mirror of
https://github.com/JimLiu/baoyu-skills.git
synced 2026-07-10 13:11:30 +00:00
Compare commits
14 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Jim Liu 宝玉
|
dad8f3a800 | ||
|
Jim Liu 宝玉
|
35298d7c9d | ||
|
Jim Liu 宝玉
|
f22374ab62 | ||
|
Jim Liu 宝玉
|
d4e80b1bc3 | ||
|
Jim Liu 宝玉
|
a5761dc71a | ||
|
Jim Liu 宝玉
|
a5189dff37 | ||
|
Jim Liu 宝玉
|
39fe872bf3 | ||
|
Jim Liu 宝玉
|
52813504f8 | ||
|
Jim Liu 宝玉
|
a4d4108cd1 | ||
 Yizhou Qian 钱亦舟
|
d7e763f1f5 | ||
|
Jim Liu 宝玉
|
097c09c59b | ||
|
Jim Liu 宝玉
|
e4cd8bfefc | ||
|
Jim Liu 宝玉
|
3dc5f2e06f | ||
|
Jim Liu 宝玉
|
e5d6c8ec68 |
@@ -6,48 +6,32 @@
|
||||
},
|
||||
"metadata": {
|
||||
"description": "Skills shared by Baoyu for improving daily work efficiency",
|
||||
"version": "1.77.0"
|
||||
"version": "1.79.2"
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
"name": "content-skills",
|
||||
"description": "Content generation and publishing skills",
|
||||
"name": "baoyu-skills",
|
||||
"description": "Content generation, AI backends, and utility tools for daily work efficiency",
|
||||
"source": "./",
|
||||
"strict": true,
|
||||
"skills": [
|
||||
"./skills/baoyu-xhs-images",
|
||||
"./skills/baoyu-post-to-x",
|
||||
"./skills/baoyu-post-to-wechat",
|
||||
"./skills/baoyu-post-to-weibo",
|
||||
"./skills/baoyu-article-illustrator",
|
||||
"./skills/baoyu-cover-image",
|
||||
"./skills/baoyu-slide-deck",
|
||||
"./skills/baoyu-comic",
|
||||
"./skills/baoyu-infographic"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "ai-generation-skills",
|
||||
"description": "AI-powered generation backends",
|
||||
"source": "./",
|
||||
"strict": true,
|
||||
"skills": [
|
||||
"./skills/baoyu-danger-gemini-web",
|
||||
"./skills/baoyu-image-gen"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "utility-skills",
|
||||
"description": "Utility tools for content processing",
|
||||
"source": "./",
|
||||
"strict": true,
|
||||
"skills": [
|
||||
"./skills/baoyu-danger-x-to-markdown",
|
||||
"./skills/baoyu-compress-image",
|
||||
"./skills/baoyu-url-to-markdown",
|
||||
"./skills/baoyu-cover-image",
|
||||
"./skills/baoyu-danger-gemini-web",
|
||||
"./skills/baoyu-danger-x-to-markdown",
|
||||
"./skills/baoyu-format-markdown",
|
||||
"./skills/baoyu-image-gen",
|
||||
"./skills/baoyu-infographic",
|
||||
"./skills/baoyu-markdown-to-html",
|
||||
"./skills/baoyu-post-to-weibo",
|
||||
"./skills/baoyu-post-to-wechat",
|
||||
"./skills/baoyu-post-to-x",
|
||||
"./skills/baoyu-slide-deck",
|
||||
"./skills/baoyu-translate",
|
||||
"./skills/baoyu-url-to-markdown",
|
||||
"./skills/baoyu-xhs-images",
|
||||
"./skills/baoyu-youtube-transcript"
|
||||
]
|
||||
}
|
||||
|
||||
@@ -2,6 +2,41 @@
|
||||
|
||||
English | [中文](./CHANGELOG.zh.md)
|
||||
|
||||
## 1.79.2 - 2026-03-23
|
||||
|
||||
### Fixes
|
||||
- `baoyu-cover-image`: simplify reference image handling — use `--ref` when model supports it, only create description files for models without reference image support
|
||||
- `baoyu-post-to-weibo`: add no-theme rule for article markdown-to-HTML conversion
|
||||
|
||||
### Tests
|
||||
- Fix Node-compatible parser tests and add parser test dependencies
|
||||
|
||||
## 1.79.1 - 2026-03-23
|
||||
|
||||
### Fixes
|
||||
- Consolidate to single plugin to prevent duplicate skill registration (by @TyrealQ)
|
||||
- `baoyu-article-illustrator`: remove opacity parameter from watermark prompt
|
||||
- `baoyu-comic`: fix Doraemon naming spacing and remove opacity from watermark prompt
|
||||
- `baoyu-xhs-images`: remove opacity from watermark prompt and fix CJK spacing
|
||||
|
||||
### Documentation
|
||||
- Update project documentation to reflect single-plugin architecture
|
||||
|
||||
## 1.79.0 - 2026-03-22
|
||||
|
||||
### Features
|
||||
- `baoyu-post-to-wechat`: improve credential loading with multi-source resolution, priority ordering, and diagnostics for skipped incomplete sources
|
||||
|
||||
## 1.78.0 - 2026-03-22
|
||||
|
||||
### Features
|
||||
- `baoyu-url-to-markdown`: add URL-specific parser layer for X/Twitter and archive.ph sites
|
||||
- `baoyu-url-to-markdown`: improved slug generation with stop words removal and subdirectory output structure
|
||||
|
||||
### Fixes
|
||||
- `baoyu-url-to-markdown`: preserve anchor elements containing media in legacy converter
|
||||
- `baoyu-url-to-markdown`: smarter title deduplication to avoid redundant headings
|
||||
|
||||
## 1.77.0 - 2026-03-22
|
||||
|
||||
### Features
|
||||
|
||||
@@ -2,6 +2,41 @@
|
||||
|
||||
[English](./CHANGELOG.md) | 中文
|
||||
|
||||
## 1.79.2 - 2026-03-23
|
||||
|
||||
### 修复
|
||||
- `baoyu-cover-image`：简化参考图片处理流程 — 模型支持 `--ref` 时直接传递，仅在模型不支持参考图时创建描述文件
|
||||
- `baoyu-post-to-weibo`：文章 Markdown 转 HTML 时不传递 --theme 参数
|
||||
|
||||
### 测试
|
||||
- 修复 Node 兼容的解析器测试，添加解析器测试依赖
|
||||
|
||||
## 1.79.1 - 2026-03-23
|
||||
|
||||
### 修复
|
||||
- 合并为单一插件，防止 skill 重复注册 (by @TyrealQ)
|
||||
- `baoyu-article-illustrator`：移除水印提示词中的不透明度参数
|
||||
- `baoyu-comic`：修正哆啦 A 梦命名间距，移除水印不透明度参数
|
||||
- `baoyu-xhs-images`：移除水印不透明度参数，修正中英文间距
|
||||
|
||||
### 文档
|
||||
- 更新项目文档以反映单一插件架构
|
||||
|
||||
## 1.79.0 - 2026-03-22
|
||||
|
||||
### 新功能
|
||||
- `baoyu-post-to-wechat`：改进凭据加载机制，支持多来源优先级解析，并提供不完整凭据来源的诊断信息
|
||||
|
||||
## 1.78.0 - 2026-03-22
|
||||
|
||||
### 新功能
|
||||
- `baoyu-url-to-markdown`：新增 URL 专用解析层，支持 X/Twitter 和 archive.ph 站点的定制化 HTML 提取
|
||||
- `baoyu-url-to-markdown`：改进 slug 生成算法，去除停用词并采用子目录输出结构
|
||||
|
||||
### 修复
|
||||
- `baoyu-url-to-markdown`：旧版转换器保留包含媒体元素的锚标签
|
||||
- `baoyu-url-to-markdown`：更智能的标题去重，避免重复添加标题
|
||||
|
||||
## 1.77.0 - 2026-03-22
|
||||
|
||||
### 新功能
|
||||
|
||||
@@ -1,16 +1,16 @@
|
||||
# CLAUDE.md
|
||||
|
||||
Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.77.0**.
|
||||
Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.79.2**.
|
||||
|
||||
## Architecture
|
||||
|
||||
Skills organized into three categories in `.claude-plugin/marketplace.json` (defines plugin metadata, version, and skill paths):
|
||||
Skills are exposed through the single `baoyu-skills` plugin in `.claude-plugin/marketplace.json` (which defines plugin metadata, version, and skill paths). The repo docs still group them into three logical areas:
|
||||
|
||||
| Category | Description |
|
||||
|----------|-------------|
|
||||
| `content-skills` | Generate or publish content (images, slides, comics, posts) |
|
||||
| `ai-generation-skills` | AI generation backends |
|
||||
| `utility-skills` | Content processing (conversion, compression, translation) |
|
||||
| Group | Description |
|
||||
|-------|-------------|
|
||||
| Content Skills | Generate or publish content (images, slides, comics, posts) |
|
||||
| AI Generation Skills | AI generation backends |
|
||||
| Utility Skills | Content processing (conversion, compression, translation) |
|
||||
|
||||
Each skill contains `SKILL.md` (YAML front matter + docs), optional `scripts/`, `references/`, `prompts/`.
|
||||
|
||||
|
||||
@@ -52,16 +52,14 @@ Run the following command in Claude Code:
|
||||
|
||||
1. Select **Browse and install plugins**
|
||||
2. Select **baoyu-skills**
|
||||
3. Select the plugin(s) you want to install
|
||||
3. Select the **baoyu-skills** plugin
|
||||
4. Select **Install now**
|
||||
|
||||
**Option 2: Direct Install**
|
||||
|
||||
```bash
|
||||
# Install specific plugin
|
||||
/plugin install content-skills@baoyu-skills
|
||||
/plugin install ai-generation-skills@baoyu-skills
|
||||
/plugin install utility-skills@baoyu-skills
|
||||
# Install the marketplace's single plugin
|
||||
/plugin install baoyu-skills@baoyu-skills
|
||||
```
|
||||
|
||||
**Option 3: Ask the Agent**
|
||||
@@ -70,13 +68,13 @@ Simply tell Claude Code:
|
||||
|
||||
> Please install Skills from github.com/JimLiu/baoyu-skills
|
||||
|
||||
### Available Plugins
|
||||
### Available Plugin
|
||||
|
||||
| Plugin | Description | Skills |
|
||||
|--------|-------------|--------|
|
||||
| **content-skills** | Content generation and publishing | [xhs-images](#baoyu-xhs-images), [infographic](#baoyu-infographic), [cover-image](#baoyu-cover-image), [slide-deck](#baoyu-slide-deck), [comic](#baoyu-comic), [article-illustrator](#baoyu-article-illustrator), [post-to-x](#baoyu-post-to-x), [post-to-wechat](#baoyu-post-to-wechat), [post-to-weibo](#baoyu-post-to-weibo) |
|
||||
| **ai-generation-skills** | AI-powered generation backends | [image-gen](#baoyu-image-gen), [danger-gemini-web](#baoyu-danger-gemini-web) |
|
||||
| **utility-skills** | Utility tools for content processing | [youtube-transcript](#baoyu-youtube-transcript), [url-to-markdown](#baoyu-url-to-markdown), [danger-x-to-markdown](#baoyu-danger-x-to-markdown), [compress-image](#baoyu-compress-image), [format-markdown](#baoyu-format-markdown), [markdown-to-html](#baoyu-markdown-to-html), [translate](#baoyu-translate) |
|
||||
The marketplace now exposes a single plugin so each skill is registered exactly once.
