from pypdf import PdfReader

reader = PdfReader("document.pdf")
text = "".join(page.extract_text() for page in reader.pages)
print(text)

uvx --with pypdf python /path/to/extract_pdf_text.py document.pdf

from pypdf import PdfReader

# Read all pages
reader = PdfReader("file.pdf")
for page in reader.pages:
    text = page.extract_text()
    print(text)

from pypdf import PdfReader

reader = PdfReader("file.pdf")
# Get pages 1-5 (0-indexed)
for page in reader.pages[0:5]:
    print(page.extract_text())

# Extract all pages to stdout
python extract_pdf_text.py document.pdf

# Extract to file
python extract_pdf_text.py document.pdf --output text.txt

# Extract specific pages
python extract_pdf_text.py document.pdf --pages 1-5
python extract_pdf_text.py document.pdf --pages 1,3,5