修复了69书吧

README.md

@@ -2,6 +2,23 @@
 
 一个**可扩展的**通用型小说下载器。
 
+# 关于本Fork
+
+本fork脚本下载：[bundle.user.js](https://github.com/ShenSheiBot/novel-downloader/raw/refs/heads/master/dist/bundle.user.js)
+
+原作者已不再维护此仓库，此fork将继续维护，新增的功能包括：
+- 允许跳过txt下载
+- 支持了新飘天文学网（piaotia）
+- 支持了xbookcn
+
+修复的网站包括：
+- Syosetu
+- 69书吧
+- Kakuyomu
+
+如有需要修复/支持的网站，请在issue中提出。作者将在空闲时间内进行修复。
+
+
 ## 关于 404 小说文库项目
 
 在这个 404 时代，由于种种原因，起点、晋江、刺猬猫、SF 等小说网站上的小说经常毫无征兆的消失。即使该小说已经入 V，即使你已经订阅了该小说。
@@ -156,12 +173,13 @@ EPUB 文件请使用相应阅读器阅读。
 | [笔趣阁](http://www.b5200.net/)                   | ✅       | ❎       |                                                                                          |
 | [言情小说](https://www.yqxsge.cc/)                | ✅       | ❎       |                                                                                          |
 | [18 看书](https://www.18kanshu.com/)              | ✅       | ❎       |                                                                                          |
+| [长篇X小说](https://book.xbookcn.net/)              | ✅       | ❎       |                                                                                          |
 | [笔下文学 333](http://www.bixia3.com/)            | ✅       | ❎       |                                                                                          |
 | [小说屋](http://www.xiaoshuowu.com/)              | ✅       | ❎       |                                                                                          |
 | [缤纷幻想](https://colorful-fantasybooks.com/)    | ✅       | ❎       |                                                                                          |
 | [弟子小说网](https://www.dizishu.com/xiaoshuo/)   | ✅       | ❎       |                                                                                          |
 | [新笔趣阁](https://www.ibiquge.la/)               | ✅       | ❎       |                                                                                          |
-| [69 书吧](https://www.69shu.com/)                 | ✅       | ❎       |                                                                                          |
+| [69 书吧](https://69shuba.cx/)                 | ✅       | ❎       |                                                                                          |
 | [笔下文学](https://www.ywggzy.com/)               | ✅       | ❎       |                                                                                          |
 | [飘天文学网](https://www.piaotia.com/)                | ✅       | ❎       |                                                                                          |
 | [红袖招](https://hongxiuzhao.me/)                 | ✅       | ❎       |                                                                                          |

src/detect.ts

@@ -3,7 +3,7 @@
 import { GmWindow } from "./global";
 import { _GM_info } from "./lib/GM";
 import { storageAvailable } from "./lib/localStorageExpired";
-import { enableDebug } from "./setting";
+import { enableDebug, skipTxtDownload } from "./setting";
 import { fetchWithRetry, fetchWithTimeout } from "./lib/http";
 
 function checkObjct(name: string) {
@@ -84,6 +84,7 @@ export const environments = async () => {
     Cookie: navigator.cookieEnabled,
     doNotTrack: navigator.doNotTrack ?? 0,
     enableDebug: enableDebug.value,
+    skipTxtDownload: skipTxtDownload.value,
     ScriptHandler: _GM_info.scriptHandler,
     "ScriptHandler version": _GM_info.version,
     "Novel-downloader version": _GM_info.script.version,

