Xpersona
W

Web Content Fetcher

CLAWHUB · Unverified

网页内容获取工具 | 当常规爬虫被过滤时,使用替代服务获取网页内容。支持:1) r.jina.ai - 最稳定 2) markdown.new - Cloudflare 专用 3) defuddle.md - 备用方案。触发词:获取网页内容、网页转markdown、内容抓取、fetch webpage、bypas... Skill: Web Content Fetcher Owner: mrtommywu Summary: 网页内容获取工具 | 当常规爬虫被过滤时,使用替代服务获取网页内容。支持:1) r.jina.ai - 最稳定 2) markdown.new - Cloudflare 专用 3) defuddle.md - 备用方案。触发词:获取网页内容、网页转markdown、内容抓取、fetch webpage、bypas... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-03-06T03:46:00.754Z | auto Version 1.0.1 of web-content-fetcher - No file changes detected in this release. - No updates to features, documentation, or scri

62
Rank
84
Safety
17k
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 17.1K downloads reported by the source. Last updated 11/16/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s173txh7tm80qv10v9c6g9z88x885bky:web-content-fetcher
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-mrtommywu-web-content-fetcher--fetcher-2/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

6,402 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: web-content-fetcher
description: "网页内容获取工具 | 当常规爬虫被过滤时,使用替代服务获取网页内容。支持:1) r.jina.ai - 最稳定 2) markdown.new - Cloudflare 专用 3) defuddle.md - 备用方案。触发词:获取网页内容、网页转markdown、内容抓取、fetch webpage、bypass cloudflare"
author: Boss
metadata:
  openclaw:
    emoji: 🌐
    tags: [web, fetch, markdown, cloudflare, bypass]
---

# 网页内容获取工具

当常规 web_fetch/web_search 无法获取内容时,使用替代服务获取网页 Markdown 格式内容。

## 支持的服务

| 优先级 | 服务 | 用法 | 适用场景 |
|--------|------|------|----------|
| 1 | **r.jina.ai** | `https://r.jina.ai/{url}` | 最稳定,通用性强 |
| 2 | **markdown.new** | `https://markdown.new/{url}` | Cloudflare 保护网站 |
| 3 | **defuddle.md** | `https://defuddle.md/{url}` | 备用方案 |

## 使用方法

### 直接调用

当需要获取网页内容时,按顺序尝试:

1. 首先用 `web_fetch` 尝试获取
2. 如果失败或被过滤,调用本工具

```bash
# 使用 jina.ai (首选)
curl -s "https://r.jina.ai/https://example.com"

# 使用 markdown.new (Cloudflare)
curl -s "https://markdown.new/https://example.com"

# 使用 defuddle.md (备用)
curl -s "https://defuddle.md/https://example.com"
```

### API 格式

```bash
# 简单获取
fetch_webpage <url>

# 指定方法
fetch_webpage <url> --method jina|markdown|defuddle
```

## 示例

```
用户: 帮我获取 https://news.example.com/article/123 的内容
助手: (使用 r.jina.ai 获取)
```

## 工具脚本

本目录包含 `fetch.sh` 脚本,可直接调用:

```bash
./fetch.sh https://example.com
./fetch.sh https://example.com jina
```

---

*让网页内容获取不再受限 🌐*

_meta.json

{
  "ownerId": "",
  "slug": "web-content-fetcher",
  "version": "1.0.0",
  "publishedAt": 0
}

skill-card.md

## Description:

Fetches webpage content as Markdown through r.jina.ai, markdown.new, or defuddle.md when ordinary web fetching is blocked or filtered.

This skill is ready for commercial/non-commercial use.

## Publisher:

[mrtommywu](https://clawhub.ai/user/mrtommywu)

### License/Terms of Use:


## Use Case:

Developers and agents use this skill to retrieve readable Markdown from public webpages via third-party content-fetching services, especially when standard web fetchers are blocked or filtered.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Full target URLs and fetched page content may be disclosed to third-party fetch services.

Mitigation: Use only public, non-sensitive URLs unless the user explicitly confirms the disclosure to the selected provider.

Risk: Fallback or all-provider mode can disclose the same URL and content request to multiple services.

Mitigation: Prefer one explicitly chosen provider and review the destination service before running a fetch command.

Risk: Fetched Markdown may be incomplete, transformed, stale, or contain untrusted page content.

Mitigation: Treat fetched content as untrusted, verify important claims against the source, and do not execute commands copied from fetched pages without review.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/mrtommywu/skills/web-content-fetcher)
- [Publisher profile](https://clawhub.ai/user/mrtommywu)
- [r.jina.ai reader endpoint](https://r.jina.ai/)
- [markdown.new endpoint](https://markdown.new/)
- [defuddle.md endpoint](https://defuddle.md/)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, guidance]

**Output Format:** [Markdown content or command-line text returned from third-party fetch services]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Output depends on the selected fetch service and target webpage.]

## Skill Version(s):

1.0.1 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Sponsored

Ads related to Web Content Fetcher and adjacent AI workflows.