from zpdf import Document

with Document("paper.pdf") as doc:
    print(doc.page_count)

    # Extract all text (reading order)
    text = doc.extract_all()

    # Extract single page
    page_text = doc.extract_page(0)

    # Extract as markdown
    md = doc.extract_all_markdown()

    # Get text with bounding boxes
    spans = doc.extract_bounds(0)
    for span in spans:
        print(f"{span.text} at ({span.x0}, {span.y0})")

with open("doc.pdf", "rb") as f:
    data = f.read()

with Document(data) as doc:
    text = doc.extract_all()