|
||||
|
||||
| Plugin | Description | Includes |
|
||||
|--------|-------------|----------|
|
||||
| **baoyu-skills** | Content generation, AI backends, and utility tools for daily work efficiency | All skills in this repository, organized below as Content Skills, AI Generation Skills, and Utility Skills |
|
||||
|
||||
## Update Skills
|
||||
|
||||
|
||||
+7
-9
@@ -52,16 +52,14 @@ clawhub install baoyu-markdown-to-html
|
||||
|
||||
1. 选择 **Browse and install plugins**
|
||||
2. 选择 **baoyu-skills**
|
||||
3. 选择要安装的插件
|
||||
3. 选择 **baoyu-skills** 插件
|
||||
4. 选择 **Install now**
|
||||
|
||||
**方式二：直接安装**
|
||||
|
||||
```bash
|
||||
# 安装指定插件
|
||||
/plugin install content-skills@baoyu-skills
|
||||
/plugin install ai-generation-skills@baoyu-skills
|
||||
/plugin install utility-skills@baoyu-skills
|
||||
# 安装 marketplace 中唯一的插件
|
||||
/plugin install baoyu-skills@baoyu-skills
|
||||
```
|
||||
|
||||
**方式三：告诉 Agent**
|
||||
@@ -72,11 +70,11 @@ clawhub install baoyu-markdown-to-html
|
||||
|
||||
### 可用插件
|
||||
|
||||
| 插件 | 说明 | 包含技能 |
|
||||
现在 marketplace 只暴露一个插件，这样每个 skill 只会注册一次。
|
||||
|
||||
| 插件 | 说明 | 包含内容 |
|
||||
|------|------|----------|
|
||||
| **content-skills** | 内容生成和发布 | [xhs-images](#baoyu-xhs-images), [infographic](#baoyu-infographic), [cover-image](#baoyu-cover-image), [slide-deck](#baoyu-slide-deck), [comic](#baoyu-comic), [article-illustrator](#baoyu-article-illustrator), [post-to-x](#baoyu-post-to-x), [post-to-wechat](#baoyu-post-to-wechat), [post-to-weibo](#baoyu-post-to-weibo) |
|
||||
| **ai-generation-skills** | AI 生成后端 | [image-gen](#baoyu-image-gen), [danger-gemini-web](#baoyu-danger-gemini-web) |
|
||||
| **utility-skills** | 内容处理工具 | [youtube-transcript](#baoyu-youtube-transcript), [url-to-markdown](#baoyu-url-to-markdown), [danger-x-to-markdown](#baoyu-danger-x-to-markdown), [compress-image](#baoyu-compress-image), [format-markdown](#baoyu-format-markdown), [markdown-to-html](#baoyu-markdown-to-html), [translate](#baoyu-translate) |
|
||||
| **baoyu-skills** | 提供内容生成、AI 后端和日常效率工具技能 | 仓库中的全部 skills，仍按下方的内容技能、AI 生成技能、工具技能三个分类展示 |
|
||||
|
||||
## 更新技能
|
||||
|
||||
|
||||
+11
-9
@@ -34,20 +34,22 @@ metadata:
|
||||
1. Create `skills/baoyu-<name>/SKILL.md` with YAML front matter
|
||||
2. Add TypeScript in `skills/baoyu-<name>/scripts/` (if applicable)
|
||||
3. Add prompt templates in `skills/baoyu-<name>/prompts/` if needed
|
||||
4. Register in `marketplace.json` under appropriate category
|
||||
4. Register the skill in `.claude-plugin/marketplace.json` under the `baoyu-skills` plugin entry
|
||||
5. Add Script Directory section to SKILL.md if skill has scripts
|
||||
6. Add openclaw metadata to frontmatter
|
||||
|
||||
## Category Selection
|
||||
## Skill Grouping
|
||||
|
||||
| If your skill... | Use category |
|
||||
|------------------|--------------|
|
||||
| Generates visual content (images, slides, comics) | `content-skills` |
|
||||
| Publishes to platforms (X, WeChat, Weibo) | `content-skills` |
|
||||
| Provides AI generation backend | `ai-generation-skills` |
|
||||
| Converts or processes content | `utility-skills` |
|
||||
All skills are registered under the single `baoyu-skills` plugin. Use these logical groups when deciding where the skill should appear in the docs:
|
||||
|
||||
New category: add plugin object to `marketplace.json` with `name`, `description`, `skills[]`.
|
||||
| If your skill... | Use group |
|
||||
|------------------|-----------|
|
||||
| Generates visual content (images, slides, comics) | Content Skills |
|
||||
| Publishes to platforms (X, WeChat, Weibo) | Content Skills |
|
||||
| Provides AI generation backend | AI Generation Skills |
|
||||
| Converts or processes content | Utility Skills |
|
||||
|
||||
If you add a new logical group, update the docs that present grouped skills, but keep the skill registered under the single `baoyu-skills` plugin entry.
|
||||
|
||||
## Writing Descriptions
|
||||
|
||||
|
||||
Generated
+105
-1
@@ -9,7 +9,11 @@
|
||||
"packages/*"
|
||||
],
|
||||
"devDependencies": {
|
||||
"tsx": "^4.20.5"
|
||||
"@mozilla/readability": "^0.6.0",
|
||||
"linkedom": "^0.18.12",
|
||||
"tsx": "^4.20.5",
|
||||
"turndown": "^7.2.2",
|
||||
"turndown-plugin-gfm": "^1.0.2"
|
||||
}
|
||||
},
|
||||
"node_modules/@esbuild/aix-ppc64": {
|
||||
@@ -454,6 +458,23 @@
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/@mixmark-io/domino": {
|
||||
"version": "2.2.0",
|
||||
"resolved": "https://registry.npmjs.org/@mixmark-io/domino/-/domino-2.2.0.tgz",
|
||||
"integrity": "sha512-Y28PR25bHXUg88kCV7nivXrP2Nj2RueZ3/l/jdx6J9f8J4nsEGcgX0Qe6lt7Pa+J79+kPiJU3LguR6O/6zrLOw==",
|
||||
"dev": true,
|
||||
"license": "BSD-2-Clause"
|
||||
},
|
||||
"node_modules/@mozilla/readability": {
|
||||
"version": "0.6.0",
|
||||
"resolved": "https://registry.npmjs.org/@mozilla/readability/-/readability-0.6.0.tgz",
|
||||
"integrity": "sha512-juG5VWh4qAivzTAeMzvY9xs9HY5rAcr2E4I7tiSSCokRFi7XIZCAu92ZkSTsIj1OPceCifL3cpfteP3pDT9/QQ==",
|
||||
"dev": true,
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">=14.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/debug": {
|
||||
"version": "4.1.12",
|
||||
"resolved": "https://registry.npmjs.org/@types/debug/-/debug-4.1.12.tgz",
|
||||
@@ -615,6 +636,13 @@
|
||||
"url": "https://github.com/sponsors/fb55"
|
||||
}
|
||||
},
|
||||
"node_modules/cssom": {
|
||||
"version": "0.5.0",
|
||||
"resolved": "https://registry.npmjs.org/cssom/-/cssom-0.5.0.tgz",
|
||||
"integrity": "sha512-iKuQcq+NdHqlAcwUY0o/HL69XQrUaQdMjmStJ8JFmUaiiQErlhrmuigkg/CU4E2J0IyUKUrMAgl36TvN67MqTw==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/debug": {
|
||||
"version": "4.4.3",
|
||||
"resolved": "https://registry.npmjs.org/debug/-/debug-4.4.3.tgz",
|
||||
@@ -896,6 +924,13 @@
|
||||
"node": ">=12.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/html-escaper": {
|
||||
"version": "3.0.3",
|
||||
"resolved": "https://registry.npmjs.org/html-escaper/-/html-escaper-3.0.3.tgz",
|
||||
"integrity": "sha512-RuMffC89BOWQoY0WKGpIhn5gX3iI54O6nRA0yC124NYVtzjmFWBIiFd8M0x+ZdX0P9R4lADg1mgP8C7PxGOWuQ==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/htmlparser2": {
|
||||
"version": "9.1.0",
|
||||
"resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-9.1.0.tgz",
|
||||
@@ -984,6 +1019,51 @@
|
||||
"node": ">=18.17"
|
||||
}
|
||||
},
|
||||
"node_modules/linkedom": {
|
||||
"version": "0.18.12",
|
||||
"resolved": "https://registry.npmjs.org/linkedom/-/linkedom-0.18.12.tgz",
|
||||
"integrity": "sha512-jalJsOwIKuQJSeTvsgzPe9iJzyfVaEJiEXl+25EkKevsULHvMJzpNqwvj1jOESWdmgKDiXObyjOYwlUqG7wo1Q==",
|
||||
"dev": true,
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"css-select": "^5.1.0",
|
||||
"cssom": "^0.5.0",
|
||||
"html-escaper": "^3.0.3",
|
||||
"htmlparser2": "^10.0.0",
|
||||
"uhyphen": "^0.2.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=16"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"canvas": ">= 2"
|
||||
},
|
||||
"peerDependenciesMeta": {
|
||||
"canvas": {
|
||||
"optional": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/linkedom/node_modules/htmlparser2": {
|
||||
"version": "10.1.0",
|
||||
"resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-10.1.0.tgz",
|
||||
"integrity": "sha512-VTZkM9GWRAtEpveh7MSF6SjjrpNVNNVJfFup7xTY3UpFtm67foy9HDVXneLtFVt4pMz5kZtgNcvCniNFb1hlEQ==",
|
||||
"dev": true,
|
||||
"funding": [
|
||||
"https://github.com/fb55/htmlparser2?sponsor=1",
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/fb55"
|
||||
}
|
||||
],
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"domelementtype": "^2.3.0",
|
||||
"domhandler": "^5.0.3",
|
||||
"domutils": "^3.2.2",
|
||||
"entities": "^7.0.1"
|
||||
}
|
||||
},
|
||||
"node_modules/longest-streak": {
|
||||
"version": "3.1.0",
|
||||
"resolved": "https://registry.npmjs.org/longest-streak/-/longest-streak-3.1.0.tgz",
|
||||
@@ -1768,6 +1848,30 @@
|
||||
"fsevents": "~2.3.3"
|
||||
}
|
||||
},
|
||||
"node_modules/turndown": {
|
||||
"version": "7.2.2",
|
||||
"resolved": "https://registry.npmjs.org/turndown/-/turndown-7.2.2.tgz",
|
||||
"integrity": "sha512-1F7db8BiExOKxjSMU2b7if62D/XOyQyZbPKq/nUwopfgnHlqXHqQ0lvfUTeUIr1lZJzOPFn43dODyMSIfvWRKQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@mixmark-io/domino": "^2.2.0"
|
||||
}
|
||||
},
|
||||
"node_modules/turndown-plugin-gfm": {
|
||||
"version": "1.0.2",
|
||||
"resolved": "https://registry.npmjs.org/turndown-plugin-gfm/-/turndown-plugin-gfm-1.0.2.tgz",
|
||||
"integrity": "sha512-vwz9tfvF7XN/jE0dGoBei3FXWuvll78ohzCZQuOb+ZjWrs3a0XhQVomJEb2Qh4VHTPNRO4GPZh0V7VRbiWwkRg==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/uhyphen": {
|
||||
"version": "0.2.0",
|
||||
"resolved": "https://registry.npmjs.org/uhyphen/-/uhyphen-0.2.0.tgz",
|
||||
"integrity": "sha512-qz3o9CHXmJJPGBdqzab7qAYuW8kQGKNEuoHFYrBwV6hWIMcpAmxDLXojcHfFr9US1Pe6zUswEIJIbLI610fuqA==",
|
||||
"dev": true,
|
||||
"license": "ISC"
|
||||
},
|
||||
"node_modules/undici": {
|
||||
"version": "6.24.0",
|
||||
"resolved": "https://registry.npmjs.org/undici/-/undici-6.24.0.tgz",
|
||||
|
||||
@@ -10,6 +10,10 @@
|
||||
"test:coverage": "node --import tsx --experimental-test-coverage --test"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@mozilla/readability": "^0.6.0",
|
||||
"linkedom": "^0.18.12",
|
||||
"turndown": "^7.2.2",
|
||||
"turndown-plugin-gfm": "^1.0.2",
|
||||
"tsx": "^4.20.5"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -280,5 +280,5 @@ TEXTURE: Halftone transitions between sides
|
||||
If watermark enabled in preferences, append:
|
||||
|
||||
```
|
||||
Include a subtle watermark "[content]" positioned at [position] with approximately [opacity*100]% visibility.
|
||||
Include a subtle watermark "[content]" positioned at [position].
|
||||
```
|
||||
|
||||
@@ -278,7 +278,7 @@ Create storyboard and character definitions using the confirmed style from Step
|
||||
| Role | Character | Visual Description |
|
||||
|------|-----------|-------------------|
|
||||
| Student | 大雄 (Nobita) | Japanese boy, 10yo, round glasses, black hair parted in middle, yellow shirt, navy shorts |
|
||||
| Mentor | 哆啦A梦 (Doraemon) | Round blue robot cat, big white eyes, red nose, whiskers, white belly with 4D pocket, golden bell, no ears |
|
||||
| Mentor | 哆啦 A 梦 (Doraemon) | Round blue robot cat, big white eyes, red nose, whiskers, white belly with 4D pocket, golden bell, no ears |
|
||||
| Challenge | 胖虎 (Gian) | Stocky boy, rough features, small eyes, orange shirt |
|
||||
| Support | 静香 (Shizuka) | Cute girl, black short hair, pink dress, gentle expression |
|
||||
|
||||
@@ -359,8 +359,7 @@ Art: [art style] | Tone: [tone] | Layout: [layout type]
|
||||
**Watermark Application** (if enabled in preferences):
|
||||
Add to each prompt:
|
||||
```
|
||||
Include a subtle watermark "[content]" positioned at [position]
|
||||
with approximately [opacity*100]% visibility. The watermark should
|
||||
Include a subtle watermark "[content]" positioned at [position]. The watermark should
|
||||
be legible but not distracting from the comic panels and storytelling.
