shareai-lab/learn-claude-code/pdf

# Using pdftotext (poppler-utils)
pdftotext input.pdf -  # Output to stdout
pdftotext input.pdf output.txt  # Output to file
 
# If pdftotext not available, try:
python3 -c "
import fitz  # PyMuPDF
doc = fitz.open('input.pdf')
for page in doc:
    print(page.get_text())
"

import fitz  # pip install pymupdf
doc = fitz.open("input.pdf")
print(f"Pages: {len(doc)}")
print(f"Metadata: {doc.metadata}")
for i, page in enumerate(doc):
    text = page.get_text()
    print(f"--- Page {i+1} ---")
    print(text)

# Using pandoc
pandoc input.md -o output.pdf
 
# With custom styling
pandoc input.md -o output.pdf --pdf-engine=xelatex -V geometry:margin=1in

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
c = canvas.Canvas("output.pdf", pagesize=letter)
c.drawString(100, 750, "Hello, PDF!")
c.save()

# Using wkhtmltopdf
wkhtmltopdf input.html output.pdf
 
# Or with Python
python3 -c "
import pdfkit
pdfkit.from_file('input.html', 'output.pdf')
"

import fitz
result = fitz.open()
for pdf_path in ["file1.pdf", "file2.pdf", "file3.pdf"]:
    doc = fitz.open(pdf_path)
    result.insert_pdf(doc)
result.save("merged.pdf")

import fitz
doc = fitz.open("input.pdf")
for i in range(len(doc)):
    single = fitz.open()
    single.insert_pdf(doc, from_page=i, to_page=i)
    single.save(f"page_{i+1}.pdf")