def genBook(self, outputFile=None):
'''
generate booklet
'''
args = self.__inArgs
if args.scanRotateAngle:
self.objs = list(page_per_xobj(self.objs))
self.rotate(int(args.scanRotateAngle))
# self.modify('0-', self.splitPage)
# self.__needFlatten = 1
# obj = self.objs.pop(0)
# self.objs.append(obj)
self.__gen = 1
if args.organizePages:
self.organize(args.organizePages)
self.__gen = 1
if args.insertPage:
self.attach(args.insertPage, self.__blank)
self.__needFlatten = 1
self.__gen = 1
if args.vCutPage:
self.modify(args.vCutPage, self.splitPage)
self.__needFlatten = 1
self.__gen = 1
if self.__needFlatten:
self.flatten()
# if args.group:
# self.group(args.group)
if args.bookletSize:
self.booklet()
self.__gen = 1
if self.__gen and outputFile is None:
outputFile = os.path.splitext(
args.inputFilePath)[0] + '_booklet' + '.pdf'
PdfWriter(outputFile).addpages(self.objs).write()
def retrieve_images_into_pdf():
if pfile == "": # or pfile.endswith(".pdf"):
messagebox.showerror("File Error-> Not PDF","Please select PDF file")
else:
from pdfrw import PdfReader, PdfWriter
from pdfrw.findobjs import page_per_xobj
ofile = 'extract.' + os.path.basename(pfile)
pages = list(page_per_xobj(PdfReader(pfile).pages, margin=0.5*72))
if not pages:
raise IndexError("No XObjects found")
writer = PdfWriter(ofile)
writer.addpages(pages)
writer.write()
messagebox.showinfo("Images retrieved","All images saved in '{0}'".format(ofile))
def extract_first_page(fname):
# create a temporary PDF file
path_tmpfile = os.path.join(tempfile.gettempdir(), os.path.basename(fname))
# extract all elements from the PDF and put them on separate pages
pdf_reader = PdfReader(fname).pages
pages = list(page_per_xobj(pdf_reader))
# write to temp file
writer = PdfWriter(path_tmpfile)
writer.addpages(pages)
writer.write()
return path_tmpfile
#!/usr/bin/env python
'''
usage: extract.py <some.pdf>
Locates Form XObjects and Image XObjects within the PDF,
and creates a new PDF containing these -- one per page.
Resulting file will be named extract.<some.pdf>
'''
import sys
import os
from pdfrw import PdfReader, PdfWriter
from pdfrw.findobjs import page_per_xobj
inpfn, = sys.argv[1:]
outfn = 'pdf_' + os.path.basename(inpfn)
pages = list(page_per_xobj(PdfReader(inpfn).pages, margin=0.5*72))
pages = pages[1::2]
if not pages:
raise IndexError("No XObjects found")
writer = PdfWriter(outfn)
writer.addpages(pages)
writer.write()
#!/usr/bin/env python
'''
usage: extract.py <some.pdf>
Locates Form XObjects and Image XObjects within the PDF,
and creates a new PDF containing these -- one per page.
Resulting file will be named extract.<some.pdf>
'''
import sys
import os
from pdfrw import PdfReader, PdfWriter
from pdfrw.findobjs import page_per_xobj
inpfn, = sys.argv[1:]
outfn = 'extract.' + os.path.basename(inpfn)
pages = list(page_per_xobj(PdfReader(inpfn).pages, margin=0.5*72))
if not pages:
raise IndexError("No XObjects found")
writer = PdfWriter()
writer.addpages(pages)
writer.write(outfn)
Locates Form XObjects and Image XObjects within the PDF,
and creates a new PDF containing these -- one per page.
Resulting file will be named extract.<some.pdf>
'''
import sys
import os
# --- Add pdfrw module to Python path ---
currentdir = os.path.dirname(os.path.realpath(__file__))
parentdir = os.path.dirname(currentdir)
sys.path.insert(0, parentdir)
# --- Import pdrfw stuff ---
from pdfrw import PdfReader, PdfWriter
from pdfrw.findobjs import page_per_xobj
# --- Main ---
inpfn, = sys.argv[1:]
outfn = 'extract.' + os.path.basename(inpfn)
# pages = list(page_per_xobj(PdfReader(inpfn).pages, margin=0.5*72))
pages = list(page_per_xobj(PdfReader(inpfn).pages))
if not pages:
raise IndexError("No XObjects found")
writer = PdfWriter(outfn)
writer.addpages(pages)
writer.write()