pdf-text-extraction-9424c5

Extract text from PDF files using pdftotext when read_file returns binary data

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/pdf-text-extraction-9424c5/SKILL.md

PDF Text Extraction via pdftotext

Problem

When using read_file on PDF documents, the function may return binary image data or garbled content instead of readable text. This occurs because PDFs can contain scanned images or complex binary structures that read_file cannot properly parse as text.

Solution

Use the pdftotext command-line utility via run_shell to extract clean text content from PDF files.

Steps

1. Verify PDF file exists

import os

pdf_path = "path/to/document.pdf"
if not os.path.exists(pdf_path):
    raise FileNotFoundError(f"PDF not found: {pdf_path}")

2. Extract text using pdftotext

from tools import run_shell

# Extract text to stdout
result = run_shell(command=f"pdftotext '{pdf_path}' -", timeout=60)
pdf_text = result.stdout

# Alternative: extract to a temporary file
temp_txt = "/tmp/extracted.txt"
run_shell(command=f"pdftotext '{pdf_path}' '{temp_txt}'", timeout=60)
with open(temp_txt, 'r') as f:
    pdf_text = f.read()

3. Handle parameter naming carefully

When calling read_file, be aware of the parameter name:

Use filetype="pdf" (not file_type)
Some tool implementations may use different parameter names

# Correct parameter usage
content = read_file(file_path="doc.pdf", filetype="pdf")

# If this returns binary/garbled data, fall back to pdftotext

Common pdftotext Options

Option	Description
`-`	Output to stdout
`-layout`	Maintain original layout
`-f <n>`	Start from page n
`-l <n>`	End at page n
`-q`	Quiet mode

Example with options:

result = run_shell(command=f"pdftotext -layout -q '{pdf_path}' -", timeout=60)

Error Handling

from tools import run_shell

def extract_pdf_text(pdf_path):
    """Extract text from PDF using pdftotext with error handling."""
    import os
    
    if not os.path.exists(pdf_path):
        raise FileNotFoundError(f"PDF not found: {pdf_path}")
    
    result = run_shell(command=f"pdftotext '{pdf_path}' -", timeout=60)
    
    if result.returncode != 0:
        raise RuntimeError(f"pdftotext failed: {result.stderr}")
    
    return result.stdout.strip()

When to Use This Pattern

read_file returns binary data, garbled text, or image content for a PDF
You need searchable/processable text from PDF documents
The PDF contains text (not just scanned images - for those, consider OCR tools)

Prerequisites

pdftotext must be installed (part of poppler-utils on Debian/Ubuntu, poppler on macOS via Homebrew)
Verify availability: run_shell(command="which pdftotext")

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/pdf-text-extraction-9424c5/SKILL.md
Commit: c5a9c4b

Last updated: 2 days ago
First committed: 14 days ago

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.