Extract pictures from Word and Excel with Python

Question

I was searching for a way to strip out pictures from these file types and this is the solution I came up with. It iterates through a given directory structure, copies any files

Answer 1

Excel files are in the form of zip file.It is easy to extract images from excel or docx file:

import zipfile
from PIL import Image, ImageFilter
import io

blur = ImageFilter.GaussianBlur(40)

def redact_images(filename,FilePath):
    outfile = filename.replace(".xlsx", "_redacted.xlsx")
    with zipfile.ZipFile(filename) as inzip:
        with zipfile.ZipFile(outfile, "w") as outzip:
            i = 0
            for info in inzip.infolist():
                name = info.filename
                content = inzip.read(info)
                if name.endswith((".png", ".jpeg", ".gif")):
                        fmt = name.split(".")[-1]
                        Name = name.split("/")[-1]
                        img = Image.open(io.BytesIO(content))
                        img.save(FilePath + str(Name))
                        outb = io.BytesIO()
                        img.save(outb, fmt)
                        content = outb.getvalue()
                        info.file_size = len(content)
                        info.CRC = zipfile.crc32(content)
                        i += 1
                outzip.writestr(info, content)

filename : Location of input excel file

FilePath : Location to save extracted images