Qimao Novel Scraper logo

Qimao Novel Scraper

Community
Yunshiro
qimao-novel-scraper

七猫小说扫榜 → 挑标杆 → 拆解前3章 → 生成新书设定(多候选供用户选择)的一站式技能。当用户要求"扫七猫""七猫扫榜""看看七猫新书""挑一本标杆书""拆解前3章""对标写新书""设计新书设定""哪些小说好写/容易火/赚钱"等时使用。依赖 playwright MCP 浏览器工具。核心原则:扫描榜看简介 → 挑热门赛道里最能打的标杆 → 抓前3章拆解爽感骨架 → 产出 2~3 种新书设定候选让用户选 → 用户选定后再输出完整设定文档。

Overview

PublisherYunshiro
Repositoryyunn-skills
Skill nameqimao-novel-scraper
Stars
54
Forks
17
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Yunshiro on GitHub. Read the source before you install it.

Installation

Install the Qimao Novel Scraper AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Yunshiro/yunn-skills/tree/main/skills/qimao-novel-scraper
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Yunshiro/yunn-skills.git /tmp/yunn-skills
mkdir -p .claude/skills
cp -r /tmp/yunn-skills/skills/qimao-novel-scraper .claude/skills/qimao-novel-scraper
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qimao Novel Scraper in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Qimao Novel Scraper on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Qimao Novel Scraper is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

七猫扫榜 · 新书设定生成器

把「扫榜 → 挑标杆 → 拆前3章 → 出新书设定」全流程做成标准作业程序。产出的不是榜单搬运,而是可落地的写作选题方案。

一、目的与边界(重要)

  • 这个技能服务的是写作者的选题决策:哪些题材好写、新书容易火、容易赚钱。
  • 对标原则:换皮不换骨。保留标杆的"爽感骨架"(身份反差、金手指快速兑现、每章爽点+钩子、快速打脸),但世界观、主角身份、金手指机制、人物关系必须全部换掉,确保不构成抄袭。
  • 产出新书设定前,必须先给用户 2~3 种候选方向,等用户选定后再生成最终完整文档。禁止直接只出一个方案。

二、前置条件

  • playwright MCP 已连接(工具:browser_tabs / browser_navigate / browser_run_code_unsafe / browser_snapshot / browser_take_screenshot)。
  • 七猫无需登录即可抓取完整榜单与正文,无反爬。

三、七猫平台结构速查

内容URL 模式
官网首页https://www.qimao.com
男生新书榜·日榜https://www.qimao.com/paihang/boy/new/date
女生新书榜·日榜https://www.qimao.com/paihang/girl/new/date
通用榜单https://www.qimao.com/paihang/{sex}/{榜单类型}/{date|month}/(sex: boy/girl;榜单类型: new 新书、hot 热销等;date 日榜 / month 月榜)
书籍详情页https://www.qimao.com/shuku/{bookid}/
章节阅读页https://www.qimao.com/shuku/{bookid}-{chapterid}/
阅读器入口https://www.qimao.com/reader/index/{bookid}/
  • 5 种榜单 × 2 种性别 × 2 种时间维度 = 20 个固定入口,URL 规律统一,可程序化抓取。
  • 首页顶部常有平台政策动态(短剧剧本征集、高保底签约等)——这是"什么赚钱"的直接信号,抓首页时要留意并记录。

四、标准流程

Step 1 扫榜(数据采集)

用 browser_navigate 打开新书榜日榜(男生/女生按需),browser_run_code_unsafe 抓榜单:

js
async (page) => {
  await page.waitForTimeout(3000);
  return await page.evaluate(() => {
    const items = [];
    // 榜单每本书的容器选择器按页面实际结构调整,抓以下字段:
    // 排名、书名、作者、大类、小类、字数、热度、状态(连载/完结)、简介、最近更新+时间
    return JSON.stringify(items);
  });
}

注意:榜单页结构与通用选择器不匹配时,先用 browser_snapshot 看真实结构,再针对性写提取脚本。每本书要拿到详情页链接(格式 /shuku/{bookid}/)。

Step 2 分析榜单(情报提炼)

对 TOP20 做 5 个维度的观察,写进报告:

  • 题材分布:各大类占比(男频通常都市/玄幻主导)
  • 核心套路:身份反差 + 金手指 + 打脸公式的共性
  • 字数窗口:新书期热度窗口对应字数区间(七猫约 23-50 万字 / 2-3 个月)
  • 更新频率:上榜书是否当日更新(稳定日更是门槛)
  • 标题模板:简介是否用 【卖点1+卖点2+卖点3】 标签前缀
  • 热度断层:头部是否断崖领先

Step 3 挑标杆(关键决策)

选择逻辑:

  1. 选热门且好写、变现强的赛道(参考 Step 2 的题材分布,如玄幻/都市)
  2. 在该赛道内选排名最高、热度最猛的一本
  3. 优先选标题本身就是钩子的书(反套路标题是教科书)
  4. 记录选择理由(赛道占比 + 排名 + 热度 + 特色)

Step 4 看简介

打开详情页 /shuku/{bookid}/,抓简介全文 + 标签。

  • 简介选择器不确定时,用通用方法:遍历 p, .book-info, [class*="intro"], [class*="brief"] 等文本块,找 40~900 字区间的正文块。
  • 简介能告诉你:主题、卖点、金手指机制、人物关系——这是"这本书讲什么"的地图。

