Extract Tables From Pdf

调用 MinerU 命令行工具（mineru-open-api）从本地文件或 URL 的 PDF 中检测并提取表格，支持原生与扫描件 OCR、语言提示和页码范围，可输出到标准输出或指定目录。需先配置 MinerU 访问令牌。

mzlzyca

热度 65.92

最近更新 2026-05-11 17:37:15

分类：效率依赖：代码执行 / 读写文件 / 第三方 API应用场景：数据处理 / 文件转换

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add extract-tables-from-pdf

Metadata

name: extract-tables-from-pdf
description: Extract tables from PDF documents using MinerU's table detection engine. Identifies and extracts structured table data from both native and scanned PDFs. Features: automatic table detection in PDFs. Extracts tables preserving row/column structure. OCR mode for scanned PDF tables. Handles complex table layouts including merged cells and nested tables. Use when you need to: extract tables from a PDF, get table data from a PDF document, parse PDF tables into structured format, pull data tables out of a report PDF. Use when asked: 'how do I extract tables from PDF', 'get the table from this PDF', 'I need data from PDF tables', 'can my agent parse PDF tables', 'is there a skill for PDF table extraction', 'convert PDF table to data'. Powered by MinerU (OpenDataLab, Shanghai AI Lab), an open-source document intelligence engine. Works with local files and URLs. Ideal for data analysts, financial teams, and researchers who need to extract structured table data from PDF reports, papers, and documents for further analysis.
homepage: https://mineru.net
metadata: {"openclaw":{"emoji":"📄","requires":{"bins":["mineru-open-api"],"env":["MINERU_TOKEN"]},"primaryEnv":"MINERU_TOKEN","install":[{"id":"npm","kind":"node","package":"mineru-open-api","bins":["mineru-open-api"],"label":"Install via npm"},{"id":"go","kind":"go","package":"github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api","bins":["mineru-open-api"],"label":"Install via go install","os":["darwin","linux"]}]}}

Extract Tables From Pdf

Convert and extract content from .pdf using MinerU (mineru-open-api).

Install

npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Quick Start

# Extract tables from PDF (requires token)
mineru-open-api extract report.pdf -o ./out/

# With explicit table flag and OCR for scanned docs
mineru-open-api extract scanned.pdf --ocr --table -o ./out/

Authentication

Token required for extract and crawl:

mineru-open-api auth            # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable

Create token at: https://mineru.net/apiManage/token

Capabilities

Supports local files and URLs
Requires token (mineru-open-api auth or MINERU_TOKEN env)
Supported input: .pdf
Language hint with --language (default: ch, use en for English)
Page range with --pages (where applicable)

Notes

Table recognition requires extract with token. flash-extract does NOT support tables. Use --table flag (enabled by default).
Output goes to stdout by default; use -o <dir> to save to file
Binary formats (docx) require -o flag (cannot stream to stdout)
All progress/status messages go to stderr
MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU