---

name: pdf description: PDF processing operations - reading, merging, splitting, text extraction, OCR, and creation.

PDF Processing Guide

Overview

This guide covers essential PDF processing operations using Python libraries and command-line tools.

Quick Start

Copyfrom 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

Copyfrom 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

Copyreader = 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)

Extract Metadata

Copyreader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Subject: {meta.subject}")

Rotate Pages

Copyreader = 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 with Layout

Copyimport pdfplumber

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

Extract Tables

Copyimport pandas as pd

with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)
    
    if all_tables:
        combined_df = pd.concat(all_tables, ignore_index=True)
        combined_df.to_excel("extracted_tables.xlsx", index=False)

reportlab - Create PDFs

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

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

# Add text
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")

# Add a line
c.line(100, height - 140, 400, height - 140)

c.save()

Command-Line Tools

pdftotext (poppler-utils)

Copy# Extract text
pdftotext input.pdf output.txt

# Extract text preserving layout
pdftotext -layout input.pdf output.txt

# Extract specific pages
pdftotext -f 1 -l 5 input.pdf output.txt  # Pages 1-5

qpdf

Copy# 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  # Rotate page 1 by 90 degrees

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

Common Tasks

Extract Text from Scanned PDFs (OCR)

Copy# Requires: pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path

# Convert PDF to images
images = convert_from_path('scanned.pdf')

# OCR each page
text = ""
for i, image in enumerate(images):
    text += f"Page {i + 1}:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

Add Watermark

Copyfrom pypdf import PdfReader, PdfWriter

# Create watermark (or load existing)
watermark = PdfReader("watermark.pdf").pages[0]

# Apply to all pages
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)

Extract Images

Copy# Using pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix
# Creates output_prefix-000.jpg, output_prefix-001.jpg, etc.

Password Protection

Copyfrom pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()
for page in reader.pages:
    writer.add_page(page)

# Add password
writer.encrypt("userpassword", "ownerpassword")
with open("encrypted.pdf", "wb") as output:
    writer.write(output)

Quick Reference

Dependencies

Copy# Python libraries
pip install pypdf pdfplumber reportlab pytesseract pdf2image

# System tools
# macOS
brew install poppler tesseract qpdf

# Ubuntu/Debian
sudo apt-get install poppler-utils tesseract-ocr qpdf

Attribution

Based on anthropics/skills pdf skill.