Page Selection

import pymupdf4llm

# Extract only the first three pages
md_text = pymupdf4llm.to_markdown("document.pdf", pages=[0, 1, 2])

n = 5
md_text = pymupdf4llm.to_markdown("document.pdf", pages=list(range(n)))

import pymupdf

doc = pymupdf.open("document.pdf")
page_count = doc.page_count

last_5 = list(range(page_count - 5, page_count))
md_text = pymupdf4llm.to_markdown("document.pdf", pages=last_5)

# Pages 10–19 (zero-based)
pages = list(range(10, 20))
md_text = pymupdf4llm.to_markdown("document.pdf", pages=pages)

# Cover page, table of contents, and appendix
md_text = pymupdf4llm.to_markdown("document.pdf", pages=[0, 1, 47, 48, 49])

# Even pages only (0, 2, 4, ...)
md_text = pymupdf4llm.to_markdown("document.pdf", pages=list(range(0, 50, 2)))

import pymupdf
import pymupdf4llm

doc = pymupdf.open("document.pdf")
print(f"Total pages: {doc.page_count}")

# Extract the second half of the document
midpoint = doc.page_count // 2
pages = list(range(midpoint, doc.page_count))

md_text = pymupdf4llm.to_markdown("document.pdf", pages=pages)

chunks = pymupdf4llm.to_markdown(
    "document.pdf",
    pages=[4, 5, 6],
    page_chunks=True
)

for chunk in chunks:
    print(f"Page {chunk['metadata']['page']}: {len(chunk['text'])} chars")
# Page 4: 1842 chars
# Page 5: 2103 chars
# Page 6: 987 chars

# JSON output — specific pages only
data = pymupdf4llm.to_json("document.pdf", pages=[0, 1, 2])

# Plain text — specific pages only
text = pymupdf4llm.to_text("document.pdf", pages=[0, 1, 2])

import pymupdf
import pymupdf4llm
from pathlib import Path

doc = pymupdf.open("large-document.pdf")
batch_size = 20
results = []

for start in range(0, doc.page_count, batch_size):
    batch = list(range(start, min(start + batch_size, doc.page_count)))
    print(f"Processing pages {batch[0]}–{batch[-1]}...")
    chunk = pymupdf4llm.to_markdown(doc, pages=batch)
    results.append(chunk)

full_text = "\n\n".join(results)
Path("output.md").write_text(full_text, encoding="utf-8")
print(f"Done. {doc.page_count} pages processed.")

import pymupdf
import pymupdf4llm

doc = pymupdf.open("document.pdf")

# Find pages that have selectable text
non_blank = [
    i for i in range(doc.page_count)
    if doc[i].get_text().strip()
]

print(f"{len(non_blank)} of {doc.page_count} pages contain text")

md_text = pymupdf4llm.to_markdown(doc, pages=non_blank)