|
||||
Ensure watermark does not overlap speech bubbles or key action.
|
||||
```
|
||||
@@ -452,8 +451,8 @@ When skill does NOT support reference images, create combined prompt files:
|
||||
|
||||
## Character Reference (maintain consistency)
|
||||
[Copy relevant sections from characters/characters.md here]
|
||||
- 大雄: Japanese boy, round glasses, yellow shirt, navy shorts...
|
||||
- 哆啦A梦: Round blue robot cat, white belly, red nose, golden bell...
|
||||
- 大雄：Japanese boy, round glasses, yellow shirt, navy shorts...
|
||||
- 哆啦 A 梦：Round blue robot cat, white belly, red nose, golden bell...
|
||||
|
||||
## Page Content
|
||||
[Original page prompt here]
|
||||
|
||||
@@ -162,15 +162,14 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md") { "user" }
|
||||
5. **Detect language**: Compare source, user input, EXTEND.md preference
|
||||
6. **Determine output directory**: Per File Structure rules
|
||||
|
||||
**⚠️ People in Reference Images — MUST follow all 3 rules:**
|
||||
**⚠️ People in Reference Images:**
|
||||
|
||||
If reference images contain **people** who should appear in the cover:
|
||||
|
||||
1. **`usage: direct`** — MUST set in refs description file. NEVER use `style` or `palette` when people need to appear
|
||||
2. **Per-character description** — MUST describe each person's distinctive features (hair, glasses, skin tone, clothing) in `refs/ref-NN-{slug}.md`. Vague descriptions like "a man" will fail
|
||||
3. **`--ref` flag** — MUST pass reference image via `--ref` in Step 4 so the model sees actual faces
|
||||
- **Model supports `--ref`** (default): Copy image to `refs/`, pass via `--ref` at generation. No description file needed — the model sees the face directly.
|
||||
- **Model does NOT support `--ref`** (Jimeng, Seedream 3.0): Create `refs/ref-NN-{slug}.md` with per-character description (hair, glasses, skin tone, clothing). Embed as MUST/REQUIRED instructions in prompt text.
|
||||
|
||||
See [reference-images.md § Character Analysis](references/workflow/reference-images.md) for description format.
|
||||
See [reference-images.md](references/workflow/reference-images.md) for full decision table.
|
||||
|
||||
### Step 2: Confirm Options ⚠️
|
||||
|
||||
|
||||
@@ -16,17 +16,24 @@ Guide for processing user-provided reference images in cover generation.
|
||||
|
||||
**If user provides file path**:
|
||||
1. Copy to `refs/ref-NN-{slug}.{ext}` (NN = 01, 02, ...)
|
||||
2. Create description: `refs/ref-NN-{slug}.md`
|
||||
3. Verify files exist before proceeding
|
||||
2. **Only** create description file `refs/ref-NN-{slug}.md` when model does NOT support `--ref` (see below)
|
||||
3. Verify image file exists before proceeding
|
||||
|
||||
**Description File Format**:
|
||||
**When to create description file**:
|
||||
|
||||
| Situation | Action |
|
||||
|-----------|--------|
|
||||
| Model supports `--ref` (Google, OpenAI, OpenRouter, Replicate, Seedream 4.0+) | Copy image only. **No description file needed.** Pass via `--ref` at generation. |
|
||||
| Model does NOT support `--ref` (Jimeng, Seedream 3.0) | Copy image + create description file. Embed description in prompt text. |
|
||||
|
||||
**Description File Format** (only when needed):
|
||||
```yaml
|
||||
---
|
||||
ref_id: NN
|
||||
filename: ref-NN-{slug}.{ext}
|
||||
usage: direct | style | palette
|
||||
---
|
||||
[User's description or auto-generated description]
|
||||
[Character or style description to embed in prompt]
|
||||
```
|
||||
|
||||
| Usage | When to Use |
|
||||
|
||||
@@ -694,6 +694,10 @@ async function main(): Promise<void> {
|
||||
}
|
||||
|
||||
const creds = loadCredentials(resolved);
|
||||
for (const skippedSource of creds.skippedSources) {
|
||||
console.error(`[wechat-api] Skipped incomplete credential source: ${skippedSource}`);
|
||||
}
|
||||
console.error(`[wechat-api] Credentials source: ${creds.source}`);
|
||||
console.error("[wechat-api] Fetching access token...");
|
||||
const accessToken = await fetchAccessToken(creds.appId, creds.appSecret);
|
||||
|
||||
|
||||
@@ -0,0 +1,139 @@
|
||||
import assert from "node:assert/strict";
|
||||
import fs from "node:fs/promises";
|
||||
import os from "node:os";
|
||||
import path from "node:path";
|
||||
import process from "node:process";
|
||||
import test, { type TestContext } from "node:test";
|
||||
|
||||
import { loadCredentials } from "./wechat-extend-config.ts";
|
||||
|
||||
function useCwd(t: TestContext, cwd: string): void {
|
||||
const previous = process.cwd();
|
||||
process.chdir(cwd);
|
||||
t.after(() => {
|
||||
process.chdir(previous);
|
||||
});
|
||||
}
|
||||
|
||||
function useHome(t: TestContext, home: string): void {
|
||||
const previous = process.env.HOME;
|
||||
process.env.HOME = home;
|
||||
t.after(() => {
|
||||
if (previous === undefined) {
|
||||
delete process.env.HOME;
|
||||
return;
|
||||
}
|
||||
process.env.HOME = previous;
|
||||
});
|
||||
}
|
||||
|
||||
function useWechatEnv(
|
||||
t: TestContext,
|
||||
values: Partial<Record<"WECHAT_APP_ID" | "WECHAT_APP_SECRET", string | undefined>>,
|
||||
): void {
|
||||
const previous = {
|
||||
WECHAT_APP_ID: process.env.WECHAT_APP_ID,
|
||||
WECHAT_APP_SECRET: process.env.WECHAT_APP_SECRET,
|
||||
};
|
||||
|
||||
if (values.WECHAT_APP_ID === undefined) {
|
||||
delete process.env.WECHAT_APP_ID;
|
||||
} else {
|
||||
process.env.WECHAT_APP_ID = values.WECHAT_APP_ID;
|
||||
}
|
||||
|
||||
if (values.WECHAT_APP_SECRET === undefined) {
|
||||
delete process.env.WECHAT_APP_SECRET;
|
||||
} else {
|
||||
process.env.WECHAT_APP_SECRET = values.WECHAT_APP_SECRET;
|
||||
}
|
||||
|
||||
t.after(() => {
|
||||
if (previous.WECHAT_APP_ID === undefined) {
|
||||
delete process.env.WECHAT_APP_ID;
|
||||
} else {
|
||||
process.env.WECHAT_APP_ID = previous.WECHAT_APP_ID;
|
||||
}
|
||||
|
||||
if (previous.WECHAT_APP_SECRET === undefined) {
|
||||
delete process.env.WECHAT_APP_SECRET;
|
||||
} else {
|
||||
process.env.WECHAT_APP_SECRET = previous.WECHAT_APP_SECRET;
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
async function makeTempDir(prefix: string): Promise<string> {
|
||||
return fs.mkdtemp(path.join(os.tmpdir(), prefix));
|
||||
}
|
||||
|
||||
async function writeEnvFile(root: string, content: string): Promise<void> {
|
||||
const envPath = path.join(root, ".baoyu-skills", ".env");
|
||||
await fs.mkdir(path.dirname(envPath), { recursive: true });
|
||||
await fs.writeFile(envPath, content);
|
||||
}
|
||||
|
||||
test("loadCredentials selects the first complete source without mixing values across sources", async (t) => {
|
||||
const cwdRoot = await makeTempDir("wechat-creds-cwd-");
|
||||
const homeRoot = await makeTempDir("wechat-creds-home-");
|
||||
|
||||
useCwd(t, cwdRoot);
|
||||
useHome(t, homeRoot);
|
||||
useWechatEnv(t, {
|
||||
WECHAT_APP_ID: undefined,
|
||||
WECHAT_APP_SECRET: "stale-secret-from-process-env",
|
||||
});
|
||||
|
||||
await writeEnvFile(cwdRoot, "WECHAT_APP_ID=cwd-app-id\nWECHAT_APP_SECRET=cwd-app-secret\n");
|
||||
await writeEnvFile(homeRoot, "WECHAT_APP_ID=home-app-id\nWECHAT_APP_SECRET=home-app-secret\n");
|
||||
|
||||
const credentials = loadCredentials();
|
||||
|
||||
assert.equal(credentials.appId, "cwd-app-id");
|
||||
assert.equal(credentials.appSecret, "cwd-app-secret");
|
||||
assert.equal(credentials.source, "<cwd>/.baoyu-skills/.env");
|
||||
assert.deepEqual(credentials.skippedSources, [
|
||||
"process.env missing WECHAT_APP_ID",
|
||||
]);
|
||||
});
|
||||
|
||||
test("loadCredentials prefers a complete process.env pair over lower-priority files", async (t) => {
|
||||
const cwdRoot = await makeTempDir("wechat-creds-cwd-");
|
||||
const homeRoot = await makeTempDir("wechat-creds-home-");
|
||||
|
||||
useCwd(t, cwdRoot);
|
||||
useHome(t, homeRoot);
|
||||
useWechatEnv(t, {
|
||||
WECHAT_APP_ID: "env-app-id",
|
||||
WECHAT_APP_SECRET: "env-app-secret",
|
||||
});
|
||||
|
||||
await writeEnvFile(cwdRoot, "WECHAT_APP_ID=cwd-app-id\nWECHAT_APP_SECRET=cwd-app-secret\n");
|
||||
await writeEnvFile(homeRoot, "WECHAT_APP_ID=home-app-id\nWECHAT_APP_SECRET=home-app-secret\n");
|
||||
|
||||
const credentials = loadCredentials();
|
||||
|
||||
assert.equal(credentials.appId, "env-app-id");
|
||||
assert.equal(credentials.appSecret, "env-app-secret");
|
||||
assert.equal(credentials.source, "process.env");
|
||||
assert.deepEqual(credentials.skippedSources, []);
|
||||
});
|
||||
|
||||
test("loadCredentials reports skipped incomplete sources when no complete pair exists", async (t) => {
|
||||
const cwdRoot = await makeTempDir("wechat-creds-cwd-");
|
||||
const homeRoot = await makeTempDir("wechat-creds-home-");
|
||||
|
||||
useCwd(t, cwdRoot);
|
||||
useHome(t, homeRoot);
|
||||
useWechatEnv(t, {
|
||||
WECHAT_APP_ID: "env-app-id",
|
||||
WECHAT_APP_SECRET: undefined,
|
||||
});
|
||||
|
||||
await writeEnvFile(cwdRoot, "WECHAT_APP_SECRET=cwd-app-secret\n");
|
||||
|
||||
assert.throws(
|
||||
() => loadCredentials(),
|
||||
/Incomplete credential sources skipped:\n- process\.env missing WECHAT_APP_SECRET\n- <cwd>\/\.baoyu-skills\/\.env missing WECHAT_APP_ID/,
|
||||
);
|
||||
});
|
||||
@@ -196,48 +196,116 @@ function aliasToEnvKey(alias: string): string {
|
||||
return alias.toUpperCase().replace(/-/g, "_");
|
||||
}
|
||||
|
||||
export function loadCredentials(account?: ResolvedAccount): { appId: string; appSecret: string } {
|
||||
if (account?.app_id && account?.app_secret) {
|
||||
return { appId: account.app_id, appSecret: account.app_secret };
|
||||
interface CredentialSource {
|
||||
name: string;
|
||||
appIdKey: string;
|
||||
appSecretKey: string;
|
||||
appId?: string;
|
||||
appSecret?: string;
|
||||
}
|
||||
|
||||
export interface LoadedCredentials {
|
||||
appId: string;
|
||||
appSecret: string;
|
||||
source: string;
|
||||
skippedSources: string[];
|
||||
}
|
||||
|
||||
function normalizeCredentialValue(value?: string): string | undefined {
|
||||
const trimmed = value?.trim();
|
||||
return trimmed ? trimmed : undefined;
|
||||
}
|
||||
|
||||
function describeMissingKeys(source: CredentialSource): string {
|
||||
const missingKeys: string[] = [];
|
||||
if (!source.appId) missingKeys.push(source.appIdKey);
|
||||
if (!source.appSecret) missingKeys.push(source.appSecretKey);
|
||||
return `${source.name} missing ${missingKeys.join(" and ")}`;
|
||||
}
|
||||
|
||||
function buildCredentialSource(
|
||||
name: string,
|
||||
values: Record<string, string | undefined>,
|
||||
appIdKey: string,
|
||||
appSecretKey: string,
|
||||
): CredentialSource {
|
||||
return {
|
||||
name,
|
||||
appIdKey,
|
||||
appSecretKey,
|
||||
appId: normalizeCredentialValue(values[appIdKey]),
|
||||
appSecret: normalizeCredentialValue(values[appSecretKey]),
|
||||
};
|
||||
}
|
||||
|
||||
function resolveCredentialSource(
