Cropping pages of a .pdf file
Use this to get the dimension of pdf
from PyPDF2 import PdfWriter, PdfReader, PdfMerger
reader = PdfReader("/Users/user.name/Downloads/sample.pdf")
page = reader.pages[0]
print(page.cropbox.lower_left)
print(page.cropbox.lower_right)
print(page.cropbox.upper_left)
print(page.cropbox.upper_right)
After this get page reference and then apply crop command
page.mediabox.lower_right = (lower_right_new_x_coordinate, lower_right_new_y_coordinate)
page.mediabox.lower_left = (lower_left_new_x_coordinate, lower_left_new_y_coordinate)
page.mediabox.upper_right = (upper_right_new_x_coordinate, upper_right_new_y_coordinate)
page.mediabox.upper_left = (upper_left_new_x_coordinate, upper_left_new_y_coordinate)
#f or example :- my custom coordinates
# page.mediabox.lower_right = (611, 500)
# page.mediabox.lower_left = (0, 500)
# page.mediabox.upper_right = (611, 700)
# page.mediabox.upper_left = (0, 700)
pyPdf does what I expect in this area. Using the following script:
#!/usr/bin/python
#
from pyPdf import PdfFileWriter, PdfFileReader
with open("in.pdf", "rb") as in_f:
input1 = PdfFileReader(in_f)
output = PdfFileWriter()
numPages = input1.getNumPages()
print "document has %s pages." % numPages
for i in range(numPages):
page = input1.getPage(i)
print page.mediaBox.getUpperRight_x(), page.mediaBox.getUpperRight_y()
page.trimBox.lowerLeft = (25, 25)
page.trimBox.upperRight = (225, 225)
page.cropBox.lowerLeft = (50, 50)
page.cropBox.upperRight = (200, 200)
output.addPage(page)
with open("out.pdf", "wb") as out_f:
output.write(out_f)
The resulting document has a trim box that is 200x200 points and starts at 25,25 points inside the media box. The crop box is 25 points inside the trim box.
Here is how my sample document looks in acrobat professional after processing with the above code:
This document will appear blank when loaded in acrobat reader.