read

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Read: Fetch Any URL or PDF as Markdown

Read：将任意URL或PDF抓取为Markdown

Convert any URL or local PDF to clean Markdown and save it.

将任意URL或本地PDF转换为干净的Markdown格式并保存。

Routing

路由规则

Input	Method
`mp.weixin.qq.com`	WeChat script
`.pdf` URL or local PDF path	PDF extraction
Everything else	Proxy cascade

After routing, load

references/read-methods.md

to get the specific commands for the chosen method, then execute.

输入	处理方法
`mp.weixin.qq.com`	微信专用脚本
`.pdf` 后缀的URL或本地PDF路径	PDF内容提取
其他所有场景	级联代理

路由完成后，加载

references/read-methods.md

获取所选方法的具体命令，然后执行。

Output Format

输出格式

Title:  {title}
Author: {author} (if available)
Source: {platform}
URL:    {original url}

Summary
{3-5 sentence summary}

Content
{full Markdown, truncated at 200 lines if long}

Title:  {title}
Author: {author} (如有)
Source: {platform}
URL:    {original url}

摘要
{3-5句话的摘要}

正文
{完整Markdown内容，内容过长时截断至200行}

Saving

保存规则

Save to

~/Downloads/{title}.md

with YAML frontmatter by default. Skip only if user says "just preview" or "don't save". Tell the user the saved path.

After saving and reporting the path, stop. Do not analyze, comment on, or discuss the content unless asked. If content was truncated at 200 lines, say so and offer to continue.

默认保存到

~/Downloads/{title}.md

，自动携带YAML前置元数据。仅当用户指定“仅预览”或“不保存”时跳过保存步骤，需告知用户保存路径。

保存并告知路径后结束流程。除非用户要求，否则不要对内容进行分析、评论或讨论。如果内容被截断为200行，需告知用户并可按需提供完整内容。

Notes

注意事项

r.jina.ai and defuddle.md require no API key
Network failures: prepend local proxy env vars if available
Long content:
```
| head -n 200
```
to preview first
GitHub URLs: prefer
```
gh
```
CLI over fetching directly

r.jina.ai和defuddle.md无需API密钥
网络故障：如果有可用本地代理环境变量，优先使用
长内容：使用
```
| head -n 200
```
先预览前200行
GitHub URL：优先使用
```
gh
```
CLI而非直接抓取