Step 5 抓前 3 章

  1. 详情页找"开始阅读"按钮(a, button 中 textContent 为"开始阅读"),点击后会在新标签页打开阅读器 /reader/index/{bookid}/——用 browser_tabs 切换过去。
  2. 正文容器:.chapter-detail-article(如失效,用通用方法扫描 [class*="read"], [class*="content"] 找正文块)。
  3. 目录容器:.book-catalog-list-content a 取章节链接(格式 /shuku/{bookid}-{chapterid}/)。
  4. 依次 browser_navigate 到第 1、2、3 章 URL,每章等待 2~3 秒后抓 .chapter-detail-article 全文。
  5. 每章约 2000 字,3 章共约 6000 字,完整存档原文(原文-标杆书-{书名}-前3章.md)。

Step 6 拆解(核心产出)

对照以下 checklist 逐项分析,写成拆解报告:

  • 开局钩子:第 1 句是否即高潮?背景设定是倒叙补还是先铺垫?(标杆做法:绝不铺垫,第一句就是冲突)
  • 金手指兑现:第几章兑现?爽点隔不隔夜?(标杆:第 2 章兑现,练气 1→4 层)
  • 每章结构:每章是否有 1 个完整爽点 + 1 个章末钩子?N 章 = N 次追读冲动
  • 打脸节奏:反派何时登场、多久被收拾?(标杆:势利未婚妻第 2 章登场、第 3 章被连招收服)
  • 设定为爽服务:金手指的一切规则是否只指向一个爽点?有没有多余设定?
  • 文风:短句密度、对话占比、笑点/反差梗。

Step 7 产出候选设定(必须多选,用户拍板)

拆解完成后,在对话中先给出 2~3 种候选新书设定方向,每种包含:

  • 题材/世界观一句话(如都市 / 玄幻 / 科幻 / 游戏 / 直播文…)
  • 一句话概念钩子
  • 主角身份 + 核心反差
  • 金手指机制(换一个,不抄标杆的)
  • 女主/关键人物
  • 前 3 章各章钩子简述

然后明确询问用户选哪一种(或要不要调整某个方向),等用户答复后再进入 Step 8。禁止跳过选择直接出文档。

Step 8 输出最终新书设定文档

用户选定后,生成完整设定文档(新书设定-{书名}.md),结构:

  1. 一句话核心卖点
  2. 书名(含备选 2~3 个,带标题钩子分析)
  3. 主角设定(身份、性格、动机、核心反差)
  4. 女主/重要配角
  5. 反派与大线(埋好长期冲突)
  6. 金手指机制(规则、成长曲线、爽点)
  7. 世界观/场景(一栋楼=微缩江湖这类同构设计)
  8. 前 3 章大纲(每章:钩子、爽点、章末悬念)
  9. 对标对照表(哪些算同构方法论、哪些是合法差异化,讲清"不抄"边界)
  10. 写作执行提醒(沿用拆解出的章法 checklist)

五、输出与落盘约定

  • 全部产物存 小说扫榜\七猫小说\,命名前缀:调研- / 原文- / 拆解- / 新书设定-,文件名带日期(跨天区分)。
  • 原文必须完整一字不改;拆解和新书设定是加工产物。
  • 完成后用 present_files 展示关键文件(拆解报告 + 新书设定 + 原文)。

六、踩坑记录(实测)

  • 榜单页通用选择器常抓空 → 先 snapshot 看真实 DOM 再写提取脚本。
  • 详情页简介选择器不固定 → 用文本块扫描法(40~900 字)兜底。
  • "开始阅读"点击后开新标签页 → 必须 browser_tabs 切换,否则抓到的是详情页。
  • 正文容器是 .chapter-detail-article,不是常见的 .content。
  • 章节链接格式 /shuku/{bookid}-{chapterid}/,直接从目录容器拿。
  • 每章抓取前等待 2~3 秒(懒加载)。
  • 书籍链接格式是 /shuku/{bookid}/ 不是 /book/。

七、可扩展

  • 同一套流程可平移到其他平台(起点、番茄、晋江),只需替换:榜单 URL、页面选择器、输出目录。
  • 女主/女生榜:跑同一流程但榜单入口用 /paihang/girl/...,题材分布结论会不同(言情/甜宠主导),拆解时注意赛道差异。

Frequently asked questions

What does the Qimao Novel Scraper AI skill do?

七猫小说扫榜 → 挑标杆 → 拆解前3章 → 生成新书设定(多候选供用户选择)的一站式技能。当用户要求"扫七猫""七猫扫榜""看看七猫新书""挑一本标杆书""拆解前3章""对标写新书""设计新书设定""哪些小说好写/容易火/赚钱"等时使用。依赖 playwright MCP 浏览器工具。核心原则:扫描榜看简介 → 挑热门赛道里最能打的标杆 → 抓前3章拆解爽感骨架 → 产出 2~3 种新书设定候选让用户选 → 用户选定后再输出完整设定文档。

Why use Qimao Novel Scraper on TypingMind?

Because you install it once and use it with any model. Qimao Novel Scraper is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Qimao Novel Scraper in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Yunshiro/yunn-skills/tree/main/skills/qimao-novel-scraper. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Qimao Novel Scraper?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Qimao Novel Scraper?

As many as you like. As long as a model supports skills, you can use Qimao Novel Scraper with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Qimao Novel Scraper AI skill free?

Yes. It is published on GitHub by Yunshiro under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