paddleocr-doc-parsing
bobholamovic 作
PDF & Documents概要
Parse documents using PaddleOCR's API.
説明
このスキルでできること
Extracts structured content from PDFs and images via a PaddleOCR API endpoint. Handles text, tables, formulas, charts, and multi-column layouts in a single call. The agent runs a Python script against the API and presents results based on what the user asks for.
Unlike basic OCR tools, it preserves full document structure including tables, formulas, reading order, and layout across complex multi-column and mixed-content documents.
使いどころ
- Pulling all tables from an invoice PDF
- Extracting LaTeX formulas from a research paper
- Parsing multi-column magazine or newspaper layouts
- Getting structured data out of scanned financial reports
- Reading figures and charts from technical documents
ワークフロー例
User asks: Extract all the tables from this financial report PDF
- 1
Runs python scripts/vl_caller.py --file-path "financial_report.pdf" --pretty
- 2
Reads the saved JSON result from the temp directory path printed to stderr
- 3
Locates table data in result[n].prunedResult and result[n].markdown fields
- 4
Displays all tables in full without truncating or summarizing
All tables from the document rendered in structured markdown, with the full raw JSON saved to a temp file for reference
要件
- PADDLEOCR_DOC_PARSING_API_URL environment variable (full endpoint URL from a PaddleOCR-compatible service)
- PADDLEOCR_ACCESS_TOKEN environment variable (API access token from the same service)
インストール
clawhub install bobholamovic/paddleocr-doc-parsingCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。