src/header.json

@@ -192,7 +192,8 @@
     "*://www.akatsuki-novels.com/stories/index/novel_id~*",
     "*://www.alphapolis.co.jp/novel/*/*",
     "*://novelup.plus/story/*",
-    "*://www.69shu.com/txt/*.htm",
+    "*://69shuba.cx/book/*.htm",
+    "*://book.xbookcn.net/search/label/*",
     "*://new-read.readmoo.com/mooreader/*",
     "*://www.iqingguo.com/book/detail/?id=*",
     "*://www.ywggzy.com/bxwx/*/",
@@ -213,7 +214,9 @@
     "*://www.42zw.la/book/*/",
     "*://www.boqugew.com/shu/*/",
     "*://www.qbtr.cc/*/*.html",
-    "*://b.guidaye.com/*/*/"
+    "*://b.guidaye.com/*/*/",
+    "*://www.esjzone.me/detail/*",
+    "*://www.esjzone.cc/detail/*"
   ],
   "exclude": [
     "*://www.jjwxc.net/onebook.php?novelid=*&chapterid=*",

src/router/download.ts

@@ -453,11 +453,16 @@ export async function getRule(): Promise<BaseRuleClass> {
       ruleClass = xiaoshuowu();
       break;
     }
-    case "www.69shu.com": {
-      const { c69shu } = await import("../rules/twoPage/69shu");
+    case "69shuba.cx": {
+      const { c69shu } = await import("../rules/onePageWithMultiIndexPage/69shu");
       ruleClass = c69shu();
       break;
     }
+    case "book.xbookcn.net": {
+      const { xbookcn } = await import("../rules/onePageWithMultiIndexPage/xbookcn");
+      ruleClass = xbookcn();
+      break;
+    }
     /* twoPage End */
 
     /** mbtxt **/
@@ -607,6 +612,12 @@ export async function getRule(): Promise<BaseRuleClass> {
       ruleClass = la42zw();
       break;
     }
+    case "www.esjzone.cc":
+    case "www.esjzone.me": {
+      const { esjzone } = await import("../rules/onePage/original/esjzone");
+      ruleClass = esjzone();
+      break;
+    }
     /** 笔趣阁END **/
 
     default: {

src/rules/onePage/original/esjzone.ts

@@ -0,0 +1,37 @@
+import { rm } from "../../../lib/dom";
+import { mkRuleClass } from "../template";
+
+export const esjzone = () =>
+  mkRuleClass({
+    bookUrl: document.location.href,
+    bookname: (
+      document.querySelector("h2") as HTMLElement
+    ).innerText.trim(),
+    author: (
+            Array.from(document.querySelectorAll('ul.book-detail li')).find(
+                li => li.textContent && li.textContent.includes('作者:')
+            )?.querySelector('a') as HTMLAnchorElement | null
+        )?.innerText.trim() || "Unknown Author",
+    introDom: document.querySelector(".description") as HTMLElement,
+    introDomPatch: (dom) => dom,
+    additionalMetadatePatch: (additionalMetadate) => {
+      additionalMetadate.tags = Array.from(
+        document.querySelectorAll(
+          'section.widget-tags.m-t-20 a.tag'
+        )
+      ).map((a) => (a as HTMLAnchorElement).innerText);
+      return additionalMetadate;
+    },
+    coverUrl: null,
+    aList: document.querySelectorAll('#chapterList a'),
+    getAName: (aElem) =>
+      (aElem as HTMLElement)?.innerText.trim(),
+    getContent: (dom) => dom.querySelector('.forum-content'),
+    contentPatch: (dom) => {
+      rm('h3', true, dom);
+      rm('footer', true, dom);
+      return dom;
+    },
+    language: "zh",
+    needLogin: true,
+  });

src/rules/onePage/original/syosetu.ts

@@ -1,11 +1,11 @@
 import { rm } from "../../../lib/dom";
 import { mkRuleClass } from "../template";
 
-const currentPageIndexBox = document.querySelector('.index_box');
+const currentPageIndexBox = document.querySelector('.p-eplist');
 
