Extract text, images and attachments from PDF files in Python using pypdf Library. Check https://products.documentprocessing.com/parser/python/pypdf/ for the details.

extract-attachments-from-pdf-in-python-using-pypdf-library.py

# Import the PdfReader class from the pypdf library
from pypdf import PdfReader

# Open a PDF file
reader = PdfReader("data.pdf")

# Iterate through the attachments in the PDF
for name, content_list in reader.attachments:

    # Iterate through the contents in each attachment
    for i, content in enumerate(content_list):

        # Open a new file for writing the attachment content
        with open(f"{name}-{i}", "wb") as fp:
            fp.write(content)

extract-images-from-pdf-in-python-using-pypdf-library.py

# Import the PdfReader class from the pypdf library
from pypdf import PdfReader

# Open the PDF file
reader = PdfReader("data.pdf")

# Initialize a counter to keep track of the extracted images
count = 0

# Iterate through each page in the PDF document
for page in reader.pages:

    # Iterate through the images on the current page
    for image_file_object in page.images:

        # Open and write the image data
        with open(str(count) + image_file_object.name, "wb") as fp:
            fp.write(image_file_object.data)
            count += 1

extract-text-from-pdf-in-python-using-pypdf-library.py

# Import the PdfReader class from the pypdf library
from pypdf import PdfReader

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

# Iterate through all the pages in the PDF document
for i in reader.pages:
    # Extract and print the text content of each page
    print(i.extract_text())