def editPDF(filename):
""" function to add metadata to pdf files"""
INPUT = filename
OUTPUT = filename[:-4] + '_updated.pdf'
output = PdfFileWriter()
fin = file(INPUT, 'rb')
pdf_in = PdfFileReader(fin)
infoDict = output._info.getObject()
###########################################################
# I've added random tags here, use what needs to be added #
# #
###########################################################
infoDict.update({
NameObject('/Tags'):
createStringObject(tag_dict[filename]),
NameObject('/Keywords'):
createStringObject(tag_dict[filename])
})
for page in range(pdf_in.getNumPages()):
output.addPage(pdf_in.getPage(page))
outputStream = file(os.path.join(directory, OUTPUT), 'wb')
output.write(outputStream)
fin.close()
outputStream.close()
def __iter__(self):
warnings.simplefilter('ignore', DeprecationWarning)
# mostly based on PdfFileWriter.write
# Begin writing, so that, even if _sweepIndirectReferences takes
# a long time, the download begins
object_positions = []
length = 0
s = self._header + "\n"
yield s
length += len(s)
externalReferenceMap = {}
self.set = set()
self._sweepIndirectReferences(externalReferenceMap, self._root)
del self.set
stream = StringIO.StringIO()
for i, obj in enumerate(self._objects):
idnum = (i + 1)
object_positions.append(length)
s1 = str(idnum) + " 0 obj\n"
obj.writeToStream(stream, None)
s2 = stream.getvalue() + "\nendobj\n"
yield s1 + s2
length += len(s1) + len(s2)
stream.reset()
stream.truncate()
# xref table
xref_location = length
yield("xref\n")
yield("0 %s\n" % (len(self._objects) + 1))
yield "0000000000 65535 f \n"
for offset in object_positions:
yield "%010d 00000 n \n" % offset
# trailer
yield("trailer\n")
trailer = DictionaryObject()
trailer.update({
NameObject("/Size"): NumberObject(len(self._objects) + 1),
NameObject("/Root"): self._root,
NameObject("/Info"): self._info,
})
if hasattr(self, "_ID"):
trailer[NameObject("/ID")] = self._ID
if hasattr(self, "_encrypt"):
trailer[NameObject("/Encrypt")] = self._encrypt
trailer.writeToStream(stream, None)
yield stream.getvalue()
# eof
yield("\nstartxref\n%s\n%%%%EOF\n" % (xref_location))
warnings.simplefilter('default', DeprecationWarning)
def addCopyrightToPDF(pdf_file_location, pdf_file_destination,copyrightText, drawText=True, title="",authors=""):
packet = StringIO.StringIO()
# create a new PDF with Reportlab
can = canvas.Canvas(packet, pagesize=letter)
can.setFont("Times-Roman",7)
ctext = copyrightText.split("\n")
if drawText:
can.drawString(30, 40, ctext[0])
can.drawString(30, 50, ctext[1])
else:
can.drawString(30, 50, "")
can.save()
#move to the beginning of the StringIO buffer
packet.seek(0)
new_pdf = PdfFileReader(packet)
# read your existing PDF
existing_pdf = PdfFileReader(file(pdf_file_location, "rb"))
output = PdfFileWriter()
npagesorig = existing_pdf.getNumPages()
#print npagesorig
for i in range(npagesorig):
page = existing_pdf.getPage(i)
# if last page
if i == (npagesorig-1):
#print "HERE",copyrightText,drawText
page.mergePage(new_pdf.getPage(0))
output.addPage(page)
infoDict = output._info.getObject()
infoDict.update({
NameObject('/Title'): createStringObject(title),
NameObject('/Author'): createStringObject(authors)
})
# finally, write "output" to a real file
outputStream = file(pdf_file_destination, "wb")
output.write(outputStream)
outputStream.close()
def replace_text(cls, page, text, replace):
# HACK
from pyPdf.pdf import ContentStream, PageObject
from pyPdf.generic import TextStringObject, NameObject
content = ContentStream(page["/Contents"].getObject(), page.pdf)
for idx in range(len(content.operations)):
operands, operator = content.operations[idx]
if operator == 'Tj':
operands[0] = TextStringObject(operands[0].replace(
text, replace))
new_page = PageObject.createBlankPage(page.pdf)
new_page.mergePage(page)
new_page[NameObject('/Contents')] = content
return new_page
def pdf_add_content(content_string, page, scale=1, offsetx=0, offsety=0):
"""Add content to the end of the content stream of the PDF page.
