auto: sync OpenClaw config 2026-07-15 14:00

2026-07-15 14:00:48 +08:00
parent 54c9c9f07a
commit a9b8497b9d
34 changed files with 715 additions and 370 deletions
@@ -0,0 +1,16 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "mineru-agent",
+  "installedVersion": "1.0.0",
+  "installedAt": 1784093313391,
+  "artifact": {
+    "kind": "archive",
+    "sha256": "07d8087614fcadb04baeffbd44c17a648ef20d964abee0e3bdeb8a353f783cf5",
+    "integrity": "sha256-B9gIdhT8rbBLrv+9RMF6ZI7yDZZKvuDjveuKNT94PPU="
+  },
+  "skillFile": {
+    "path": "SKILL.md",
+    "sha256": "53a78554ce3f911b92feb405517baa4a80a636d43a9a67f2bed3e34e6f955c0d"
+  }
+}
@@ -0,0 +1,93 @@
+---
+name: mineru
+description: 用 MinerU Agent 轻量解析 API 将 PDF/Word/PPT/Excel/图片解析为 Markdown，无需 Token，IP 限频。适用于文档解析、表格提取、OCR 识别。
+---
+
+# 📄 MinerU - 文档解析
+
+> PDF/Word/PPT/Excel/图片 → 结构化 Markdown
+
+## 🎯 触发条件
+
+当用户要求解析文档、提取文档内容、OCR 识别、将文件转为 Markdown 时使用。
+
+## 🔗 API 信息
+
+- **Base URL:** `https://mineru.net/api/v1/agent`
+- **认证方式:** 无需 Token，IP 限频
+- **文档:** https://mineru.net/apiManage/docs
+
+## 📋 支持的文件类型
+
+| 类型 | 格式 |
+|------|------|
+| 📕 PDF | 论文、书籍、扫描件 |
+| 📝 Word | .docx |
+| 📊 PPT | .pptx |
+| 📊 Excel | .xls, .xlsx |
+| 🖼️ 图片 | .png, .jpg, .jpeg, .jp2, .webp, .gif, .bmp |
+
+## ⚠️ 限制
+
+| 限制项 | 限制值 |
+|--------|--------|
+| 文件大小 | 10 MB |
+| 文件页数 | 20 页 |
+
+## 🚀 使用方式
+
+### 方式一：URL 解析（文件有公开 URL 时）
+
+直接调用解析脚本：
+
+```bash
+python3 SKILL_DIR/scripts/mineru_parse.py --url "https://example.com/file.pdf"
+```
+
+可选参数：
+- `--language ch|en` （默认 ch）
+- `--page_range 1-10`（仅 PDF 有效）
+- `--output /path/to/output.md`（指定输出文件）
+
+### 方式二：文件上传解析（本地文件）
+
+```bash
+python3 SKILL_DIR/scripts/mineru_parse.py --file /path/to/document.pdf
+```
+
+### 方式三：在对话中直接使用
+
+用户发送文件或提供文件路径/URL 时，调用脚本解析，将结果返回给用户。
+
+## 🔄 API 流程
+
+### URL 模式
+1. `POST /parse/url` → 获取 task_id
+2. `GET /parse/{task_id}` → 轮询直到 done
+3. 下载 markdown_url 返回结果
+
+### 文件上传模式
+1. `POST /parse/file` → 获取 task_id + file_url
+2. `PUT file_url` → 上传文件到 OSS
+3. `GET /parse/{task_id}` → 轮询直到 done
+4. 下载 markdown_url 返回结果
+
+## ❌ 错误码
+
+| 错误码 | 说明 | 应对策略 |
+|--------|------|----------|
+| -30001 | 文件大小超出限制（10MB） | 拆分文件或告知用户 |
+| -30002 | 不支持的文件类型 | 检查文件格式 |
+| -30003 | 页数超出限制 | 指定 page_range 拆分 |
+| -30004 | 请求参数错误 | 检查必填参数 |
+
+## 💡 使用技巧
+
+1. **中文文档用 `language: ch`**
+2. **大文件指定 `page_range` 分段解析**
+3. **Word/PPT 用 Office 原生 API 解析，速度最快**
+4. **解析结果为 Markdown 格式，可直接用于后续处理**
+
+---
+
+*轻量快速，无需 Token！📄*
@@ -0,0 +1,6 @@
+{
+  "ownerId": "kn769prr6yvf6e094xz6ebnrmd83n0kz",
+  "slug": "mineru-agent",
+  "version": "1.0.0",
+  "publishedAt": 1774515060069
+}
@@ -0,0 +1,148 @@
+#!/usr/bin/env python3
+"""MinerU Agent 轻量解析 API - 文档转 Markdown
+
+用法:
+  URL 模式:  python3 mineru_parse.py --url "https://example.com/file.pdf"
+  文件模式:  python3 mineru_parse.py --file /path/to/document.pdf
+
+可选参数:
+  --language ch|en        解析语言，默认 ch
+  --page_range 1-10       页码范围，仅 PDF 有效
+  --output /path/to/out.md  指定输出文件路径
+  --timeout 300           轮询超时秒数，默认 300
+"""
+
+import argparse
+import json
+import os
+import sys
+import time
+
