PDF Verification with Command-Line Tools

# Get full PDF info
pdfinfo document.pdf

# Get only page count
pdfinfo document.pdf | grep Pages

# Extract page count as a number
pdfinfo document.pdf | grep Pages | awk '{print $2}'

# Extract all text to stdout
pdftotext document.pdf -

# Extract text to a file
pdftotext document.pdf output.txt

# Extract text from specific page range
pdftotext -f 1 -l 3 document.pdf output.txt

# Preserve layout (rough formatting)
pdftotext -layout document.pdf output.txt

# Check if tools are installed
which pdfinfo
which pdftotext

# Or test with --help
pdfinfo --help 2>&1 | head -1

# Debian/Ubuntu
apt-get update && apt-get install -y poppler-utils

# RHEL/CentOS/Fedora
yum install -y poppler-utils
# or
dnf install -y poppler-utils

# macOS (with Homebrew)
brew install poppler

# Verify page count matches expected
EXPECTED_PAGES=4
ACTUAL_PAGES=$(pdfinfo document.pdf | grep Pages | awk '{print $2}')

if [ "$ACTUAL_PAGES" -eq "$EXPECTED_PAGES" ]; then
    echo "✓ Page count verified: $ACTUAL_PAGES pages"
else
    echo "✗ Page count mismatch: expected $EXPECTED_PAGES, got $ACTUAL_PAGES"
fi

# Check for required sections/content
pdftotext document.pdf - | grep -i "checklist" && echo "✓ Contains checklist section"
pdftotext document.pdf - | grep -i "references" && echo "✓ Contains references section"

# Count occurrences of key terms
pdftotext document.pdf - | grep -ci "assessment"  # Case-insensitive count

import subprocess

def get_pdf_page_count(pdf_path):
    """Get page count using pdfinfo"""
    result = subprocess.run(
        ['pdfinfo', pdf_path],
        capture_output=True,
        text=True
    )
    for line in result.stdout.split('\n'):
        if line.startswith('Pages:'):
            return int(line.split(':')[1].strip())
    return None

def extract_pdf_text(pdf_path):
    """Extract all text from PDF using pdftotext"""
    result = subprocess.run(
        ['pdftotext', pdf_path, '-'],
        capture_output=True,
        text=True
    )
    return result.stdout

def verify_pdf(pdf_path, expected_pages, required_terms):
    """Verify PDF has expected page count and contains required terms"""
    # Check page count
    pages = get_pdf_page_count(pdf_path)
    if pages != expected_pages:
        return False, f"Expected {expected_pages} pages, got {pages}"
    
    # Check content
    text = extract_pdf_text(pdf_path).lower()
    missing = [term for term in required_terms if term.lower() not in text]
    
    if missing:
        return False, f"Missing terms: {missing}"
    
    return True, "PDF verification passed"