn4.fiction.live/fp/$1?height=" + n + "&width=" + t + "&quality=95")),
+        e = e.replace(/(\w+)\.cloudfront.net\/(.+)/g, "cdn4.fiction.live/$2?height=" + n + "&width=" + t + "&quality=95").replace(/cdn3.fiction.live\/(.+)/g, "cdn4.fiction.live/$1?height=" + n + "&width=" + t + "&quality=95")),
+      -1 != e.indexOf("filepicker.io") && (e = e.replace(/www\.filepicker\.io\/api\/file\/(\w+)/g, "cdn4.fiction.live/fp/$1?height=" + n + "&width=" + t + "&quality=95")),
+        e = e.replace(/cdn3.fiction.live\/(.+)/g, "cdn4.fiction.live/$1?height=" + n + "&width=" + t + "&quality=95")),
+      -1 != e.indexOf("filepicker.io") && (e = e.replace(/www\.filepicker\.io\/api\/file\/(\w+)/g, "cdn4.fiction.live/fp/$1?height=" + n + "&width=" + t + "&quality=95&aspect_ratio=" + t + ":" + n)),
+        e = e.replace(/(\w+)\.cloudfront.net\/(.+)/g, "cdn4.fiction.live/$2?height=" + n + "&width=" + t + "&quality=95&aspect_ratio=" + t + ":" + n).replace(/cdn3.fiction.live\/(.+)/g, "cdn4.fiction.live/$1?height=" + n + "&width=" + t + "&quality=95&aspect_ratio=" + t + ":" + n),
+        e = o(e),
+      a() && (e = e.replace(/cdn6.fiction.live\/file\/fictionlive\/(.+)/g, "cdn6.fiction.live/file/fictionlive/thumb/$1").replace(/cdn4.fiction.live\/(.+)/g, "cdn6.fiction.live/file/fictionlive/thumb/$1").replace(/cdn3.fiction.live\/(.+)/g, "cdn6.fiction.live/file/fictionlive/thumb/$1")),
+        e = e.replace(/cdn4.fiction.live\/(.+)/g, "cdn6.fiction.live/file/fictionlive/$1")) : (e = e.replace(/(\w+)\.cloudfront.net/g, "cdn6.fiction.live/file/fictionlive").replace(/www\.filepicker\.io\/api\/file\/(\w+)/g, "cdn4.fiction.live/fp/$1"),
+        e = e.replace(/cdn4.fiction.live\/(.+)/g, "cdn6.fiction.live/file/fictionlive/$1").replace(/cdn3.fiction.live\/(.+)/g, "cdn6.fiction.live/file/fictionlive/$1")),
+      e
+  }
+}

src/imageURLParser.js

@@ -1,3 +1,13 @@
+import {imageURLParser} from "../imageURLParser.js";
+
 export default function buildChapter($content, update) {
-	$content.innerHTML = update['b'];
+  $content.innerHTML = update['b'];
+
+  try {
+    $content.querySelectorAll('img').forEach(el => {
+      el.src = imageURLParser(el.src);
+    });
+  } catch (err) {
+    console.error(err);
+  }
 }

src/view/buildChapter.js

@@ -1,11 +1,5 @@
+import {imageURLParser} from "../imageURLParser.js";
+
 export default function formatAvatarSrc(src, size = 64) {
-	const cloudfrontMatch = src.match(/https?:\/\/[A-z0-9]+.cloudfront.net\/images\/(.+)/i);
-	if (cloudfrontMatch) {
-		return `https://cdn.fiction.live/h${size}-w${size}-cfill/images/${cloudfrontMatch[1]}`;
-	}
-	const filepickerMatch = src.match(/https?:\/\/www.filepicker.io\/api\/file\/(.+)/i);
-	if (filepickerMatch) {
-		return `https://www.filepicker.io/api/file/${filepickerMatch[1]}/convert?w=${size}&h=${size}&fit=crop&cache=true`;
-	}
-	return src;
+	return imageURLParser(src, size, size);
 }