CCITTFaxDecode फ़िल्टर के लिए PyPDF2 के साथ पायथन में:
import PyPDF2
import struct
"""
Links:
PDF format: http://www.adobe.com/content/dam/Adobe/en/devnet/acrobat/pdfs/pdf_reference_1-7.pdf
CCITT Group 4: https://www.itu.int/rec/dologin_pub.asp?lang=e&id=T-REC-T.6-198811-I!!PDF-E&type=items
Extract images from pdf: http://stackoverflow.com/questions/2693820/extract-images-from-pdf-without-resampling-in-python
Extract images coded with CCITTFaxDecode in .net: http://stackoverflow.com/questions/2641770/extracting-image-from-pdf-with-ccittfaxdecode-filter
TIFF format and tags: http://www.awaresystems.be/imaging/tiff/faq.html
"""
def tiff_header_for_CCITT(width, height, img_size, CCITT_group=4):
tiff_header_struct = '<' + '2s' + 'h' + 'l' + 'h' + 'hhll' * 8 + 'h'
return struct.pack(tiff_header_struct,
b'II',
42,
8,
8,
256, 4, 1, width,
257, 4, 1, height,
258, 3, 1, 1,
259, 3, 1, CCITT_group,
262, 3, 1, 0,
273, 4, 1, struct.calcsize(tiff_header_struct),
278, 4, 1, height,
279, 4, 1, img_size,
0
)
pdf_filename = 'scan.pdf'
pdf_file = open(pdf_filename, 'rb')
cond_scan_reader = PyPDF2.PdfFileReader(pdf_file)
for i in range(0, cond_scan_reader.getNumPages()):
page = cond_scan_reader.getPage(i)
xObject = page['/Resources']['/XObject'].getObject()
for obj in xObject:
if xObject[obj]['/Subtype'] == '/Image':
"""
The CCITTFaxDecode filter decodes image data that has been encoded using
either Group 3 or Group 4 CCITT facsimile (fax) encoding. CCITT encoding is
designed to achieve efficient compression of monochrome (1 bit per pixel) image
data at relatively low resolutions, and so is useful only for bitmap image data, not
for color images, grayscale images, or general data.
K < 0 --- Pure two-dimensional encoding (Group 4)
K = 0 --- Pure one-dimensional encoding (Group 3, 1-D)
K > 0 --- Mixed one- and two-dimensional encoding (Group 3, 2-D)
"""
if xObject[obj]['/Filter'] == '/CCITTFaxDecode':
if xObject[obj]['/DecodeParms']['/K'] == -1:
CCITT_group = 4
else:
CCITT_group = 3
width = xObject[obj]['/Width']
height = xObject[obj]['/Height']
data = xObject[obj]._data
img_size = len(data)
tiff_header = tiff_header_for_CCITT(width, height, img_size, CCITT_group)
img_name = obj[1:] + '.tiff'
with open(img_name, 'wb') as img_file:
img_file.write(tiff_header + data)
pdf_file.close()