|
||||
sources: CredentialSource[],
|
||||
account?: ResolvedAccount,
|
||||
): LoadedCredentials {
|
||||
const skippedSources: string[] = [];
|
||||
|
||||
for (const source of sources) {
|
||||
if (source.appId && source.appSecret) {
|
||||
return {
|
||||
appId: source.appId,
|
||||
appSecret: source.appSecret,
|
||||
source: source.name,
|
||||
skippedSources,
|
||||
};
|
||||
}
|
||||
|
||||
if (source.appId || source.appSecret) {
|
||||
skippedSources.push(describeMissingKeys(source));
|
||||
}
|
||||
}
|
||||
|
||||
const hint = account?.alias ? ` (account: ${account.alias})` : "";
|
||||
const partialHint = skippedSources.length > 0
|
||||
? `\nIncomplete credential sources skipped:\n- ${skippedSources.join("\n- ")}`
|
||||
: "";
|
||||
|
||||
throw new Error(
|
||||
`Missing WECHAT_APP_ID or WECHAT_APP_SECRET${hint}.\n` +
|
||||
"Set via EXTEND.md account config, environment variables, or .baoyu-skills/.env file." +
|
||||
partialHint
|
||||
);
|
||||
}
|
||||
|
||||
export function loadCredentials(account?: ResolvedAccount): LoadedCredentials {
|
||||
const cwdEnvPath = path.join(process.cwd(), ".baoyu-skills", ".env");
|
||||
const homeEnvPath = path.join(os.homedir(), ".baoyu-skills", ".env");
|
||||
const cwdEnv = loadEnvFile(cwdEnvPath);
|
||||
const homeEnv = loadEnvFile(homeEnvPath);
|
||||
|
||||
const sources: CredentialSource[] = [];
|
||||
|
||||
if (account?.app_id || account?.app_secret) {
|
||||
sources.push({
|
||||
name: account.alias ? `EXTEND.md account "${account.alias}"` : "EXTEND.md account config",
|
||||
appIdKey: "app_id",
|
||||
appSecretKey: "app_secret",
|
||||
appId: normalizeCredentialValue(account.app_id),
|
||||
appSecret: normalizeCredentialValue(account.app_secret),
|
||||
});
|
||||
}
|
||||
|
||||
const prefix = account?.alias ? `WECHAT_${aliasToEnvKey(account.alias)}_` : "";
|
||||
|
||||
let appId = "";
|
||||
let appSecret = "";
|
||||
|
||||
if (prefix) {
|
||||
appId = process.env[`${prefix}APP_ID`]
|
||||
|| cwdEnv[`${prefix}APP_ID`]
|
||||
|| homeEnv[`${prefix}APP_ID`]
|
||||
|| "";
|
||||
appSecret = process.env[`${prefix}APP_SECRET`]
|
||||
|| cwdEnv[`${prefix}APP_SECRET`]
|
||||
|| homeEnv[`${prefix}APP_SECRET`]
|
||||
|| "";
|
||||
}
|
||||
|
||||
if (!appId) {
|
||||
appId = process.env.WECHAT_APP_ID || cwdEnv.WECHAT_APP_ID || homeEnv.WECHAT_APP_ID || "";
|
||||
}
|
||||
if (!appSecret) {
|
||||
appSecret = process.env.WECHAT_APP_SECRET || cwdEnv.WECHAT_APP_SECRET || homeEnv.WECHAT_APP_SECRET || "";
|
||||
}
|
||||
|
||||
if (!appId || !appSecret) {
|
||||
const hint = account?.alias ? ` (account: ${account.alias})` : "";
|
||||
throw new Error(
|
||||
`Missing WECHAT_APP_ID or WECHAT_APP_SECRET${hint}.\n` +
|
||||
"Set via EXTEND.md account config, environment variables, or .baoyu-skills/.env file."
|
||||
const prefixedKeyLabel = `${prefix}APP_ID/${prefix}APP_SECRET`;
|
||||
sources.push(
|
||||
buildCredentialSource(`process.env (${prefixedKeyLabel})`, process.env, `${prefix}APP_ID`, `${prefix}APP_SECRET`),
|
||||
buildCredentialSource(`<cwd>/.baoyu-skills/.env (${prefixedKeyLabel})`, cwdEnv, `${prefix}APP_ID`, `${prefix}APP_SECRET`),
|
||||
buildCredentialSource(`~/.baoyu-skills/.env (${prefixedKeyLabel})`, homeEnv, `${prefix}APP_ID`, `${prefix}APP_SECRET`),
|
||||
);
|
||||
}
|
||||
|
||||
return { appId, appSecret };
|
||||
sources.push(
|
||||
buildCredentialSource("process.env", process.env, "WECHAT_APP_ID", "WECHAT_APP_SECRET"),
|
||||
buildCredentialSource("<cwd>/.baoyu-skills/.env", cwdEnv, "WECHAT_APP_ID", "WECHAT_APP_SECRET"),
|
||||
buildCredentialSource("~/.baoyu-skills/.env", homeEnv, "WECHAT_APP_ID", "WECHAT_APP_SECRET"),
|
||||
);
|
||||
|
||||
return resolveCredentialSource(sources, account);
|
||||
}
|
||||
|
||||
export function listAccounts(config: WechatExtendConfig): string[] {
|
||||
|
||||
@@ -123,6 +123,8 @@ ${BUN_X} {baseDir}/scripts/weibo-article.ts article.md --cover ./cover.jpg
|
||||
- Title: 32 characters max (truncated with warning if longer)
|
||||
- Summary/导语: 44 characters max (auto-regenerated from content if longer)
|
||||
|
||||
**Markdown-to-HTML**: Do NOT pass any `--theme` parameter when converting markdown to HTML. Use the default theme (no theme argument).
|
||||
|
||||
**Article Workflow**:
|
||||
1. Opens `https://card.weibo.com/article/v3/editor`
|
||||
2. Clicks "写文章" button, waits for editor to become editable
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
---
|
||||
name: baoyu-url-to-markdown
|
||||
description: Fetch any URL and convert to markdown using Chrome CDP. Saves the rendered HTML snapshot alongside the markdown, uses an upgraded Defuddle pipeline with better web-component handling and YouTube transcript extraction, and automatically falls back to the pre-Defuddle HTML-to-Markdown pipeline when needed. If local browser capture fails entirely, it can fall back to the hosted defuddle.md API. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.
|
||||
version: 1.58.1
|
||||
version: 1.59.0
|
||||
metadata:
|
||||
openclaw:
|
||||
homepage: https://github.com/JimLiu/baoyu-skills#baoyu-url-to-markdown
|
||||
@@ -30,6 +30,9 @@ Fetches any URL via Chrome CDP, saves the rendered HTML snapshot, and converts i
|
||||
|--------|---------|
|
||||
| `scripts/main.ts` | CLI entry point for URL fetching |
|
||||
| `scripts/html-to-markdown.ts` | Markdown conversion entry point and converter selection |
|
||||
| `scripts/parsers/index.ts` | Unified parser entry: dispatches URL-specific rules before generic converters |
|
||||
| `scripts/parsers/types.ts` | Unified parser interface shared by all rule files |
|
||||
| `scripts/parsers/rules/*.ts` | One file per URL rule, for example X status and X article |
|
||||
| `scripts/defuddle-converter.ts` | Defuddle-based conversion |
|
||||
| `scripts/legacy-converter.ts` | Pre-Defuddle legacy extraction and markdown conversion |
|
||||
| `scripts/markdown-conversion-shared.ts` | Shared metadata parsing and markdown document helpers |
|
||||
@@ -115,10 +118,13 @@ Full reference: [references/config/first-time-setup.md](references/config/first-
|
||||
## Features
|
||||
|
||||
- Chrome CDP for full JavaScript rendering
|
||||
- URL-specific parser layer for sites that need custom HTML rules before generic extraction
|
||||
- Two capture modes: auto or wait-for-user
|
||||
- Save rendered HTML as a sibling `-captured.html` file
|
||||
- Clean markdown output with metadata
|
||||
- Upgraded Defuddle-first markdown conversion with automatic fallback to the pre-Defuddle extractor from git history
|
||||
- X/Twitter pages can use HTML-specific parsing for Tweets and Articles, which improves title/body/media extraction on `x.com` / `twitter.com`
|
||||
- `archive.ph` / related archive mirrors can restore the original URL from `input[name=q]` and prefer `#CONTENT` before falling back to the page body
|
||||
- Materializes shadow DOM content before conversion so web-component pages survive serialization better
|
||||
- YouTube pages can include transcript/caption text in the markdown when YouTube exposes a caption track
|
||||
- If local browser capture fails completely, can fall back to `defuddle.md/<url>` and still save markdown
|
||||
@@ -201,14 +207,16 @@ When `--download-media` is enabled:
|
||||
|
||||
Conversion order:
|
||||
|
||||
1. Try Defuddle first
|
||||
2. For rich pages such as YouTube, prefer Defuddle's extractor-specific output (including transcripts when available) instead of replacing it with the legacy pipeline
|
||||
3. If Defuddle throws, cannot load, returns obviously incomplete markdown, or captures lower-quality content than the legacy pipeline, automatically fall back to the pre-Defuddle extractor
|
||||
4. If the entire local browser capture flow fails before markdown can be produced, try the hosted `https://defuddle.md/<url>` API and save its markdown output directly
|
||||
5. The legacy fallback path uses the older Readability/selector/Next.js-data based HTML-to-Markdown implementation recovered from git history
|
||||
1. Try the URL-specific parser layer first when a site rule matches
|
||||
2. If no specialized parser matches, try Defuddle
|
||||
3. For rich pages such as YouTube, prefer Defuddle's extractor-specific output (including transcripts when available) instead of replacing it with the legacy pipeline
|
||||
4. If Defuddle throws, cannot load, returns obviously incomplete markdown, or captures lower-quality content than the legacy pipeline, automatically fall back to the pre-Defuddle extractor
|
||||
5. If the entire local browser capture flow fails before markdown can be produced, try the hosted `https://defuddle.md/<url>` API and save its markdown output directly
|
||||
6. The legacy fallback path uses the older Readability/selector/Next.js-data based HTML-to-Markdown implementation recovered from git history
|
||||
|
||||
CLI output will show:
|
||||
|
||||
- `Converter: parser:...` when a URL-specific parser succeeded
|
||||
- `Converter: defuddle` when Defuddle succeeds
|
||||
- `Converter: legacy:...` plus `Fallback used: ...` when fallback was needed
|
||||
- `Converter: defuddle-api` when local browser capture failed and the hosted API was used instead
|
||||
|
||||
@@ -12,6 +12,7 @@ import {
|
||||
scoreMarkdownQuality,
|
||||
shouldCompareWithLegacy,
|
||||
} from "./legacy-converter.js";
|
||||
import { tryUrlRuleParsers } from "./parsers/index.js";
|
||||
|
||||
export type { ConversionResult, PageMetadata };
|
||||
export { createMarkdownDocument, formatMetadataYaml };
|
||||
@@ -105,6 +106,11 @@ export async function extractContent(html: string, url: string): Promise<Convers
|
||||
const capturedAt = new Date().toISOString();
|
||||
const baseMetadata = extractMetadataFromHtml(html, url, capturedAt);
|
||||
|
||||
const specializedResult = tryUrlRuleParsers(html, url, baseMetadata);
|
||||
if (specializedResult) {
|
||||
return specializedResult;
|
||||
}
|
||||
|
||||
const defuddleResult = await tryDefuddleConversion(html, url, baseMetadata);
|
||||
if (defuddleResult.ok) {
|
||||
if (shouldPreferDefuddle(defuddleResult.result)) {
|
||||
|
||||
@@ -521,14 +521,18 @@ turndown.addRule("collapseFigure", {
|
||||
|
||||
turndown.addRule("dropInvisibleAnchors", {
|
||||
filter(node) {
|
||||
return node.nodeName === "A" && !(node as Element).textContent?.trim();
|
||||
return (
|
||||
node.nodeName === "A" &&
|
||||
!(node as Element).textContent?.trim() &&
|
||||
!(node as Element).querySelector("img, video, picture, source")
|
||||
);
|
||||
},
|
||||
replacement() {
|
||||
return "";
|
||||
},
|
||||
});
|
||||
|
||||
function convertHtmlToMarkdown(html: string): string {
|
||||
export function convertHtmlFragmentToMarkdown(html: string): string {
|
||||
if (!html || !html.trim()) return "";
|
||||
|
||||
try {