+import requests
+
+BASE_URL = "https://mineru.net/api/v1/agent"
+
+STATE_LABELS = {
+    "uploading": "文件下载中",
+    "pending": "排队中",
+    "running": "解析中",
+    "waiting-file": "等待文件上传",
+}
+
+
+def poll_result(task_id, timeout=300, interval=3):
+    """轮询查询解析结果，返回 Markdown 文本或 None。"""
+    start = time.time()
+    while time.time() - start < timeout:
+        resp = requests.get(f"{BASE_URL}/parse/{task_id}")
+        result = resp.json()
+        data = result.get("data", {})
+        state = data.get("state", "unknown")
+        elapsed = int(time.time() - start)
+
+        if state == "done":
+            md_url = data["markdown_url"]
+            print(f"[{elapsed}s] 解析完成", file=sys.stderr)
+            md_resp = requests.get(md_url)
+            md_resp.encoding = "utf-8"
+            return md_resp.text
+
+        if state == "failed":
+            err_msg = data.get("err_msg", "未知错误")
+            err_code = data.get("err_code", "")
+            print(f"[{elapsed}s] 解析失败 [{err_code}]: {err_msg}", file=sys.stderr)
+            return None
+
+        label = STATE_LABELS.get(state, state)
+        print(f"[{elapsed}s] {label}...", file=sys.stderr)
+        time.sleep(interval)
+
+    print(f"轮询超时 ({timeout}s)，task_id: {task_id}", file=sys.stderr)
+    return None
+
+
+def parse_by_url(url, language="ch", page_range=None, timeout=300):
+    """通过 URL 提交文档解析任务并等待结果。"""
+    data = {"url": url, "language": language}
+    if page_range:
+        data["page_range"] = page_range
+
+    resp = requests.post(f"{BASE_URL}/parse/url", json=data)
+    result = resp.json()
+    if result.get("code") != 0:
+        print(f"提交失败: {result.get('msg')}", file=sys.stderr)
+        return None
+
+    task_id = result["data"]["task_id"]
+    print(f"任务已提交, task_id: {task_id}", file=sys.stderr)
+    return poll_result(task_id, timeout=timeout)
+
+
+def parse_by_file(file_path, language="ch", page_range=None, timeout=300):
+    """通过文件上传提交文档解析任务并等待结果。"""
+    if not os.path.exists(file_path):
+        print(f"文件不存在: {file_path}", file=sys.stderr)
+        return None
+
+    file_name = os.path.basename(file_path)
+    file_size = os.path.getsize(file_path)
+    if file_size > 10 * 1024 * 1024:
+        print(f"文件大小 {file_size/1024/1024:.1f}MB 超出 10MB 限制", file=sys.stderr)
+        return None
+
+    # 1. 获取签名上传 URL
+    data = {"file_name": file_name, "language": language}
+    if page_range:
+        data["page_range"] = page_range
+
+    resp = requests.post(f"{BASE_URL}/parse/file", json=data)
+    result = resp.json()
+    if result.get("code") != 0:
+        print(f"获取上传链接失败: {result.get('msg')}", file=sys.stderr)
+        return None
+
+    task_id = result["data"]["task_id"]
+    file_url = result["data"]["file_url"]
+    print(f"任务已创建, task_id: {task_id}", file=sys.stderr)
+
+    # 2. PUT 上传文件到 OSS
+    with open(file_path, "rb") as f:
+        put_resp = requests.put(file_url, data=f)
+        if put_resp.status_code not in (200, 201):
+            print(f"文件上传失败, HTTP {put_resp.status_code}", file=sys.stderr)
+            return None