 // Attempt to get the first and last page anchors
-const firstPageAnchor = document.querySelector('.novelview_pager-first');
-const lastPageAnchor = document.querySelector('.novelview_pager-last');
+const firstPageAnchor = document.querySelector('.c-pager__item--first');
+const lastPageAnchor = document.querySelector('.c-pager__item--last');
 
 if (firstPageAnchor && lastPageAnchor) {
   // Fallback to the current URL if href is null, it means we're on the last or first page
@@ -29,7 +29,7 @@ if (firstPageAnchor && lastPageAnchor) {
       const html = await response.text();
       const parser = new DOMParser();
       const doc = parser.parseFromString(html, 'text/html');
-      const pageIndexBox = doc.querySelector('.index_box');
+      const pageIndexBox = doc.querySelector('.p-eplist');
       if (pageIndexBox && currentPageIndexBox) {
         const childrenArray = Array.from(pageIndexBox.children);
         if (insertAfterCurrentBox) {
@@ -72,15 +72,15 @@ export const syosetu = () => {
   };
   const getAList = () => {
     const _aList = document.querySelectorAll(
-      "dl.novel_sublist2 dd.subtitle > a"
+      "body > div.l-container > main > article > div.p-eplist > div > a"
     );
     if (_aList.length !== 0) {
       return _aList;
     } else {
       const a = document.createElement("a");
       a.href = document.location.href;
       a.innerText = (
-        document.querySelector(".novel_title") as HTMLElement
+        document.querySelector(".p-novel__title") as HTMLElement
       )?.innerText;
       return [a];
     }
@@ -94,26 +94,24 @@ export const syosetu = () => {
   return mkRuleClass({
     bookUrl: document.location.href,
     bookname: (
-      document.querySelector(".novel_title") as HTMLElement
+      document.querySelector(".p-novel__title") as HTMLElement
     ).innerText.trim(),
     author: (
       document.querySelector(
-        ".novel_writername > a, .novel_writername"
+        "body > div.l-container > main > article > div.p-novel__author > a"
       ) as HTMLAnchorElement
-    ).innerText
-      .replace("作者：", "")
-      .trim(),
+    ).innerText,
     introDom: getIntroDom(),
     introDomPatch: (dom) => dom,
     coverUrl: null,
     aList: getAList(),
-    sections: document.querySelectorAll("div.chapter_title"),
+    sections: document.querySelectorAll(".p-eplist__chapter-title"),
     getSName: (dom) => (dom as HTMLElement).innerText.trim(),
     getContent: (dom) => {
       const content = document.createElement("div");
-      const novelP = dom.querySelector("#novel_p");
-      const novelHonbun = dom.querySelector("#novel_honbun");
-      const novelA = dom.querySelector("#novel_a");
+      const novelP = dom.querySelector(".p-novel__text--preface");
+      const novelHonbun = dom.querySelector(".p-novel__text:not(.p-novel__text--preface):not(.p-novel__text--afterword)");
+      const novelA = dom.querySelector(".p-novel__text--afterword");
       if (novelP) {
         content.appendChild(novelP);
         const hr = dom.createElement("hr");