|
||||
@@ -609,7 +613,7 @@ export function shouldCompareWithLegacy(markdown: string): boolean {
|
||||
export function convertWithLegacyExtractor(html: string, baseMetadata: PageMetadata): ConversionResult {
|
||||
const extracted = extractFromHtml(html);
|
||||
|
||||
let markdown = extracted?.html ? convertHtmlToMarkdown(extracted.html) : "";
|
||||
let markdown = extracted?.html ? convertHtmlFragmentToMarkdown(extracted.html) : "";
|
||||
if (!markdown.trim()) {
|
||||
markdown = extracted?.textContent?.trim() || fallbackPlainText(html);
|
||||
}
|
||||
|
||||
@@ -52,15 +52,71 @@ function parseArgs(argv: string[]): Args {
|
||||
return args;
|
||||
}
|
||||
|
||||
function generateSlug(title: string, url: string): string {
|
||||
const text = title || new URL(url).pathname.replace(/\//g, "-");
|
||||
return text
|
||||
const SLUG_STOP_WORDS = new Set([
|
||||
"the", "a", "an", "is", "are", "was", "were", "be", "been", "being",
|
||||
"have", "has", "had", "do", "does", "did", "will", "would", "shall",
|
||||
"should", "may", "might", "must", "can", "could", "to", "of", "in",
|
||||
"for", "on", "with", "at", "by", "from", "as", "into", "through",
|
||||
"during", "before", "after", "above", "below", "between", "out",
|
||||
"off", "over", "under", "again", "further", "then", "once", "here",
|
||||
"there", "when", "where", "why", "how", "all", "both", "each",
|
||||
"few", "more", "most", "other", "some", "such", "no", "nor", "not",
|
||||
"only", "own", "same", "so", "than", "too", "very", "just", "but",
|
||||
"and", "or", "if", "this", "that", "these", "those", "it", "its",
|
||||
"http", "https", "www", "com", "org", "net", "post", "article",
|
||||
]);
|
||||
|
||||
function extractSlugFromContent(content: string): string | null {
|
||||
const body = content.replace(/^---\n[\s\S]*?\n---\n?/, "").slice(0, 1000);
|
||||
const words = body
|
||||
.replace(/[^\w\s-]/g, " ")
|
||||
.split(/\s+/)
|
||||
.filter((w) => /^[a-zA-Z]/.test(w) && w.length >= 2 && !SLUG_STOP_WORDS.has(w.toLowerCase()))
|
||||
.map((w) => w.toLowerCase());
|
||||
|
||||
const unique: string[] = [];
|
||||
const seen = new Set<string>();
|
||||
for (const w of words) {
|
||||
if (!seen.has(w)) {
|
||||
seen.add(w);
|
||||
unique.push(w);
|
||||
if (unique.length >= 6) break;
|
||||
}
|
||||
}
|
||||
return unique.length >= 2 ? unique.join("-").slice(0, 50) : null;
|
||||
}
|
||||
|
||||
function generateSlug(title: string, url: string, content?: string): string {
|
||||
const asciiWords = title
|
||||
.replace(/[^\w\s]/g, " ")
|
||||
.split(/\s+/)
|
||||
.filter((w) => /[a-zA-Z]/.test(w) && w.length >= 2 && !SLUG_STOP_WORDS.has(w.toLowerCase()))
|
||||
.map((w) => w.toLowerCase());
|
||||
|
||||
if (asciiWords.length >= 2) {
|
||||
return asciiWords.slice(0, 6).join("-").slice(0, 50);
|
||||
}
|
||||
|
||||
if (content) {
|
||||
const contentSlug = extractSlugFromContent(content);
|
||||
if (contentSlug) return contentSlug;
|
||||
}
|
||||
|
||||
const GENERIC_PATH_SEGMENTS = new Set(["status", "article", "post", "posts", "p", "blog", "news", "articles"]);
|
||||
const parsed = new URL(url);
|
||||
const pathSlug = parsed.pathname
|
||||
.split("/")
|
||||
.filter((s) => s.length > 0 && !/^\d{10,}$/.test(s) && !GENERIC_PATH_SEGMENTS.has(s.toLowerCase()))
|
||||
.join("-")
|
||||
.toLowerCase()
|
||||
.replace(/[^\w\s-]/g, "")
|
||||
.replace(/\s+/g, "-")
|
||||
.replace(/[^\w-]/g, "-")
|
||||
.replace(/-+/g, "-")
|
||||
.replace(/^-|-$/g, "")
|
||||
.slice(0, 50) || "page";
|
||||
.slice(0, 40);
|
||||
|
||||
const prefix = asciiWords.slice(0, 2).join("-");
|
||||
const combined = prefix ? `${prefix}-${pathSlug}` : pathSlug;
|
||||
return combined.slice(0, 50) || "page";
|
||||
}
|
||||
|
||||
function formatTimestamp(): string {
|
||||
@@ -124,18 +180,18 @@ async function fetchDefuddleApiMarkdown(targetUrl: string): Promise<{ markdown:
|
||||
};
|
||||
}
|
||||
|
||||
async function generateOutputPath(url: string, title: string, outputDir?: string): Promise<string> {
|
||||
async function generateOutputPath(url: string, title: string, outputDir?: string, content?: string): Promise<string> {
|
||||
const domain = new URL(url).hostname.replace(/^www\./, "");
|
||||
const slug = generateSlug(title, url);
|
||||
const slug = generateSlug(title, url, content);
|
||||
const dataDir = outputDir ? path.resolve(outputDir) : resolveUrlToMarkdownDataDir();
|
||||
const basePath = path.join(dataDir, domain, `${slug}.md`);
|
||||
const basePath = path.join(dataDir, domain, slug, `${slug}.md`);
|
||||
|
||||
if (!(await fileExists(basePath))) {
|
||||
return basePath;
|
||||
}
|
||||
|
||||
const timestampSlug = `${slug}-${formatTimestamp()}`;
|
||||
return path.join(dataDir, domain, `${timestampSlug}.md`);
|
||||
return path.join(dataDir, domain, timestampSlug, `${timestampSlug}.md`);
|
||||
}
|
||||
|
||||
async function waitForUserSignal(): Promise<void> {
|
||||
@@ -249,13 +305,12 @@ async function main(): Promise<void> {
|
||||
|
||||
try {
|
||||
const result = await captureUrl(args);
|
||||
outputPath = args.output || await generateOutputPath(args.url, result.metadata.title, args.outputDir);
|
||||
document = createMarkdownDocument(result);
|
||||
outputPath = args.output || await generateOutputPath(args.url, result.metadata.title, args.outputDir, document);
|
||||
const outputDir = path.dirname(outputPath);
|
||||
htmlSnapshotPath = deriveHtmlSnapshotPath(outputPath);
|
||||
await mkdir(outputDir, { recursive: true });
|
||||
await writeFile(htmlSnapshotPath, result.rawHtml, "utf-8");
|
||||
|
||||
document = createMarkdownDocument(result);
|
||||
conversionMethod = result.conversionMethod;
|
||||
fallbackReason = result.fallbackReason;
|
||||
} catch (error) {
|
||||
@@ -265,10 +320,9 @@ async function main(): Promise<void> {
|
||||
|
||||
try {
|
||||
const remoteResult = await fetchDefuddleApiMarkdown(args.url);
|
||||
outputPath = args.output || await generateOutputPath(args.url, remoteResult.title, args.outputDir);
|
||||
await mkdir(path.dirname(outputPath), { recursive: true });
|
||||
|
||||
document = remoteResult.markdown;
|
||||
outputPath = args.output || await generateOutputPath(args.url, remoteResult.title, args.outputDir, document);
|
||||
await mkdir(path.dirname(outputPath), { recursive: true });
|
||||
conversionMethod = "defuddle-api";
|
||||
fallbackReason = `Local browser capture failed: ${primaryError}`;
|
||||
} catch (remoteError) {
|
||||
|
||||
@@ -300,6 +300,24 @@ export function createMarkdownDocument(result: ConversionResult): string {
|
||||
const escapedTitle = result.metadata.title.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
|
||||
const titleRegex = new RegExp(`^#\\s+${escapedTitle}\\s*(\\n|$)`, "i");
|
||||
const hasTitle = titleRegex.test(result.markdown.trimStart());
|
||||
const title = result.metadata.title && !hasTitle ? `\n\n# ${result.metadata.title}\n\n` : "\n\n";
|
||||
const firstMeaningfulLine = result.markdown
|
||||
.replace(/\r\n/g, "\n")
|
||||
.split("\n")
|
||||
.map((line) => line.trim())
|
||||
.find((line) => line && !/^!?\[[^\]]*\]\([^)]+\)$/.test(line))
|
||||
?.replace(/^>\s*/, "")
|
||||
?.replace(/^#+\s+/, "")
|
||||
?.trim();
|
||||
const comparableTitle = result.metadata.title.toLowerCase().replace(/(?:\.{3}|…)\s*$/, "");
|
||||
const comparableFirstLine = firstMeaningfulLine?.toLowerCase() ?? "";
|
||||
const titleRepeatsContent =
|
||||
comparableTitle !== "" &&
|
||||
comparableFirstLine !== "" &&
|
||||
(comparableFirstLine === comparableTitle ||
|
||||
comparableFirstLine.startsWith(comparableTitle) ||
|
||||
comparableTitle.startsWith(comparableFirstLine));
|
||||
const title = result.metadata.title && !hasTitle && !titleRepeatsContent
|
||||
? `\n\n# ${result.metadata.title}\n\n`
|
||||
: "\n\n";
|
||||
return yaml + title + result.markdown;
|
||||
}
|
||||
|
||||
@@ -0,0 +1,206 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
|
||||
import {
|
||||
createMarkdownDocument,
|
||||
extractMetadataFromHtml,
|
||||
} from "../markdown-conversion-shared.js";
|
||||
import { tryUrlRuleParsers } from "./index.js";
|
||||
|
||||
const CAPTURED_AT = "2026-03-22T06:00:00.000Z";
|
||||
|
||||
const ARTICLE_HTML = `<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<body>
|
||||
<div data-testid="twitterArticleReadView">
|
||||
<a href="/dotey/article/2035141635713941927/media/1">
|
||||
<div data-testid="tweetPhoto">
|
||||
<img src="https://pbs.twimg.com/media/article-cover.jpg" alt="Image">
|
||||
</div>
|
||||
</a>
|
||||
<div data-testid="twitter-article-title">Karpathy："写代码"已经不是对的动词了</div>
|
||||
<div data-testid="User-Name">
|
||||
<a href="/dotey">宝玉 Verified account</a>
|
||||
<a href="/dotey">@dotey</a>
|
||||
<time datetime="2026-03-20T23:49:11.000Z">Mar 20</time>
|
||||
</div>
|
||||
<div data-testid="twitterArticleRichTextView">
|
||||
<p>Andrej Karpathy 说他从 2024 年 12 月起就基本没手写过一行代码。</p>
|
||||
<a href="/dotey/article/2035141635713941927/media/2">
|
||||
<div>
|
||||
<div>
|
||||
<div data-testid="tweetPhoto">
|
||||
<img src="https://pbs.twimg.com/media/article-inline.jpg" alt="Image">
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</a>
|
||||
<h2>要点速览</h2>
|
||||
<ul>
|
||||
<li>核心焦虑从 GPU 利用率转向 Token 吞吐量</li>
|
||||
</ul>
|
||||
<blockquote>
|
||||
<p>写代码已经不是对的动词了。</p>
|
||||
</blockquote>
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
</html>`;
|
||||
|
||||
const STATUS_HTML = `<!doctype html>
|
||||
<html lang="en">
|
||||
<body>
|
||||
<article data-testid="tweet">
|
||||
<div data-testid="User-Name">
|
||||
<a href="/dotey">宝玉 Verified account</a>
|
||||
<a href="/dotey">@dotey</a>
|
||||
<time datetime="2026-03-22T05:33:00.000Z">Mar 22</time>
|
||||
</div>
|
||||
<div data-testid="tweetText">
|
||||
<span>转译：把下面这段加到你的 Codex 自定义指令里，体验会好太多：</span>
|
||||
</div>
|
||||
<div data-testid="tweetPhoto">
|
||||
<img src="https://pbs.twimg.com/media/tweet-main.jpg" alt="Image">
|
||||
</div>
|
||||
<div data-testid="User-Name">
|
||||
<a href="/mattshumer_">Matt Shumer Verified account</a>
|
||||
<a href="/mattshumer_">@mattshumer_</a>
|
||||
<time datetime="2026-03-17T00:00:00.000Z">Mar 17</time>
|
||||
</div>
|
||||
<div data-testid="tweetText">
|
||||
<span>Add this to your Codex custom instructions for a way better experience.</span>
|
||||
</div>
|
||||
</article>
|
||||
</body>
|
||||
</html>`;
|
||||
|
||||
const ARCHIVE_HTML = `<!doctype html>
|
||||
<html>
|
||||
<head>
|
||||
<title>archive.ph</title>
|
||||
</head>
|
||||
<body>
|
||||
<form>
|
||||
<input
|
||||
type="text"
|
||||
name="q"
|
||||
value="https://www.newscientist.com/article/2520204-major-leap-towards-reanimation-after-death-as-mammals-brain-preserved/"
|
||||
>
|
||||
</form>
|
||||
<div id="HEADER">
|
||||
Archive shell text that should be ignored when CONTENT exists.
