跳到正文
TakoAPI
返回技能列表

paddleocr-doc-parsing-v2

由 hiotec 提供

Image & Video Generation
651下载量由 clawskills.sh 提供
4星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Parse documents using PaddleOCR's API.

描述

该技能的功能

Parses images and PDF files using PaddleOCR's API, extracting text and layout structure into Markdown format. Supports sync mode for quick processing and async mode for large or multi-page documents. Handles 110+ languages and detects text blocks, tables, and formulas.

Automatic layout analysis preserves document structure (headings, tables, formulas) that plain OCR tools typically flatten into raw text.

何时使用

  • Extracting text from scanned invoices or receipts
  • Converting multi-page PDFs to structured Markdown
  • Parsing documents in non-Latin scripts
  • Processing large batches of PDFs asynchronously
  • Pulling table data out of image-based reports

示例工作流

输入

User asks: extract the content of this scanned contract PDF

智能体
  1. 1

    Checks file size to determine sync vs async mode

  2. 2

    Calls paddleocr_parse.sh with -t pdf flag on the file

  3. 3

    Polls job status if async mode is used

  4. 4

    Receives JSON response with markdown.text field

  5. 5

    Returns structured Markdown with preserved headings and tables

输出

Markdown representation of the contract with section headings and any tables intact

前置要求

  • PADDLEOCR_ACCESS_TOKEN environment variable
  • PADDLEOCR_API_URL environment variable
  • PaddleOCR account and API credentials from paddleocr.com

安装

clawhub install hiotec/paddleocr-doc-parsing-v2

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接