+    print("文件上传成功，等待解析...", file=sys.stderr)
+
+    # 3. 轮询等待结果
+    return poll_result(task_id, timeout=timeout)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="MinerU 文档解析")
+    group = parser.add_mutually_exclusive_group(required=True)
+    group.add_argument("--url", help="远程文件 URL")
+    group.add_argument("--file", help="本地文件路径")
+    parser.add_argument("--language", default="ch", help="解析语言 (默认 ch)")
+    parser.add_argument("--page_range", help="页码范围，如 1-10（仅 PDF）")
+    parser.add_argument("--output", "-o", help="输出文件路径（默认 stdout）")
+    parser.add_argument("--timeout", type=int, default=300, help="轮询超时秒数（默认 300）")
+    args = parser.parse_args()
+
+    if args.url:
+        content = parse_by_url(args.url, language=args.language, page_range=args.page_range, timeout=args.timeout)
+    else:
+        content = parse_by_file(args.file, language=args.language, page_range=args.page_range, timeout=args.timeout)
+
+    if content is None:
+        sys.exit(1)
+
+    if args.output:
+        with open(args.output, "w", encoding="utf-8") as f:
+            f.write(content)
+        print(f"结果已保存到: {args.output}", file=sys.stderr)
+    else:
+        print(content)
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,41 @@
+## Description: <br>
+MinerU Agent Free parses PDFs, Office documents, spreadsheets, presentations, and images into Markdown through MinerU's lightweight remote parsing API without token authentication. <br>
+
+This skill is ready for commercial/non-commercial use. <br>
+
+## Publisher: <br>
+[haxck](https://clawhub.ai/user/haxck) <br>
+
+### License/Terms of Use: <br>
+MIT-0 <br>
+
+
+## Use Case: <br>
+Developers and agents use this skill to convert user-selected document files or public file URLs into Markdown for document parsing, OCR, table extraction, and downstream analysis. <br>
+
+### Deployment Geography for Use: <br>
+Global <br>
+
+## Known Risks and Mitigations: <br>
+Risk: Selected documents or provided URLs are sent to MinerU's remote parsing service. <br>
+Mitigation: Use only documents and URLs approved for that service; avoid confidential, regulated, or proprietary content unless policy allows it. <br>
+Risk: Returned Markdown may contain untrusted document content. <br>
+Mitigation: Treat parsed Markdown as data for review or extraction, not as instructions for the agent to execute. <br>
+
+
+## Reference(s): <br>
+- [MinerU Agent API documentation](https://mineru.net/apiManage/docs) <br>
+- [ClawHub skill page](https://clawhub.ai/haxck/mineru-agent) <br>
+
+
+## Skill Output: <br>
+**Output Type(s):** [Markdown, Text, Shell commands, Files] <br>
+**Output Format:** [Markdown returned to stdout or written to an output file] <br>
+**Output Parameters:** [1D] <br>
+**Other Properties Related to Output:** [Supports URL or local file input, optional language selection, PDF page ranges, and timeout control.] <br>
+
+## Skill Version(s): <br>
+1.0.0 (source: server release evidence) <br>
+
+## Ethical Considerations: <br>
+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. <br>