Best Python PDF Library for Working with PDFs

best-python-pdf-library.md

Explore the Best Python PDF Library for Working with PDFs

best-python-pdf-library_add_text.py

import aspose.pdf as ap

# Open an existing PDF
document = ap.Document("CreatePDF.pdf")

# Get the first page
page = document.pages[1]  # 1-based indexing

# Add new text to the page
text_fragment = ap.text.TextFragment("This text was added programmatically!")
text_fragment.position = ap.text.Position(100, 700)
text_fragment.text_state.font_size = 12
text_fragment.text_state.font = ap.text.FontRepository.find_font("Times New Roman")
page.paragraphs.add(text_fragment)

# Save the modified document
document.save("AddText.pdf")

best-python-pdf-library_create_pdf.py

import aspose.pdf as ap

# Create a new document
document = ap.Document()

# Add a page
page = document.pages.add()

# Add text to the page
text_fragment = ap.text.TextFragment("Hello, Aspose.PDF for Python!")
text_fragment.position = ap.text.Position(100, 600)
text_fragment.text_state.font_size = 14
text_fragment.text_state.font = ap.text.FontRepository.find_font("Arial")
text_fragment.text_state.foreground_color = ap.Color.blue

# Add the text fragment to the page
page.paragraphs.add(text_fragment)

# Add a table
table = ap.Table()
table.column_widths = "100 100 100"
table.default_cell_border = ap.BorderInfo(ap.BorderSide.ALL, 0.5, ap.Color.black)
table.default_cell_padding = ap.MarginInfo(5, 5, 5, 5)

# Add rows and cells
row = table.rows.add()
cell = row.cells.add("Product")
cell = row.cells.add("Quantity")
cell = row.cells.add("Price")

row = table.rows.add()
cell = row.cells.add("Widget A")
cell = row.cells.add("10")
cell = row.cells.add("$5.99")

row = table.rows.add()
cell = row.cells.add("Widget B")
cell = row.cells.add("5")
cell = row.cells.add("$10.99")

# Add the table to the page
page.paragraphs.add(table)

# Save the document
document.save("CreatePDF.pdf")

best-python-pdf-library_extract_text.py

import aspose.pdf as ap

# Open PDF document
document = ap.Document("AddText.pdf")

textAbsorber = ap.text.TextAbsorber()

document.pages.accept(textAbsorber)

extractedText = textAbsorber.text

# Show the output
print(extractedText)

best-python-pdf-library_insert_image.py

import aspose.pdf as ap

# Open an existing PDF
document = ap.Document("CreatePDF.pdf")

# Get the first page
page = document.pages[1]  # 1-based indexing

# Insert an image
image = ap.Image()
image.file = "aspose-logo.png"
image.fix_width = 400
image.fix_height = 100
page.paragraphs.add(image)

# Save the modified document
document.save("InsertImage.pdf")

best-python-pdf-library_pdf_to_excel.py

import aspose.pdf as ap

input_pdf = DIR_INPUT + "sample.pdf"
output_pdf =  DIR_OUTPUT + "convert_pdf_to_xlsx.xlsx"

# Open PDF document
document = ap.Document(input_pdf)

# Create save options
save_option = ap.ExcelSaveOptions()

# Save the file into XLSX
document.save(output_pdf, save_option)

best-python-pdf-library_pdf_to_html.py

import aspose.pdf as ap

input_pdf = DIR_INPUT + "sample.pdf"
output_pdf = DIR_OUTPUT + "pdf_to_html.html"

# Load PDF document
document = ap.Document(input_pdf)

# Save PDF in HTML format
save_options = ap.HtmlSaveOptions()
document.save(output_pdf, save_options)

best-python-pdf-library_pdf_to_word.py

import aspose.pdf as ap

# Load the PDF document
pdf_document = ap.Document("document.pdf")

# Convert to DOCX (Word)
save_options = ap.DocSaveOptions()
save_options.format = ap.DocSaveOptions.DocFormat.DOC_X

# Save the modified document
pdf_document.save("output.docx", save_options)

best-python-pdf-library_secure_pdf.py

# Load the PDF document
document = ap.Document("document.pdf")

# Instantiate Document Privileges object
# Apply restrictions on all privileges
documentPrivilege = ap.facades.DocumentPrivilege.forbid_all

# Only allow screen reading
documentPrivilege.allow_screen_readers = True

# Encrypt the file with User and Owner password
# Need to set the password, so that once the user views the file with user password
# Only screen reading option is enabled
document.encrypt("user", "owner", documentPrivilege, ap.CryptoAlgorithm.RC4X128, False)

# Save the encrypted document
document.save("secured_document.pdf")