web_extract(urls=["https://arxiv.org/pdf/2402.03300"])
web_extract(urls=["https://example.com/report.pdf"])

pip install pymupdf pymupdf4llm

python scripts/extract_pymupdf.py document.pdf              # Plain text
python scripts/extract_pymupdf.py document.pdf --markdown    # Markdown
python scripts/extract_pymupdf.py document.pdf --tables      # Tables
python scripts/extract_pymupdf.py document.pdf --images out/ # Extract images
python scripts/extract_pymupdf.py document.pdf --metadata    # Title, author, pages
python scripts/extract_pymupdf.py document.pdf --pages 0-4   # Specific pages

python3 -c "
import pymupdf
doc = pymupdf.open('document.pdf')
for page in doc:
    print(page.get_text())
"

# Check disk space first
python scripts/extract_marker.py --check

pip install marker-pdf

python scripts/extract_marker.py document.pdf                # Markdown
python scripts/extract_marker.py document.pdf --json         # JSON with metadata
python scripts/extract_marker.py document.pdf --output_dir out/  # Save images
python scripts/extract_marker.py scanned.pdf                 # Scanned PDF (OCR)
python scripts/extract_marker.py document.pdf --use_llm      # LLM-boosted accuracy

marker_single document.pdf --output_dir ./output
marker /path/to/folder --workers 4    # Batch

# Abstract only (fast)
web_extract(urls=["https://arxiv.org/abs/2402.03300"])

# Full paper
web_extract(urls=["https://arxiv.org/pdf/2402.03300"])

# Search
web_search(query="arxiv GRPO reinforcement learning 2026")

# Split: extract pages 1-5 to a new PDF
import pymupdf
doc = pymupdf.open("report.pdf")
new = pymupdf.open()
for i in range(5):
    new.insert_pdf(doc, from_page=i, to_page=i)
new.save("pages_1-5.pdf")

# Merge multiple PDFs
import pymupdf
result = pymupdf.open()
for path in ["a.pdf", "b.pdf", "c.pdf"]:
    result.insert_pdf(pymupdf.open(path))
result.save("merged.pdf")

# Search for text across all pages
import pymupdf
doc = pymupdf.open("report.pdf")
for i, page in enumerate(doc):
    results = page.search_for("revenue")
    if results:
        print(f"Page {i+1}: {len(results)} match(es)")
        print(page.get_text("text"))