Inputs: content_string The PDF drawing commands to add, as a single string.
page The pyPdf.pdf.PageObject to add the content to.
scale Before adding the content, adjust the the coordinate
offsetx system with a (uniform) scale factor and a
offsety translation of offsetx and offsety.
"""
coord_trans = '%.2f 0 0 %.2f %.2f %.2f cm' % (scale, scale, offsetx,
offsety)
commands = '\n'.join(('Q', 'q', coord_trans, content_string, 'Q'))
try:
orig_content = page['/Contents'].getObject()
except KeyError:
orig_content = ArrayObject([])
stream = ContentStream(orig_content, page.pdf)
stream.operations.insert(0, [[], 'q']) # Existing content may not restore
stream.operations.append([[], commands]) # graphics state at the end.
page[NameObject('/Contents')] = stream
from pyPdf import PdfFileWriter, PdfFileReader
from pyPdf.generic import NameObject, createStringObject
OUTPUT = 'ml1.pdf'
INPUT = 'NOFO.pdf'
# There is no interface through pyPDF with which to set this other then getting
# your hands dirty like so:
output = PdfFileWriter()
fin = file(INPUT, 'rb')
pdf_in = PdfFileReader(fin)
infoDict = output._info.getObject()
print infoDict
infoDict.update({
NameObject('/Title'): createStringObject(u'title'),
NameObject('/Author'): createStringObject(u'author'),
NameObject('/Subject'): createStringObject(u'subject'),
NameObject('/Creator'): createStringObject(u'a script')
})
print infoDict
for page in range(pdf_in.getNumPages()):
output.addPage(pdf_in.getPage(page))
outputStream = file(OUTPUT, 'wb')
output.write(outputStream)
outputStream.close()
from pyPdf import PdfFileReader, PdfFileWriter
pdf = PdfFileReader(open(OUTPUT, 'rb'))
import sys
parser = argparse.ArgumentParser(description=u'Limpia los metadatos de un PDF y opcionalmente añade título y autor')
parser.add_argument("input", help="fichero pdf origen")
parser.add_argument("output", help="fichero pdf destino")
args = parser.parse_args()
fin = file(args.input, 'rb')
pdfIn = PdfFileReader(fin)
pdfOut = PdfFileWriter()
for page in range(pdfIn.getNumPages()):
pdfOut.addPage(pdfIn.getPage(page))
info = pdfOut._info.getObject()
del info[NameObject('/Producer')]
title = raw_input("Titulo:").decode(sys.stdin.encoding)
author = raw_input("Autor:").decode(sys.stdin.encoding)
info.update({
NameObject('/Title'): createStringObject(title),
NameObject('/Author'): createStringObject(author)
})
fout = open(args.output, 'wb')
pdfOut.write(fout)
fin.close()
fout.close()
inpfn = raw_input('Enter PDF path : ')
fin = file(inpfn, 'rb')
pdf_in = PdfFileReader(fin)
writer = PdfFileWriter()
for page in range(pdf_in.getNumPages()):
writer.addPage(pdf_in.getPage(page))
infoDict = writer._info.getObject()
info = pdf_in.documentInfo
for key in info:
infoDict.update({NameObject(key): createStringObject(info[key])})
# add the grade
list_of_data_to_delete = [
'/CreationDate', '/Author', '/Creator', '/ModDate', '/Producer', '/Title'
]
for item in list_of_data_to_delete:
try:
infoDict.update({NameObject(item): createStringObject(u'')})
except:
print("can't delete : ", i)
fout = open('outputFile.pdf', 'wb')
writer.write(fout)
fin.close()