This is a professional solution to compress PDF using Python. Use our PDF optimization API to develop high-level, platform-independent software in Python. Try it online for free!
This Python library provides developers with the ability to quickly and efficiently compress PDF documents programmatically. Easily get optimized PDF output ready for printing, archiving or sharing over the network. It is a standalone PDF document processing solution for Python that does not require any third party software to be installed.
Our product provides Python developers with an integrated API to reduce the size of PDF files. PDF compression is performed in two passes. During the first pass, all pages of the PDF are converted to image format. Our product uses adaptive and highly efficient image compression algorithms that allow developers to get compact PDF output while maintaining the optimal quality of the document. On the next pass, the sequence of images is compressed and combined to form the content of a new, optimized PDF file.
PDF compression made easy with 'Aspose.Words for Python via .NET'. The following example demonstrates how reduce the size of a PDF file in Python:
pip install aspose-words
import aspose.words as aw
renderer = aw.pdf2word.fixedformats.PdfFixedRenderer()
pdf_read_options = aw.pdf2word.fixedformats.PdfFixedOptions()
pdf_read_options.image_format = aw.pdf2word.fixedformats.FixedImageFormat.JPEG
pdf_read_options.jpeg_quality = 50
with open ("Input.pdf", 'rb') as pdf_stream:
pages_stream = renderer.save_pdf_as_images(pdf_stream, pdf_read_options);
builder = aw.DocumentBuilder()
for i in range(0, len(pages_stream)):
# Set maximum page size to avoid the current page image scaling.
max_page_dimension = 1584
page_setup = builder.page_setup
set_page_size(page_setup, max_page_dimension, max_page_dimension)
page_image = builder.insert_image(pages_stream[i])
set_page_size(page_setup, page_image.width, page_image.height)
page_setup.top_margin = 0
page_setup.left_margin = 0
page_setup.bottom_margin = 0
page_setup.right_margin = 0
if i != len(pages_stream) - 1:
builder.insert_break(aw.BreakType.SECTION_BREAK_NEW_PAGE)
save_options = aw.saving.PdfSaveOptions()
save_options.cache_background_graphics = true
builder.document.save("Output.pdf", save_options)
def set_page_size(page_setup, width, height):
page_setup.page_width = width;
page_setup.page_height = height;
import aspose.words as aw
doc = aw.Document("Input.pdf")
doc.cleanup()
shapes = [node.as_shape() for node in doc.get_child_nodes(aw.NodeType.SHAPE, True)]
for shape in shapes:
if shape.isImage:
# It's up to developer to choose the library for image compression.
image = Image.open(shape.image_data.to_stream())
# ...
# Compress image and set it back to the shape.
shape.image_data.set_image("yourCompressedImage")
save_options = aw.saving.PdfSaveOptions
save_options.cache_background_graphics = true
doc.save("Output.pdf", save_options)
import aspose.words as aw
doc = aw.Document("Input.pdf")
doc.cleanup()
shapes = [node.as_shape() for node in doc.get_child_nodes(aw.NodeType.SHAPE, True)]
for shape in shapes:
if shape.isImage:
# It's up to developer to choose the library for image compression.
image = Image.open(shape.image_data.to_stream())
# ...
# Compress image and set it back to the shape.
shape.image_data.set_image("yourCompressedImage")
doc.save("Output.pdf")
import aspose.words as aw
doc = aw.Document("Input.pdf")
doc.cleanup()
shapes = [node.as_shape() for node in doc.get_child_nodes(aw.NodeType.SHAPE, True)]
for shape in shapes:
if shape.isImage:
# It's up to developer to choose the library for image compression.
image = Image.open(shape.image_data.to_stream())
# ...
# Compress image and set it back to the shape.
shape.image_data.set_image("yourCompressedImage")
save_options = aw.saving.OoxmlSaveOptions
save_options.compression_level = aw.saving.CompressionLevel.MAXIMUM
doc.save("Output.pdf", save_options)
import aspose.words as aw
doc = aw.Document()
builder = aw.DocumentBuilder(doc)
shape = builder.InsertImage("Input.pdf")
save_options = aw.saving.ImageSaveOptions(aw.SaveFormat.PDF)
shape.get_shape_renderer().save("Output.pdf", save_options)
import aspose.words as aw
renderer = aw.pdf2word.fixedformats.PdfFixedRenderer()
pdf_read_options = aw.pdf2word.fixedformats.PdfFixedOptions()
pdf_read_options.image_format = aw.pdf2word.fixedformats.FixedImageFormat.JPEG
pdf_read_options.jpeg_quality = 50
with open ("Input.pdf", 'rb') as pdf_stream:
pages_stream = renderer.save_pdf_as_images(pdf_stream, pdf_read_options);
builder = aw.DocumentBuilder()
for i in range(0, len(pages_stream)):
# Set maximum page size to avoid the current page image scaling.
max_page_dimension = 1584
page_setup = builder.page_setup
set_page_size(page_setup, max_page_dimension, max_page_dimension)
page_image = builder.insert_image(pages_stream[i])
set_page_size(page_setup, page_image.width, page_image.height)
page_setup.top_margin = 0
page_setup.left_margin = 0
page_setup.bottom_margin = 0
page_setup.right_margin = 0
if i != len(pages_stream) - 1:
builder.insert_break(aw.BreakType.SECTION_BREAK_NEW_PAGE)
save_options = aw.saving.PdfSaveOptions()
save_options.cache_background_graphics = true
builder.document.save("Output.pdf", save_options)
def set_page_size(page_setup, width, height):
page_setup.page_width = width;
page_setup.page_height = height;
We host our Python packages in PyPi repositories. Please follow the step-by-step instructions on how to install "Aspose.Words for Python via .NET" to your developer environment.
This package is compatible with Python ≥3.5 and <3.12. If you develop software for Linux, please have a look at additional requirements for gcc and libpython in Product Documentation.
You can optimize files in many other file formats: