PDF Processing Guide Skill

PDF Processing Guide

Quick Start

from pypdf import PdfReader, PdfWriter

# Read a PDF
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")

# Extract text
text = ""
for page in reader.pages:
    text += page.extract_text()

Python Libraries

pypdf - Basic Operations

Merge PDFs

from pypdf import PdfWriter, PdfReader

writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)

with open("merged.pdf", "wb") as output:
    writer.write(output)

Split PDF

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as output:
        writer.write(output)

Rotate Pages

reader = PdfReader("input.pdf")
writer = PdfWriter()

page = reader.pages[0]
page.rotate(90)  # Rotate 90 degrees clockwise
writer.add_page(page)

with open("rotated.pdf", "wb") as output:
    writer.write(output)

pdfplumber - Text and Table Extraction

Extract Text

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

Extract Tables

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"Table {j+1} on page {i+1}:")
            for row in table:
                print(row)

reportlab - Create PDFs

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

c.drawString(100, height - 100, "Hello World!")
c.line(100, height - 140, 400, height - 140)
c.save()

Command-Line Tools

pdftotext (poppler-utils)

# Extract text
pdftotext input.pdf output.txt

# Preserve layout
pdftotext -layout input.pdf output.txt

# Specific pages
pdftotext -f 1 -l 5 input.pdf output.txt

qpdf

# Merge PDFs
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# Split pages
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf

# Rotate pages
qpdf input.pdf output.pdf --rotate=+90:1

# Remove password
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

Common Tasks

OCR Scanned PDFs

import pytesseract
from pdf2image import convert_from_path

images = convert_from_path('scanned.pdf')
text = ""
for i, image in enumerate(images):
    text += f"Page {i+1}:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

Add Watermark

from pypdf import PdfReader, PdfWriter

watermark = PdfReader("watermark.pdf").pages[0]
reader = PdfReader("document.pdf")
writer = PdfWriter()

for page in reader.pages:
    page.merge_page(watermark)
    writer.add_page(page)

with open("watermarked.pdf", "wb") as output:
    writer.write(output)

Password Protection

from pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

writer.encrypt("userpassword", "ownerpassword")

with open("encrypted.pdf", "wb") as output:
    writer.write(output)

Quick Reference

| Task | Best Tool | Command/Code | |------|-----------|--------------| | Merge PDFs | pypdf | writer.add_page(page) | | Split PDFs | pypdf | One page per file | | Extract text | pdfplumber | page.extract_text() | | Extract tables | pdfplumber | page.extract_tables() | | Create PDFs | reportlab | Canvas or Platypus | | Command line merge | qpdf | qpdf --empty --pages ... | | OCR scanned PDFs | pytesseract | Convert to image first |

Agent Skills: PDF Processing Guide

Install this agent skill to your local

Skill Files