AGENT SKILL

reliable-pdf-extraction

Use shell commands or Python libraries to extract PDF text when read_file PDF handler fails

使用场景文档处理
License 许可
MIT
所属仓库
HKUDS/AgentPilot
最近更新
2026-11-12
Stars
★ 8.0k
Forks
944

01 前言 Front Matter

name
reliable-pdf-extraction
description
Use shell commands or Python libraries to extract PDF text when read_file PDF handler fails

02 资源文件 1

03 SKILL.md 正文

Reliable PDF Text Extraction

Problem

The read_file tool with filetype='pdf' often returns binary image data, errors, or unusable output when attempting to extract text from PDF documents. This makes it unreliable for structured data extraction tasks.

Solution

Use run_shell with command-line tools (pdftotext, pdfinfo) or execute_code_sandbox with Python libraries (PyMuPDF, pdfplumber) to extract PDF text content reliably.

Methods

Method 1: pdftotext (Recommended for simple extraction)

# Extract all text to stdout
pdftotext input.pdf -

# Or extract to file
pdftotext input.pdf output.txt
cat output.txt

Method 2: pdfinfo (For metadata)

pdfinfo input.pdf

Method 3: Python with PyMuPDF (fitz)

import fitz  # PyMuPDF

doc = fitz.open("input.pdf")
text = ""
for page in doc:
    text += page.get_text()
print(text)
doc.close()

Method 4: Python with pdfplumber (Better for tables/structured data)

import pdfplumber

with pdfplumber.open("input.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)
        # For tables:
        # tables = page.extract_tables()

Workflow

  1. Attempt read_file with filetype='pdf' first (in case it works)

  2. Check output - If you receive:

    • Binary/garbage data
    • Error messages
    • Empty or truncated content
    • Image data instead of text
  3. Fall back to one of the extraction methods above:

    • Use pdftotext via run_shell for quick text extraction
    • Use pdfplumber via execute_code_sandbox for structured data/tables
    • Use PyMuPDF for complex layouts or when you need more control
  4. Process the extracted text for your task

Example Usage

# Via run_shell
result = run_shell(command="pdftotext document.pdf -")
pdf_text = result.stdout

# Via execute_code_sandbox
code = """
import pdfplumber
with pdfplumber.open("/path/to/document.pdf") as pdf:
    for page in pdf.pages:
        print(page.extract_text())
"""
result = execute_code_sandbox(code=code)
pdf_text = result.stdout

Tips

  • pdftotext is fastest and most reliable for plain text extraction
  • pdfplumber excels at extracting tables and preserving layout
  • PyMuPDF offers the most control for complex PDF structures
  • Always check if the PDF is scanned/image-based (may need OCR tools like tesseract)
  • Some PDFs have copy protection that may prevent text extraction

04 同仓库更多 Skills

HKUDS
HKUDS/AgentPilot

agentpilot

Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.

★ 8.0k
HKUDS
HKUDS/AgentPilot

remember

Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.

★ 8.0k
HKUDS
HKUDS/AgentPilot

skill-discovery

Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.

Skill与智能体开发
★ 8.0k
HKUDS
HKUDS/AgentPilot

delegate-task

Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.

Skill与智能体开发
★ 8.0k
HKUDS
HKUDS/AgentPilot

write-special-chars-ts-check

Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.

★ 8.0k
HKUDS
HKUDS/AgentPilot

write-special-chars-readback

Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of /tmp helper scripts.

★ 8.0k