Python PDF Operations: Merging, Splitting, Encryption, Decryption, Text Extraction, Watermarking, Page Removal, Rotation, and HTML-to-PDF Conversion

Merge Multiple PDF Files

from PyPDF2 import PdfMerger

def merge_pdfs(paths, output):
    merger = PdfMerger()
    for pdf in paths:
        merger.append(pdf)
    merger.write(output)
    merger.close()

paths = ['/path/to/file1.pdf', '/path/to/file2.pdf']
output = '/path/to/merged.pdf'
merge_pdfs(paths, output)

Split PDF Files

from PyPDF2 import PdfReader, PdfWriter

def split_pdf(input_path, start_page, end_page, output_path):
    with open(input_path, 'rb') as file:
        pdf = PdfReader(file)
        writer = PdfWriter()
        for i in range(start_page - 1, end_page):
            writer.add_page(pdf.pages[i])
        with open(output_path, 'wb') as output:
            writer.write(output)

input_path = '/path/to/input.pdf'
start_page = 1
end_page = 5
output_path = '/path/to/output.pdf'
split_pdf(input_path, start_page, end_page, output_path)

Encrypt PDF Files

from PyPDF2 import PdfWriter, PdfReader

def encrypt_pdf(input_path, output_path, password):
    with open(input_path, 'rb') as file:
        pdf = PdfReader(file)
        writer = PdfWriter()
        for page in pdf.pages:
            writer.add_page(page)
        writer.encrypt(password)
        with open(output_path, 'wb') as output:
            writer.write(output)

input_path = '/path/to/input.pdf'
output_path = '/path/to/encrypted.pdf'
password = 'mysecretpassword'
encrypt_pdf(input_path, output_path, password)

Decrypt PDF Files

from PyPDF2 import PdfReader, PdfWriter

def decrypt_pdf(input_path, output_path, password):
    with open(input_path, 'rb') as file:
        pdf = PdfReader(file)
        if not pdf.is_encrypted or pdf.decrypt(password) == 0:
            raise ValueError("Password incorrect or file not encrypted.")
        writer = PdfWriter()
        for page in pdf.pages:
            writer.add_page(page)
        with open(output_path, 'wb') as output:
            writer.write(output)

input_path = '/path/to/encrypted.pdf'
output_path = '/path/to/decrypted.pdf'
password = 'mysecretpassword'
decrypt_pdf(input_path, output_path, password)

Extract Text from PDF

from PyPDF2 import PdfReader

def extract_text_from_pdf(pdf_path):
    with open(pdf_path, 'rb') as file:
        pdf = PdfReader(file)
        text = ''
        for page in pdf.pages:
            text += page.extract_text()
    return text

pdf_path = '/path/to/input.pdf'
text = extract_text_from_pdf(pdf_path)
print(text)

Add Text to a PDF Page

from PyPDF2 import PdfWriter, PdfReader
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
import io

def add_text_to_pdf(pdf_path, output_path, text, x, y):
    packet = io.BytesIO()
    can = canvas.Canvas(packet, pagesize=letter)
    can.drawString(x, y, text)
    can.save()
    packet.seek(0)
    new_pdf = PdfReader(packet)
    existing_pdf = PdfReader(open(pdf_path, "rb"))
    output = PdfWriter()
    page = existing_pdf.pages[0]
    page.merge_page(new_pdf.pages[0])
    output.add_page(page)
    outputStream = open(output_path, "wb")
    output.write(outputStream)
    outputStream.close()

pdf_path = '/path/to/input.pdf'
output_path = '/path/to/output_with_text.pdf'
text = 'This is some text.'
x = 50
y = 750
add_text_to_pdf(pdf_path, output_path, text, x, y)

Add Watermark to PDF

from PyPDF2 import PdfReader, PdfWriter
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter

def add_watermark(input_pdf, output_pdf, watermark_text):
    watermark = canvas.Canvas("/tmp/watermark.pdf", pagesize=letter)
    watermark.saveState()
    watermark.setFont("Helvetica", 80)
    watermark.rotate(45)
    watermark.setFillAlpha(0.1)
    watermark.drawString(150, 300, watermark_text)
    watermark.restoreState()
    watermark.save()
    watermark_pdf = PdfReader(open("/tmp/watermark.pdf", "rb"))
    input_pdf = PdfReader(open(input_pdf, "rb"))
    output_pdf = PdfWriter()
    watermark_page = watermark_pdf.pages[0]
    for page in input_pdf.pages:
        page.merge_page(watermark_page)
        output_pdf.add_page(page)
    outputStream = open(output_pdf, "wb")
    output_pdf.write(outputStream)
    outputStream.close()

input_pdf = '/path/to/input.pdf'
output_pdf = '/path/to/output_with_watermark.pdf'
watermark_text = 'Confidential'
add_watermark(input_pdf, output_pdf, watermark_text)

Delete PDF Pages

from PyPDF2 import PdfReader, PdfWriter

def remove_pages(input_pdf, output_pdf, page_numbers):
    input_pdf = PdfReader(open(input_pdf, "rb"))
    output_pdf = PdfWriter()
    for i, page in enumerate(input_pdf.pages):
        if i + 1 not in page_numbers:
            output_pdf.add_page(page)
    outputStream = open(output_pdf, "wb")
    output_pdf.write(outputStream)
    outputStream.close()

input_pdf = '/path/to/input.pdf'
output_pdf = '/path/to/output_without_pages.pdf'
page_numbers = [1, 3]  # Pages to remove
remove_pages(input_pdf, output_pdf, page_numbers)

Rotate PDF Pages

from PyPDF2 import PdfReader, PdfWriter

def rotate_pages(input_pdf, output_pdf, page_numbers, angle):
    input_pdf = PdfReader(open(input_pdf, "rb"))
    output_pdf = PdfWriter()
    for i, page in enumerate(input_pdf.pages):
        if i + 1 in page_numbers:
            page.rotate(angle)
        output_pdf.add_page(page)
    outputStream = open(output_pdf, "wb")
    output_pdf.write(outputStream)
    outputStream.close()

input_pdf = '/path/to/input.pdf'
output_pdf = '/path/to/output_rotated.pdf'
page_numbers = [2, 4]  # Pages to rotate
angle = 90  # Rotation angle (90, 180, 270)
rotate_pages(input_pdf, output_pdf, page_numbers, angle)

Convert HTML to PDF

from weasyprint import HTML

def html_to_pdf(html_path, output_path):
    HTML(html_path).write_pdf(output_path)

html_path = '/path/to/input.html'
output_path = '/path/to/output.pdf'
html_to_pdf(html_path, output_path)