|
||||
</div>
|
||||
<div id="CONTENT">
|
||||
<h1>Major leap towards reanimation after death as mammal brain preserved</h1>
|
||||
<p>
|
||||
Researchers say the preserved structure and activity markers suggest a significant step
|
||||
forward in keeping delicate brain tissue viable after clinical death.
|
||||
</p>
|
||||
<p>
|
||||
The archive wrapper should not take precedence over the actual article body when the
|
||||
CONTENT container is available for parsing.
|
||||
</p>
|
||||
<img src="https://cdn.example.com/brain.jpg" alt="Brain tissue">
|
||||
</div>
|
||||
</body>
|
||||
</html>`;
|
||||
|
||||
const ARCHIVE_FALLBACK_HTML = `<!doctype html>
|
||||
<html>
|
||||
<head>
|
||||
<title>archive.ph</title>
|
||||
</head>
|
||||
<body>
|
||||
<input type="text" name="q" value="https://example.com/fallback-story">
|
||||
<main>
|
||||
<h1>Fallback body parsing still works</h1>
|
||||
<p>
|
||||
When CONTENT is absent, the parser should fall back to the body content instead of
|
||||
returning null or keeping the archive wrapper as the final URL.
|
||||
</p>
|
||||
<p>
|
||||
This ensures archived pages with slightly different layouts still produce usable markdown.
|
||||
</p>
|
||||
</main>
|
||||
</body>
|
||||
</html>`;
|
||||
|
||||
function parse(html: string, url: string) {
|
||||
const baseMetadata = extractMetadataFromHtml(html, url, CAPTURED_AT);
|
||||
return tryUrlRuleParsers(html, url, baseMetadata);
|
||||
}
|
||||
|
||||
test("parses archive.ph pages from CONTENT and restores the original URL", () => {
|
||||
const result = parse(ARCHIVE_HTML, "https://archive.ph/SMcX5");
|
||||
|
||||
assert.ok(result);
|
||||
assert.equal(result.conversionMethod, "parser:archive-ph");
|
||||
assert.equal(
|
||||
result.metadata.url,
|
||||
"https://www.newscientist.com/article/2520204-major-leap-towards-reanimation-after-death-as-mammals-brain-preserved/"
|
||||
);
|
||||
assert.equal(
|
||||
result.metadata.title,
|
||||
"Major leap towards reanimation after death as mammal brain preserved"
|
||||
);
|
||||
assert.equal(result.metadata.coverImage, "https://cdn.example.com/brain.jpg");
|
||||
assert.ok(result.markdown.includes("Researchers say the preserved structure"));
|
||||
assert.ok(result.markdown.includes(""));
|
||||
assert.ok(!result.markdown.includes("Archive shell text that should be ignored"));
|
||||
});
|
||||
|
||||
test("falls back to body when archive.ph CONTENT is missing", () => {
|
||||
const result = parse(ARCHIVE_FALLBACK_HTML, "https://archive.ph/fallback");
|
||||
|
||||
assert.ok(result);
|
||||
assert.equal(result.conversionMethod, "parser:archive-ph");
|
||||
assert.equal(result.metadata.url, "https://example.com/fallback-story");
|
||||
assert.equal(result.metadata.title, "Fallback body parsing still works");
|
||||
assert.ok(result.markdown.includes("When CONTENT is absent"));
|
||||
});
|
||||
|
||||
test("parses X article pages from HTML", () => {
|
||||
const result = parse(
|
||||
ARTICLE_HTML,
|
||||
"https://x.com/dotey/article/2035141635713941927"
|
||||
);
|
||||
|
||||
assert.ok(result);
|
||||
assert.equal(result.conversionMethod, "parser:x-article");
|
||||
assert.equal(result.metadata.title, "Karpathy：\"写代码\"已经不是对的动词了");
|
||||
assert.equal(result.metadata.author, "宝玉 (@dotey)");
|
||||
assert.equal(result.metadata.coverImage, "https://pbs.twimg.com/media/article-cover.jpg");
|
||||
assert.equal(result.metadata.published, "2026-03-20T23:49:11.000Z");
|
||||
assert.equal(result.metadata.language, "zh");
|
||||
assert.ok(result.markdown.includes("## 要点速览"));
|
||||
assert.ok(
|
||||
result.markdown.includes(
|
||||
"[](/dotey/article/2035141635713941927/media/2)"
|
||||
)
|
||||
);
|
||||
assert.ok(result.markdown.includes("写代码已经不是对的动词了。"));
|
||||
|
||||
const document = createMarkdownDocument(result);
|
||||
assert.ok(document.includes("# Karpathy：\"写代码\"已经不是对的动词了"));
|
||||
});
|
||||
|
||||
test("parses X status pages from HTML without duplicating the title heading", () => {
|
||||
const result = parse(
|
||||
STATUS_HTML,
|
||||
"https://x.com/dotey/status/2035590649081196710"
|
||||
);
|
||||
|
||||
assert.ok(result);
|
||||
assert.equal(result.conversionMethod, "parser:x-status");
|
||||
assert.equal(result.metadata.author, "宝玉 (@dotey)");
|
||||
assert.equal(result.metadata.coverImage, "https://pbs.twimg.com/media/tweet-main.jpg");
|
||||
assert.equal(result.metadata.language, "zh");
|
||||
assert.ok(result.markdown.includes("转译：把下面这段加到你的 Codex 自定义指令里"));
|
||||
assert.ok(result.markdown.includes("> Quote from Matt Shumer (@mattshumer_)"));
|
||||
assert.ok(result.markdown.includes("!["));
|
||||
|
||||
const document = createMarkdownDocument(result);
|
||||
assert.ok(
|
||||
!document.includes("\n\n# 转译：把下面这段加到你的 Codex 自定义指令里，体验会好太多：\n\n")
|
||||
);
|
||||
});
|
||||
@@ -0,0 +1,47 @@
|
||||
import {
|
||||
isMarkdownUsable,
|
||||
normalizeMarkdown,
|
||||
parseDocument,
|
||||
type ConversionResult,
|
||||
type PageMetadata,
|
||||
} from "../markdown-conversion-shared.js";
|
||||
import { URL_RULE_PARSERS } from "./rules/index.js";
|
||||
import type { UrlRuleParserContext } from "./types.js";
|
||||
|
||||
export type { UrlRuleParser, UrlRuleParserContext } from "./types.js";
|
||||
|
||||
export function tryUrlRuleParsers(
|
||||
html: string,
|
||||
url: string,
|
||||
baseMetadata: PageMetadata
|
||||
): ConversionResult | null {
|
||||
const document = parseDocument(html);
|
||||
const context: UrlRuleParserContext = {
|
||||
html,
|
||||
url,
|
||||
document,
|
||||
baseMetadata,
|
||||
};
|
||||
|
||||
for (const parser of URL_RULE_PARSERS) {
|
||||
if (!parser.supports(context)) continue;
|
||||
|
||||
try {
|
||||
const result = parser.parse(context);
|
||||
if (!result) continue;
|
||||
|
||||
const markdown = normalizeMarkdown(result.markdown);
|
||||
if (!isMarkdownUsable(markdown, html)) continue;
|
||||
|
||||
return {
|
||||
...result,
|
||||
markdown,
|
||||
};
|
||||
} catch (error) {
|
||||
const message = error instanceof Error ? error.message : String(error);
|
||||
console.warn(`[url-to-markdown] parser ${parser.id} failed: ${message}`);
|
||||
}
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
@@ -0,0 +1,97 @@
|
||||
import { convertHtmlFragmentToMarkdown } from "../../legacy-converter.js";
|
||||
import {
|
||||
normalizeMarkdown,
|
||||
pickString,
|
||||
type ConversionResult,
|
||||
} from "../../markdown-conversion-shared.js";
|
||||
import type { UrlRuleParser, UrlRuleParserContext } from "../types.js";
|
||||
|
||||
const ARCHIVE_HOSTS = new Set([
|
||||
"archive.ph",
|
||||
"archive.is",
|
||||
"archive.today",
|
||||
"archive.md",
|
||||
"archive.vn",
|
||||
"archive.li",
|
||||
"archive.fo",
|
||||
]);
|
||||
|
||||
function isArchiveHost(url: string): boolean {
|
||||
try {
|
||||
return ARCHIVE_HOSTS.has(new URL(url).hostname.toLowerCase());
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
function readOriginalUrl(document: Document): string | undefined {
|
||||
const value = document.querySelector("input[name='q']")?.getAttribute("value")?.trim();
|
||||
if (!value) return undefined;
|
||||
|
||||
try {
|
||||
return new URL(value).href;
|
||||
} catch {
|
||||
return undefined;
|
||||
}
|
||||
}
|
||||
|
||||
function summarize(text: string, maxLength: number): string | undefined {
|
||||
const normalized = text.replace(/\s+/g, " ").trim();
|
||||
if (!normalized) return undefined;
|
||||
if (normalized.length <= maxLength) return normalized;
|
||||
return `${normalized.slice(0, Math.max(0, maxLength - 1)).trimEnd()}…`;
|
||||
}
|
||||
|
||||
function pickContentRoot(document: Document): Element | null {
|
||||
return (
|
||||
document.querySelector("#CONTENT") ??
|
||||
document.querySelector("#content") ??
