Add and extract annotations from PDF documents using pypdf library. Check https://products.documentprocessing.com/annotation/python/pypdf/ for more details.

add-link-annotation-to-pdf-using-pypdf-library.py

# Import necessary classes and modules from the pypdf library
from pypdf import PdfReader, PdfWriter
from pypdf.annotations import Link, Rectangle

# Read the existing PDF file named "documentprocessing.pdf"
reader = PdfReader("documentprocessing.pdf")

# Get the first page of the PDF
page = reader.pages[0]

# Create a new PDF writer
writer = PdfWriter()

# Add the read page to the new PDF writer
writer.add_page(page)

# Create a Link annotation
annotation = Link(
  
    # Provide the URL
    url="https://example.com/",
  
    #Provide the size and coordinates for the link annotation
    rect=(50, 600, 200, 650),
)

# Create a Rectangle annotation
annotation2 = Rectangle(
    rect=(50, 600, 200, 650),
)

# Add the Link and Rectangle annotations to the first page of the new PDF
writer.add_annotation(page_number=0, annotation=annotation)
writer.add_annotation(page_number=0, annotation=annotation2)

# Write the annotated PDF to a new file named "link-annotated-pdf.pdf"
with open("link-annotated-pdf.pdf", "wb") as fp:
    writer.write(fp)

add-rectangle-annotation-to-pdf-using-pypdf-library.py

# Import necessary modules from pypdf library
from pypdf import PdfReader, PdfWriter
from pypdf.annotations import Rectangle

# Read the PDF file using PdfReader
reader = PdfReader("documentprocessing.pdf")

# Get the first page of the PDF
page = reader.pages[0]

# Create a new PdfWriter object to write the modified PDF
writer = PdfWriter()

# Add the page from the original PDF to the new writer
writer.add_page(page)

# Define the rectangle annotation with coordinates (35, 690, 170, 720)
annotation = Rectangle(rect=(35, 690, 170, 720))

# Add the rectangle annotation to the first page of the new PDF
writer.add_annotation(page_number=0, annotation=annotation)

# Write the modified PDF to a new file ("annotated-pdf.pdf")
with open("annotated-pdf.pdf", "wb") as fp:
    writer.write(fp)

add-text-annotation-to-pdf-using-pypdf-library.py

# Import necessary classes and modules from PyPDF library
from pypdf import PdfReader, PdfWriter
from pypdf.annotations import Text

# Open the original PDF file for reading
reader = PdfReader("documentprocessing.pdf")

# Get the first page of the original PDF
page = reader.pages[0]

# Create a new PDF writer object
writer = PdfWriter()

# Add the first page of the original PDF to the new PDF
writer.add_page(page)

# Create a Text annotation with specified text and rectangle coordinates
annotation = Text(
  
    text="Hi there,\nWelcome to DocumentProcessing.com",
  
    rect=(180, 705, 240, 755)
)

# Add the annotation to the first page of the new PDF
writer.add_annotation(page_number=0, annotation=annotation)

# Open the new PDF file for writing in binary mode
with open("annotated.pdf", "wb") as fp:
  
    # Write the content of the new PDF to the file
    writer.write(fp)

extract-annotations-from-pdf-using-pypdf-library.py

# Import necessary modules from pypdf library
from pypdf import PdfReader

# Create a PdfReader object to read the PDF file
reader = PdfReader("documentprocessing.pdf")

# Iterate through all pages in the PDF
for page in reader.pages:
  
    # Check if the page contains annotations ("/Annots" key)
    if "/Annots" in page:
      
        # Iterate through each annotation on the page
        for annot in page["/Annots"]:
          
            # Get the annotation object
            obj = annot.get_object()
            
            # Extract relevant information from the annotation object
            # - "subtype" represents the type of annotation (e.g., text, link)
            # - "location" represents the rectangle coordinates of the annotation
            annotation = {"subtype": obj["/Subtype"], "location": obj["/Rect"]}
            
            # Print the extracted annotation information
            print(annotation)