---
id: daily-read
name: "read"
url: https://skills.yangsir.net/skill/daily-read
author: tw93
domain: ai-data-management-analysis
tags: ["data-extraction", "markdown", "web-scraping", "pdf-processing", "information-retrieval"]
install_count: 5100
rating: 4.40 (27 reviews)
github: https://github.com/tw93/waza
---

# read

> 将任意URL或本地PDF转换为清晰Markdown格式，支持飞书文档、代理链和自动降级，快速提取结构化内容

**Stats**: 5,100 installs · 4.4/5 (27 reviews)

## Before / After 对比

### 网页转Markdown

**Before**:

手动复制网页内容到编辑器，清理HTML标签和广告，调整格式混乱的标题和列表，处理PDF需要OCR或在线转换工具，一篇文档需要20分钟

**After**:

输入URL或PDF路径自动输出干净Markdown，智能识别标题层级和代码块，保留原文结构的同时去除冗余元素，30秒完成转换

| Metric | Before | After | Change |
|---|---|---|---|
| 文档处理时间 | 20分钟 | 0.5分钟 | -98% |

## Readme

# read

# Read: Fetch Any URL or PDF as Markdown

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

## Routing

Input
Method

`feishu.cn`, `larksuite.com`
Feishu API script

`.pdf` URL or local PDF path
PDF extraction

Everything else
Run `scripts/fetch.sh {url}` (proxy cascade with auto-fallback)

After routing, load `references/read-methods.md` to get the specific commands for the chosen method, then execute.

## Output Format

```
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}

```

## Saving

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.

## Notes

- 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

Weekly Installs522Repository[tw93/waza](https://github.com/tw93/waza)GitHub Stars1.6KFirst Seen4 days agoSecurity Audits[Gen Agent Trust HubWarn](/tw93/waza/read/security/agent-trust-hub)[SocketPass](/tw93/waza/read/security/socket)[SnykWarn](/tw93/waza/read/security/snyk)Installed onclaude-code483codex418opencode413gemini-cli413warp412amp412

---
*Source: https://skills.yangsir.net/skill/daily-read*
*Markdown mirror: https://skills.yangsir.net/api/skill/daily-read/markdown*