|
||||
document.body
|
||||
);
|
||||
}
|
||||
|
||||
function pickContentTitle(root: Element, fallbackTitle: string): string {
|
||||
const contentTitle = pickString(
|
||||
root.querySelector("h1")?.textContent,
|
||||
root.querySelector("[itemprop='headline']")?.textContent,
|
||||
root.querySelector("article h2")?.textContent
|
||||
);
|
||||
if (contentTitle) return contentTitle;
|
||||
if (fallbackTitle && !/^archive\./i.test(fallbackTitle.trim())) return fallbackTitle;
|
||||
return "";
|
||||
}
|
||||
|
||||
function parseArchivePage(context: UrlRuleParserContext): ConversionResult | null {
|
||||
const root = pickContentRoot(context.document);
|
||||
if (!root) return null;
|
||||
|
||||
const markdown = normalizeMarkdown(convertHtmlFragmentToMarkdown(root.innerHTML));
|
||||
if (!markdown) return null;
|
||||
|
||||
const originalUrl = readOriginalUrl(context.document) ?? context.baseMetadata.url;
|
||||
const bodyText = root.textContent?.replace(/\s+/g, " ").trim() ?? "";
|
||||
const published = root.querySelector("time[datetime]")?.getAttribute("datetime") ?? undefined;
|
||||
const coverImage = root.querySelector("img[src]")?.getAttribute("src") ?? undefined;
|
||||
|
||||
return {
|
||||
metadata: {
|
||||
...context.baseMetadata,
|
||||
url: originalUrl,
|
||||
title: pickContentTitle(root, context.baseMetadata.title),
|
||||
description: summarize(bodyText, 220) ?? context.baseMetadata.description,
|
||||
published: pickString(published, context.baseMetadata.published) ?? undefined,
|
||||
coverImage: pickString(coverImage, context.baseMetadata.coverImage) ?? undefined,
|
||||
},
|
||||
markdown,
|
||||
rawHtml: context.html,
|
||||
conversionMethod: "parser:archive-ph",
|
||||
};
|
||||
}
|
||||
|
||||
export const archivePhRuleParser: UrlRuleParser = {
|
||||
id: "archive-ph",
|
||||
supports(context) {
|
||||
return isArchiveHost(context.url);
|
||||
},
|
||||
parse: parseArchivePage,
|
||||
};
|
||||
@@ -0,0 +1,10 @@
|
||||
import { archivePhRuleParser } from "./archive-ph.js";
|
||||
import { xArticleRuleParser } from "./x-article.js";
|
||||
import { xStatusRuleParser } from "./x-status.js";
|
||||
import type { UrlRuleParser } from "../types.js";
|
||||
|
||||
export const URL_RULE_PARSERS: UrlRuleParser[] = [
|
||||
archivePhRuleParser,
|
||||
xArticleRuleParser,
|
||||
xStatusRuleParser,
|
||||
];
|
||||
@@ -0,0 +1,137 @@
|
||||
import {
|
||||
normalizeMarkdown,
|
||||
pickString,
|
||||
type ConversionResult,
|
||||
} from "../../markdown-conversion-shared.js";
|
||||
import type { UrlRuleParser, UrlRuleParserContext } from "../types.js";
|
||||
import {
|
||||
cleanText,
|
||||
collectMediaMarkdown,
|
||||
convertXRichTextElementToMarkdown,
|
||||
extractPublishedForCurrentUrl,
|
||||
inferLanguage,
|
||||
isXArticlePath,
|
||||
isXHost,
|
||||
normalizeXMarkdown,
|
||||
parseUrl,
|
||||
pickFirstValidLinkText,
|
||||
sanitizeCoverImage,
|
||||
summarizeText,
|
||||
} from "./x-shared.js";
|
||||
|
||||
function collectArticleMarkdown(root: Element): { markdown: string; mediaUrls: string[] } {
|
||||
const parts: string[] = [];
|
||||
const seenMedia = new Set<string>();
|
||||
const mediaUrls: string[] = [];
|
||||
|
||||
function pushPart(value: string): void {
|
||||
const normalized = normalizeMarkdown(value);
|
||||
if (!normalized) return;
|
||||
parts.push(normalized);
|
||||
}
|
||||
|
||||
function walk(node: Element): void {
|
||||
const testId = node.getAttribute("data-testid");
|
||||
|
||||
if (testId === "twitterArticleRichTextView" || testId === "longformRichTextComponent") {
|
||||
const bodyMedia = collectMediaMarkdown(node, seenMedia);
|
||||
mediaUrls.push(...bodyMedia.urls.filter((url) => !mediaUrls.includes(url)));
|
||||
pushPart(convertXRichTextElementToMarkdown(node));
|
||||
return;
|
||||
}
|
||||
|
||||
if (testId === "tweetPhoto") {
|
||||
const media = collectMediaMarkdown(node, seenMedia);
|
||||
mediaUrls.push(...media.urls.filter((url) => !mediaUrls.includes(url)));
|
||||
for (const line of media.lines) pushPart(line);
|
||||
return;
|
||||
}
|
||||
|
||||
if (
|
||||
testId === "twitter-article-title" ||
|
||||
testId === "User-Name" ||
|
||||
testId === "Tweet-User-Avatar" ||
|
||||
testId === "reply" ||
|
||||
testId === "retweet" ||
|
||||
testId === "like" ||
|
||||
testId === "bookmark" ||
|
||||
testId === "caret" ||
|
||||
testId === "app-text-transition-container"
|
||||
) {
|
||||
return;
|
||||
}
|
||||
|
||||
if (node.tagName === "TIME" || node.tagName === "BUTTON") {
|
||||
return;
|
||||
}
|
||||
|
||||
for (const child of Array.from(node.children)) {
|
||||
walk(child);
|
||||
}
|
||||
}
|
||||
|
||||
for (const child of Array.from(root.children)) {
|
||||
walk(child);
|
||||
}
|
||||
|
||||
return {
|
||||
markdown: normalizeXMarkdown(parts.join("\n\n")),
|
||||
mediaUrls,
|
||||
};
|
||||
}
|
||||
|
||||
function parseXArticle(context: UrlRuleParserContext): ConversionResult | null {
|
||||
const articleRoot = context.document.querySelector("[data-testid='twitterArticleReadView']") as Element | null;
|
||||
if (!articleRoot) return null;
|
||||
|
||||
const title = cleanText(
|
||||
context.document.querySelector("[data-testid='twitter-article-title']")?.textContent
|
||||
);
|
||||
const identity = pickFirstValidLinkText(
|
||||
context.document.querySelector("[data-testid='User-Name']")
|
||||
);
|
||||
const published = extractPublishedForCurrentUrl(articleRoot, context.url);
|
||||
const { markdown, mediaUrls } = collectArticleMarkdown(articleRoot);
|
||||
if (!markdown) return null;
|
||||
|
||||
const bodyText = cleanText(
|
||||
context.document.querySelector("[data-testid='twitterArticleRichTextView']")?.textContent ??
|
||||
context.document.querySelector("[data-testid='longformRichTextComponent']")?.textContent
|
||||
);
|
||||
|
||||
return {
|
||||
metadata: {
|
||||
...context.baseMetadata,
|
||||
title: pickString(title, context.baseMetadata.title) ?? "",
|
||||
description: summarizeText(bodyText, 220) ?? context.baseMetadata.description,
|
||||
author: pickString(identity.author, context.baseMetadata.author) ?? undefined,
|
||||
published: pickString(published, context.baseMetadata.published) ?? undefined,
|
||||
coverImage: sanitizeCoverImage(mediaUrls[0], context.baseMetadata.coverImage),
|
||||
language: inferLanguage(bodyText, context.baseMetadata.language),
|
||||
},
|
||||
markdown,
|
||||
rawHtml: context.html,
|
||||
conversionMethod: "parser:x-article",
|
||||
};
|
||||
}
|
||||
|
||||
export const xArticleRuleParser: UrlRuleParser = {
|
||||
id: "x-article",
|
||||
supports(context) {
|
||||
const parsed = parseUrl(context.url);
|
||||
if (!parsed || !isXHost(parsed.hostname)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return (
|
||||
isXArticlePath(parsed.pathname) ||
|
||||
Boolean(
|
||||
context.document.querySelector("[data-testid='twitterArticleReadView']") ||
|
||||
context.document.querySelector("[data-testid='twitterArticleRichTextView']")
|
||||
)
|
||||
);
|
||||
},
|
||||
parse(context) {
|
||||
return parseXArticle(context);
|
||||
},
|
||||
};
|
||||
@@ -0,0 +1,249 @@
|
||||
import { convertHtmlFragmentToMarkdown } from "../../legacy-converter.js";
|
||||
import { normalizeMarkdown } from "../../markdown-conversion-shared.js";
|
||||
|
||||
export const DEFAULT_X_OG_IMAGE = "https://abs.twimg.com/rweb/ssr/default/v2/og/image.png";
|
||||
|
||||
export type MediaResult = {
|
||||
lines: string[];
|
||||
urls: string[];
|
||||
};
|
||||
|
||||
export function isXHost(hostname: string): boolean {
|
||||
const normalized = hostname.toLowerCase();
|
||||
return (
|
||||
normalized === "x.com" ||
|
||||
normalized === "twitter.com" ||
|
||||
normalized.endsWith(".x.com") ||
|
||||
normalized.endsWith(".twitter.com")
|
||||
);
|
||||
}
|
||||
|
||||
export function parseUrl(input: string): URL | null {
|
||||
try {
|
||||
return new URL(input);
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
export function isXStatusPath(pathname: string): boolean {
|
||||
return /^\/[^/]+\/status(?:es)?\/\d+$/i.test(pathname) || /^\/i\/web\/status\/\d+$/i.test(pathname);
|
||||
}
|
||||
|
||||
export function isXArticlePath(pathname: string): boolean {
|
||||
return /^\/[^/]+\/article\/\d+$/i.test(pathname) || /^\/(?:i\/)?article\/\d+$/i.test(pathname);
|
||||
}
|
||||
|
||||
export function cleanText(value: string | null | undefined): string {
|
||||
return (value ?? "").replace(/\s+/g, " ").trim();
|
||||
}
|
||||
|
||||
export function cleanUserLabel(value: string | null | undefined): string {
|
||||
return cleanText(value).replace(/\bVerified account\b/gi, "").replace(/\s{2,}/g, " ").trim();
|
||||
}
|
||||
|
||||
export function escapeMarkdownAlt(text: string): string {
|
||||
return text.replace(/[\[\]]/g, "\\$&");
|
||||
}
|
||||
|
||||
export function normalizeAlt(text: string | null | undefined): string {
|
||||
const cleaned = cleanText(text);
|
||||
if (!cleaned || /^(image|photo)$/i.test(cleaned)) return "";
|
||||
return escapeMarkdownAlt(cleaned);
|
||||
}
|
||||
|
||||
export function summarizeText(text: string, maxLength: number): string | undefined {
|
||||
const normalized = cleanText(text);
|
||||
if (!normalized) return undefined;
|
||||
return normalized.length > maxLength
|
||||
? `${normalized.slice(0, maxLength - 3)}...`
|
||||
: normalized;
|
||||
}
|
||||
|
||||
export function buildTweetTitle(text: string, fallback: string): string {
|
||||
return summarizeText(text, 80) ?? fallback;
|
||||
}
|
||||
|
||||
export function normalizeXMarkdown(markdown: string): string {
|
||||
return normalizeMarkdown(markdown.replace(/^(#{1,6})\s*\n+([^\n])/gm, "$1 $2"));
|
||||
}
|
||||
|
||||
export function inferLanguage(text: string, fallback?: string): string | undefined {
|
||||
const normalized = cleanText(text);
|
||||
if (!normalized) return fallback;
|
||||
|
||||
const han = (normalized.match(/\p{Script=Han}/gu) || []).length;
|
||||
const hiragana = (normalized.match(/\p{Script=Hiragana}/gu) || []).length;
|
||||
const katakana = (normalized.match(/\p{Script=Katakana}/gu) || []).length;
|
||||
const hangul = (normalized.match(/\p{Script=Hangul}/gu) || []).length;
|
||||
|
||||
if (hangul >= 8) return "ko";
|
||||
if (hiragana + katakana >= 8) return "ja";
|
||||
if (han >= 16) return "zh";
|
||||
return fallback;
|
||||
}
|
||||
|
||||
export function buildQuoteMarkdown(markdown: string, author?: string): string {
|
||||
const normalized = normalizeMarkdown(markdown);
|
||||
if (!normalized) return "";
|
||||
|
||||
const lines = normalized.split("\n");
|
||||
const prefixed = lines.map((line) => (line ? `> ${line}` : ">")).join("\n");
|
||||
const header = author ? `> Quote from ${author}` : "> Quote";
|
||||
return `${header}\n${prefixed}`;
|
||||
}
|
||||
|
