Extract image from pdf python

import PyPDF2

from PIL import Image

if __name__ == '__main__':
    input1 = PyPDF2.PdfFileReader(open("input.pdf", "rb"))
    page0 = input1.getPage(0)
    xObject = page0['/Resources']['/XObject'].getObject()

    for obj in xObject:
        if xObject[obj]['/Subtype'] == '/Image':
            size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
            data = xObject[obj].getData()
            if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
                mode = "RGB"
            else:
                mode = "P"

            if xObject[obj]['/Filter'] == '/FlateDecode':
                img = Image.frombytes(mode, size, data)
                img.save(obj[1:] + ".png")
            elif xObject[obj]['/Filter'] == '/DCTDecode':
                img = open(obj[1:] + ".jpg", "wb")
                img.write(data)
                img.close()
            elif xObject[obj]['/Filter'] == '/JPXDecode':
                img = open(obj[1:] + ".jp2", "wb")
                img.write(data)
                img.close()

Source: stackoverflow.com

Similar codes

1 vote291 views2 answers
Python spread operator
Python
8 votes281 views3 answers
Python append csv to dataframe
Python
0 vote287 views1 answer
How to find out the max and min date on the basis of property id in pandas
Python
0 vote279 views1 answer
Tkinter filedialog get directory path
Python
0 vote275 views1 answer
How to check if variable in python is of what kind
Python
13 votes259 views3 answers
Duplicate in list python
Python
0 vote285 views1 answer
201903100110041
Python
0 vote268 views1 answer
Python call function in the same class
Python
8 votes275 views1 answer
ValueError: invalid literal for int() with base 10: site:stackoverflow.com
Python
0 vote264 views1 answer
Pandas convert date to quarter
Python