Explore PDF parsing features of PyMuPDF like extracting text, images & tables from PDF, inserting text into PDF or text recognition using OCR etc. Check https://products.documentprocessing.com/parser/python/pymupdf/ for more details.

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

# Import PyMuPDF
import fitz

# File path you want to extract images from
file = "data.pdf"

# Open the file
pdf_file = fitz.open(file)

# Iterate over PDF pages
for page_index in range(len(pdf_file)):
    # Get the page itself
    page = pdf_file[page_index]

    # Get the image list for the page
    image_list = page.get_images(full=True)

    # Printing the number of images found on this page
    if image_list:
        print(f"[+] Found a total of {len(image_list)} images in page {page_index + 1}")
    else:
        print("[!] No images found on page", page_index + 1)

    # Extract images from the page
    for image_index, img in enumerate(image_list, start=1):
        xref = img[0]
        base_image = pdf_file.extract_image(xref)
        image_bytes = base_image["image"]
        image_ext = base_image["ext"]

        # Save the image to a file
        image_filename = f"page_{page_index + 1}_image_{image_index}.{image_ext}"
        with open(image_filename, "wb") as img_file:
            img_file.write(image_bytes)

# Close the PDF document
pdf_file.close()

extract-tables-from-pdf-in-python-using-pymupdf-library.py

# import package PyMuPDF
import fitz  

# Open some document, for example a PDF (could also be EPUB, XPS, etc.)
doc = fitz.open("table_handling_example.pdf")

# Load a desired page. This works via 0-based numbers
page = doc[0]

# Look for tables on this page and display the table count
tabs = page.find_tables()
print(f"{len(tabs.tables)} table(s) on {page}")

# Select the first table
tab = tabs[0]

df = tab.to_pandas()
print("Table:")
print(df)

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

# Import PyMuPDF
import fitz  

# Open a PDF file
pdf_document = "documentprocessing.pdf"
doc = fitz.open(pdf_document)

# Initialize an empty string to store extracted text
extracted_text = ""

# Iterate through each page and extract text
for page_num in range(doc.page_count):
    page = doc[page_num]
    extracted_text += page.get_text()
    
# Close the PDF document
doc.close()

# Perform text analysis (e.g., count words)
word_count = len(extracted_text.split())
print(f"The Extracted text is as follows:\n{extracted_text}")
print(f"Total words in the document: {word_count}")

insert-text-into-pdf-in-python-using-pymupdf-library.py

# Import PyMuPDF
import fitz

# Open a PDF file
doc = fitz.open("documentprocessing.pdf")
page = doc[0]  # Access the first page

# Define the starting point for the text
p = fitz.Point(75, 150)

# Define the text to be inserted
text = "Some text,\nspread across\nseveral lines."

# Insert the text on the page
rc = page.insert_text(p, text)

# Print the number of lines printed on the page
print("%i lines printed on page %i." % (rc, page.number))

# Save the modified PDF to a new file
doc.save("text.pdf")

pdf-text-recognition-in-python-using-pymupdf-library.py

# Import PyMuPDF
import fitz
import os

# Set the TESSDATA_PREFIX environment variable to the folder containing the language file
os.environ['TESSDATA_PREFIX'] = 'F://'

# Open the PDF file
pdf_document = fitz.open('data.pdf')

# Get the page from the PDF document
page_number = 1
page = pdf_document[page_number - 1]

# Perform OCR using get_textpage_ocr
textpage_ocr = page.get_textpage_ocr(flags=3, language='eng', dpi=72, full=False, tessdata=None)

# Extract text from the OCR result
text = textpage_ocr.extractText()

# Print the OCR result
print(text)

# Close the PDF document
pdf_document.close()