||||
export function pickFirstValidLinkText(userNameEl: Element | null | undefined): {
|
||||
name?: string;
|
||||
username?: string;
|
||||
author?: string;
|
||||
} {
|
||||
if (!userNameEl) return {};
|
||||
|
||||
const linkTexts = Array.from(userNameEl.querySelectorAll("a[href]"))
|
||||
.map((link) => cleanUserLabel(link.textContent))
|
||||
.filter(Boolean);
|
||||
|
||||
let username = linkTexts.find((text) => text.startsWith("@"));
|
||||
let name = linkTexts.find((text) => !text.startsWith("@") && !/^(promote|more)$/i.test(text));
|
||||
|
||||
if (!username || !name) {
|
||||
const text = cleanUserLabel(userNameEl.textContent);
|
||||
const fallbackMatch = text.match(/^(.*?)\s*(@[A-Za-z0-9_]+)(?:\s*·.*)?$/);
|
||||
if (fallbackMatch) {
|
||||
name = name ?? cleanText(fallbackMatch[1]);
|
||||
username = username ?? cleanText(fallbackMatch[2]);
|
||||
}
|
||||
}
|
||||
|
||||
const author = name && username ? `${name} (${username})` : username ?? name;
|
||||
return { name, username, author };
|
||||
}
|
||||
|
||||
export function extractPublishedForCurrentUrl(root: ParentNode, url: string): string | undefined {
|
||||
const parsed = parseUrl(url);
|
||||
if (!parsed) return undefined;
|
||||
const currentPath = parsed.pathname.toLowerCase();
|
||||
|
||||
for (const timeElement of root.querySelectorAll("a[href] time[datetime]")) {
|
||||
const href = timeElement.closest("a")?.getAttribute("href");
|
||||
const hrefUrl = href ? parseUrl(href.startsWith("http") ? href : `${parsed.origin}${href}`) : null;
|
||||
if (hrefUrl?.pathname.toLowerCase() === currentPath) {
|
||||
return timeElement.getAttribute("datetime") ?? undefined;
|
||||
}
|
||||
}
|
||||
|
||||
return root.querySelector("time[datetime]")?.getAttribute("datetime") ?? undefined;
|
||||
}
|
||||
|
||||
export function collectMediaMarkdown(root: ParentNode, seen: Set<string>): MediaResult {
|
||||
const lines: string[] = [];
|
||||
const urls: string[] = [];
|
||||
const rootElement = root as Element & {
|
||||
getAttribute?: (name: string) => string | null;
|
||||
};
|
||||
const photoNodes = [
|
||||
...(typeof rootElement.getAttribute === "function" &&
|
||||
rootElement.getAttribute("data-testid") === "tweetPhoto"
|
||||
? [rootElement]
|
||||
: []),
|
||||
...Array.from(root.querySelectorAll("[data-testid='tweetPhoto']")),
|
||||
];
|
||||
|
||||
for (const node of photoNodes) {
|
||||
const img = node.querySelector("img");
|
||||
const imageUrl = img?.getAttribute("src");
|
||||
if (imageUrl && !seen.has(imageUrl)) {
|
||||
seen.add(imageUrl);
|
||||
urls.push(imageUrl);
|
||||
lines.push(``);
|
||||
}
|
||||
|
||||
const video = node.querySelector("video");
|
||||
const posterUrl = video?.getAttribute("poster");
|
||||
if (posterUrl && !seen.has(posterUrl)) {
|
||||
seen.add(posterUrl);
|
||||
urls.push(posterUrl);
|
||||
lines.push(``);
|
||||
}
|
||||
|
||||
const videoUrl = video?.getAttribute("src") ?? video?.querySelector("source")?.getAttribute("src");
|
||||
if (videoUrl && !seen.has(videoUrl)) {
|
||||
seen.add(videoUrl);
|
||||
urls.push(videoUrl);
|
||||
lines.push(`[video](${videoUrl})`);
|
||||
}
|
||||
}
|
||||
|
||||
return { lines, urls };
|
||||
}
|
||||
|
||||
export function materializeTweetPhotoNodes(root: Element): void {
|
||||
for (const photo of Array.from(root.querySelectorAll("[data-testid='tweetPhoto']"))) {
|
||||
const document = photo.ownerDocument;
|
||||
const container = document.createElement("span");
|
||||
|
||||
const img = photo.querySelector("img");
|
||||
const imageUrl = img?.getAttribute("src");
|
||||
if (imageUrl) {
|
||||
const image = document.createElement("img");
|
||||
image.setAttribute("src", imageUrl);
|
||||
const alt = normalizeAlt(img?.getAttribute("alt"));
|
||||
if (alt) {
|
||||
image.setAttribute("alt", alt);
|
||||
}
|
||||
container.appendChild(image);
|
||||
}
|
||||
|
||||
const video = photo.querySelector("video");
|
||||
const posterUrl = video?.getAttribute("poster");
|
||||
if (posterUrl) {
|
||||
const poster = document.createElement("img");
|
||||
poster.setAttribute("src", posterUrl);
|
||||
poster.setAttribute("alt", "video");
|
||||
container.appendChild(poster);
|
||||
}
|
||||
|
||||
const videoUrl = video?.getAttribute("src") ?? video?.querySelector("source")?.getAttribute("src");
|
||||
if (videoUrl) {
|
||||
if (container.childNodes.length > 0) {
|
||||
container.appendChild(document.createTextNode(" "));
|
||||
}
|
||||
const link = document.createElement("a");
|
||||
link.setAttribute("href", videoUrl);
|
||||
link.textContent = "video";
|
||||
container.appendChild(link);
|
||||
}
|
||||
|
||||
if (container.childNodes.length === 0) {
|
||||
photo.remove();
|
||||
continue;
|
||||
}
|
||||
|
||||
photo.replaceWith(container);
|
||||
}
|
||||
}
|
||||
|
||||
function collapseLinkedMediaContainers(root: Element): void {
|
||||
for (const anchor of Array.from(root.querySelectorAll("a[href]"))) {
|
||||
const images = Array.from(anchor.querySelectorAll("img"));
|
||||
if (images.length !== 1) continue;
|
||||
if (cleanText(anchor.textContent)) continue;
|
||||
|
||||
const image = images[0].cloneNode(true);
|
||||
anchor.replaceChildren(image);
|
||||
}
|
||||
}
|
||||
|
||||
export function convertXRichTextElementToMarkdown(node: Element): string {
|
||||
const clone = node.cloneNode(true) as Element;
|
||||
materializeTweetPhotoNodes(clone);
|
||||
collapseLinkedMediaContainers(clone);
|
||||
return normalizeXMarkdown(convertHtmlFragmentToMarkdown(clone.innerHTML));
|
||||
}
|
||||
|
||||
export function sanitizeCoverImage(primary?: string, fallback?: string): string | undefined {
|
||||
if (primary) return primary;
|
||||
if (!fallback || fallback === DEFAULT_X_OG_IMAGE) return undefined;
|
||||
return fallback;
|
||||
}
|
||||
@@ -0,0 +1,82 @@
|
||||
import type { ConversionResult } from "../../markdown-conversion-shared.js";
|
||||
import type { UrlRuleParser, UrlRuleParserContext } from "../types.js";
|
||||
import {
|
||||
buildQuoteMarkdown,
|
||||
buildTweetTitle,
|
||||
cleanText,
|
||||
collectMediaMarkdown,
|
||||
convertXRichTextElementToMarkdown,
|
||||
extractPublishedForCurrentUrl,
|
||||
inferLanguage,
|
||||
isXHost,
|
||||
isXStatusPath,
|
||||
normalizeXMarkdown,
|
||||
parseUrl,
|
||||
pickFirstValidLinkText,
|
||||
sanitizeCoverImage,
|
||||
summarizeText,
|
||||
} from "./x-shared.js";
|
||||
|
||||
function parseXStatus(context: UrlRuleParserContext): ConversionResult | null {
|
||||
const article = context.document.querySelector("article[data-testid='tweet'], article") as Element | null;
|
||||
if (!article) return null;
|
||||
|
||||
const tweetTextElements = Array.from(article.querySelectorAll("[data-testid='tweetText']")) as Element[];
|
||||
if (tweetTextElements.length === 0) return null;
|
||||
|
||||
const userNameElements = Array.from(article.querySelectorAll("[data-testid='User-Name']")) as Element[];
|
||||
const mainTextElement = tweetTextElements[0];
|
||||
const mainIdentity = pickFirstValidLinkText(userNameElements[0]);
|
||||
const published = extractPublishedForCurrentUrl(article, context.url);
|
||||
const mainMarkdown = normalizeXMarkdown(convertXRichTextElementToMarkdown(mainTextElement));
|
||||
if (!mainMarkdown) return null;
|
||||
|
||||
const parts = [mainMarkdown];
|
||||
const quotedTextElements = tweetTextElements.slice(1);
|
||||
const quotedUserNameElements = userNameElements.slice(1);
|
||||
|
||||
quotedTextElements.forEach((element, index) => {
|
||||
const quoteMarkdown = normalizeXMarkdown(convertXRichTextElementToMarkdown(element));
|
||||
if (!quoteMarkdown) return;
|
||||
const quoteIdentity = pickFirstValidLinkText(quotedUserNameElements[index]);
|
||||
parts.push(buildQuoteMarkdown(quoteMarkdown, quoteIdentity.author));
|
||||
});
|
||||
|
||||
const media = collectMediaMarkdown(article, new Set<string>());
|
||||
if (media.lines.length > 0) {
|
||||
parts.push(media.lines.join("\n\n"));
|
||||
}
|
||||
|
||||
const mainText = cleanText(mainTextElement.textContent);
|
||||
const markdown = normalizeXMarkdown(parts.join("\n\n"));
|
||||
|
||||
return {
|
||||
metadata: {
|
||||
...context.baseMetadata,
|
||||
title: buildTweetTitle(mainText, context.baseMetadata.title),
|
||||
description: summarizeText(mainText, 220) ?? context.baseMetadata.description,
|
||||
author: mainIdentity.author ?? context.baseMetadata.author,
|
||||
published: published ?? context.baseMetadata.published,
|
||||
coverImage: sanitizeCoverImage(media.urls[0], context.baseMetadata.coverImage),
|
||||
language: inferLanguage(mainText, context.baseMetadata.language),
|
||||
},
|
||||
markdown,
|
||||
rawHtml: context.html,
|
||||
conversionMethod: "parser:x-status",
|
||||
};
|
||||
}
|
||||
|
||||
export const xStatusRuleParser: UrlRuleParser = {
|
||||
id: "x-status",
|
||||
supports(context) {
|
||||
const parsed = parseUrl(context.url);
|
||||
if (!parsed || !isXHost(parsed.hostname)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return isXStatusPath(parsed.pathname) && Boolean(context.document.querySelector("[data-testid='tweetText']"));
|
||||
},
|
||||
parse(context): ConversionResult | null {
|
||||
return parseXStatus(context);
|
||||
},
|
||||
};
|
||||
@@ -0,0 +1,14 @@
|
||||
import type { ConversionResult, PageMetadata } from "../markdown-conversion-shared.js";
|
||||
|
||||
export interface UrlRuleParserContext {
|
||||
html: string;
|
||||
url: string;
|
||||
document: Document;
|
||||
baseMetadata: PageMetadata;
|
||||
}
|
||||
|
||||
export interface UrlRuleParser {
|
||||
id: string;
|
||||
supports(context: UrlRuleParserContext): boolean;
|
||||
parse(context: UrlRuleParserContext): ConversionResult | null;
|
||||
}
|
||||
@@ -151,8 +151,7 @@ From outline entry:
|
||||
```markdown
|
||||
## Watermark
|
||||
|
||||
Include a subtle watermark "{content}" positioned at {position}
|
||||
with approximately {opacity*100}% visibility. The watermark should
|
||||
Include a subtle watermark "{content}" positioned at {position}. The watermark should
|
||||
be legible but not distracting from the main content.
|
||||
```
|
||||
|
||||
@@ -295,19 +294,19 @@ Create a Xiaohongshu (Little Red Book) style infographic following these guideli
|
||||
## Content
|
||||
|
||||
**Position**: Content (Page 3 of 6)
|
||||
**Core Message**: ChatGPT使用技巧
|
||||
**Core Message**: ChatGPT 使用技巧
|
||||
|
||||
**Text Content**:
|
||||
- Title: 「ChatGPT」
|
||||
- Subtitle: 最强AI助手
|
||||
- Subtitle: 最强 AI 助手
|
||||
- Points:
|
||||
- 写文案：给出框架，秒出初稿
|
||||
- 改文章：润色、翻译、总结
|
||||
- 编程：写代码、找bug
|
||||
- 编程：写代码、找 bug
|
||||
- 学习：解释概念、出题练习
|
||||
|
||||
**Visual Concept**:
|
||||
ChatGPT logo居中，四周放射状展示功能点
|
||||
ChatGPT logo 居中，四周放射状展示功能点
|
||||
深色科技背景，霓虹绿点缀
|
||||
|
||||
---
|
||||
|
||||
Reference in New Issue
Block a user