src/rules/onePageWithMultiIndexPage/69shu.ts

@@ -0,0 +1,82 @@
+import { rm, rm2 } from "../../lib/dom";
+import { getHtmlDOM } from "../../lib/http";
+import { mkRuleClass } from "./template";
+
+export const c69shu = () =>
+  mkRuleClass({
+    bookUrl: document.location.href,
+    bookname: document.querySelector("h1")?.innerText ?? "",
+    author: document.querySelector<HTMLAnchorElement>(
+        ".booknav2 > p:nth-child(3) > a"
+    )?.innerText ?? "",
+    introDom: 
+      document.querySelector(
+        ".lastcontent"
+      ) as HTMLParagraphElement,
+    introDomPatch: (content) => content,
+    coverUrl: document.querySelector<HTMLImageElement>(".bookimg2 > img")?.src ?? null,
+    getIndexPages: async () => {
+      const indexPages: Document[] = [];
+      const menuUrl = (
+        document.querySelector('a.btn.more-btn[href^="https://69shuba.cx/book/"]') as HTMLAnchorElement
+      ).href;
+      const doc = await getHtmlDOM(menuUrl, "GBK");
+      indexPages.push(doc);
+      return indexPages;
+    },
+    getAList: (doc) => Array.from(doc.querySelectorAll("#catalog ul a")).reverse() as unknown as NodeListOf<Element>,
+    getAName: (aElem) => (aElem as HTMLElement).innerText.trim(),
+    getContent: (doc) => doc.querySelector(".txtnav"),
+    contentPatch: (content) => {
+      rm(".hide720, .txtright, .bottom-ad", true, content);
+      rm2([/^谷[\u4e00-\u9fa5]{0,1}$/gm], content);
+
+      // Replace text nodes between <p> nodes with <p> nodes
+      const walker = document.createTreeWalker(content, NodeFilter.SHOW_TEXT, null);
+      const nodesToReplace = [];
+
+      while (walker.nextNode()) {
+        const node = walker.currentNode;
+        if (
+          node.parentNode &&
+          node.parentNode.nodeName !== 'P' &&
+          node.textContent &&
+          node.textContent.trim() !== ''
+        ) {
+          nodesToReplace.push(node);
+        }
+      }
+
+      nodesToReplace.forEach((node) => {
+        const p = document.createElement('p');
+        p.textContent = node.textContent;
+        if (node.parentNode) {
+          node.parentNode.replaceChild(p, node);
+        }
+      });
+
+      // Split <p> elements containing <br /> tags
+      const paragraphs = content.querySelectorAll('p');
+      const brRegex = /<br\s*\/?>/i;
+
+      paragraphs.forEach((p) => {
+        if (brRegex.test(p.innerHTML)) {
+          const parts = p.innerHTML.split(brRegex);
+          const fragment = document.createDocumentFragment();
+          parts.forEach((part) => {
+            const newP = document.createElement('p');
+            newP.innerHTML = part.trim();
+            if (newP.innerHTML !== '') {
+              fragment.appendChild(newP);
+            }
+          });
+          if (p.parentNode) {
+            p.parentNode.replaceChild(fragment, p);
+          }
+        }
+      });
+
+      return content;
+    },
+    language: "zh"
+  });

src/rules/onePageWithMultiIndexPage/xbookcn.ts

@@ -0,0 +1,38 @@
+import { getHtmlDOM } from "../../lib/http";
+import { mkRuleClass } from "./template";
+
+export const xbookcn = () =>
+  mkRuleClass({
+    bookUrl: document.location.href,
+    bookname: document.querySelector(".status-msg-body")?.textContent ?? "",
+    author: document.querySelector<HTMLAnchorElement>(
+        ".entry-content > p:nth-child(1)"
+    )?.innerText.split("：")[1] ?? "",
+    introDom: 
+      document.querySelector(
+        ".entry-content"
+      ) as HTMLParagraphElement,
+    introDomPatch: (content) => content,
+    coverUrl: null,
+    getIndexPages: async () => {
+        const bookUrl = document.location.origin + document.location.pathname;
+        const indexPages: Document[] = [];
+        let nextUrl = bookUrl;
+        do {
+          const doc = await getHtmlDOM(nextUrl, "UTF-8");
+          indexPages.push(doc);
+          nextUrl =
+            (
+              doc.querySelector(
+                "#Blog1_blog-pager-older-link"
+              ) as HTMLAnchorElement
+            )?.href ?? null;
+        } while (nextUrl);
+        return indexPages;
+    },
+    getAList: (doc) => doc.querySelectorAll("h3 > a"),
+    getAName: (aElem) => (aElem as HTMLElement).innerText.trim(),
+    getContent: (doc) => doc.querySelector(".entry-content") as HTMLElement,
+    contentPatch: (content) => content,
+    language: "zh",
+  });

src/save/epub.ts

@@ -278,6 +278,8 @@ export class EPUB extends Options {
       [
         `<?xml version="1.0" encoding="utf-8"?>`,
         htmlText
+          .replaceAll("<p><br /></p>", "")
+          .replaceAll("<p><br/></p>", "")
           .replaceAll("data-src-address", "src")
           .replaceAll(/[\u{0000}-\u{001f}]/gu, "")
           .replaceAll(/[\u{007f}-\u{009f}]/gu, "")