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

0 vote247 views2 answers
Pip config proxy
Python
0 vote248 views1 answer
Default dictionary value
Python
1 vote250 views1 answer
Remove columns that contain certain names in pandas
Python
0 vote256 views1 answer
Django button
Python
0 vote278 views1 answer
Numpy how to dropzero
Python
1 vote339 views1 answer
Sum values in django models
Python Django
11 votes237 views3 answers
__name__== __main__ in python
Python
1 vote255 views1 answer
Python singleton
Python
4 votes259 views1 answer
Get current url python
Python
0 vote245 views1 answer
Dict map()
Python