闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > table-ocr
t

表格OCR识别

技能标识：table-ocr

OCR and extract tables from scanned PDFs and images using MinerU. Recognizes table structures in image-based documents and converts them to structured Markdown. Features: table detection and recognition from PDFs and images (.png, .jpg, .jpeg, .webp). OCR for scanned documents with image-embedded tables. Supports complex table layouts with merged cells. Combined OCR and table extraction in one pass. Use when you need to: extract tables from scanned PDFs, OCR tables from images, convert image tab

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 0.4.0
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

表格OCR识别

表格OCR

使用MinerU（mineru-open-api）从.pdf/图片（.png/.jpg/.jpeg/.webp）中转换并提取内容。

安装

bash
npm install -g mineru-open-api

或通过Go安装（macOS/Linux）：


go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

快速开始

bash

从PDF中提取表格（需要令牌）


mineru-open-api extract report.pdf -o ./out/

对扫描文档使用显式表格标记和OCR

mineru-open-api extract scanned.pdf --ocr --table -o ./out/

身份验证

extract和crawl命令需要令牌：

bash
mineru-open-api auth # 交互式令牌设置
export MINERU_TOKEN=your-token # 或通过环境变量设置

在以下地址创建令牌：https://mineru.net/apiManage/token

功能特性

  • - 支持本地文件和URL
  • 需要令牌（mineru-open-api auth或MINERU_TOKEN环境变量）
  • 支持的输入格式：.pdf / 图片（.png/.jpg/.jpeg/.webp）
  • 通过--language指定语言（默认：ch，英文使用en）
  • 通过--pages指定页码范围（适用时）

注意事项

  • - 表格识别需要使用令牌执行extract命令。对扫描内容使用--ocr，对表格检测使用--table（extract中默认同时启用两者）
  • 输出默认发送到标准输出；使用-o 保存到文件
  • 二进制格式（docx）需要使用-o标记（无法流式输出到标准输出）
  • 所有进度/状态消息发送到标准错误输出
  • MinerU是OpenDataLab（上海人工智能实验室）的开源项目：https://github.com/opendatalab/MinerU

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 table-ocr-1775989981 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 table-ocr-1775989981 技能

通过命令行安装

skillhub install table-ocr-1775989981

下载

⬇ 下载 table-ocr v0.4.0（免费）

文件大小: 1.92 KB | 发布时间: 2026-4-13 12:15

v0.4.0 最新 2026-4-13 12:15
SEO: expand description for better ClawHub vector search discovery

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部