def __pdf_meta_writer(self):
if os.path.isfile(self.source_file):
with open(self.source_file, "rb") as input_file:
fileinput = PdfFileReader(input_file)
output = PdfFileWriter()
meta_data = output._info.getObject()
meta_data.update({
NameObject("/Title"): createStringObject(self.title),
NameObject("/Author"): createStringObject(self.author),
NameObject("/Subject"): createStringObject(self.subject),
NameObject("/Keywords"): createStringObject(self.keywords)
})
for page in range(fileinput.getNumPages()):
output.addPage(fileinput.getPage(page))
with file(self.temp_file_path, "wb") as output_stream:
output.write(output_stream)
output_stream.close()
input_file.close()
self.__file_replacement()
self.__fast_web_view()
else:
broken_file_path = str("File: %s not found!!!" % self.source_file)
self.trigger.emit(broken_file_path)
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 setMetadata(self, metadata):
"""Returns a document with new metadata.
Keyword arguments:
metadata -- expected an dictionary with metadata.
"""
# TODO: date as "D:20090401124817-04'00'" ASN.1 for ModDate and CreationDate
input_pdf = PdfFileReader(open(self.document.getUrl(), "rb"))
output_pdf = PdfFileWriter()
modification_date = metadata.pop("ModificationDate", None)
if modification_date:
metadata['ModDate'] = modification_date
if type(metadata.get('Keywords', None)) is list:
metadata['Keywords'] = metadata['Keywords'].join(' ')
args = {}
for key, value in list(metadata.items()):
args[NameObject('/' + key.capitalize())] = createStringObject(value)
output_pdf._info.getObject().update(args)
for page_num in range(input_pdf.getNumPages()):
output_pdf.addPage(input_pdf.getPage(page_num))
output_stream = io.BytesIO()
output_pdf.write(output_stream)
return output_stream.getvalue()
def save(self, filename):
temps = []
for (i,page) in zip(self.mypages, self.pages):
for j, section in enumerate(page.get_sections()):
sys.stdout.write("\rWriting Image for page %d/%d, section %d/%d "%(i+1, len(self.pages), j+1, len(page.get_sections())))
sys.stdout.flush()
sectionfile = tempfile.NamedTemporaryFile(suffix='.png')
temps.append(sectionfile)
(x,y,w,h) = section
pagefn = "%s[%d]"%(self.original, i)
density = 300
x = int(x*density / 72)
y = int(y*density / 72)
w = int(w*density / 72)
h = int(h*density / 72)
execute(["convert", "-density", str(density), pagefn, "-crop", '%dx%d%+d%+d'%(w,h,x,y), '-trim', '+repage', '-trim', sectionfile.name])
sys.stdout.write("\n")
sys.stdout.flush()
sections = temps
midfile = 'x.pdf'
execute(["convert"] + [f.name for f in sections] + [midfile])
for f in sections:
f.close()
output = PdfFileWriter()
infoDict = output._info.getObject()
infoDict.update({
NameObject('/Title'): createStringObject(self.info.get('title', "david")),
NameObject('/Author'): createStringObject(self.info.get('author', ""))
})
input1 = PdfFileReader(file(midfile, "rb"))
for pn in range(input1.getNumPages()):
output.addPage(input1.getPage(pn))
outputStream = file(outfile, "wb")
output.write(outputStream)
outputStream.close()
execute(['rm', midfile])
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 modifyMeta(pathFile, fileNameInput, fileNameOutput, metaInfo):
# There is no interface through pyPDF with which to set this other then getting
# your hands dirty like so:
inputFile = os.path.join(pathFile,fileNameInput)
outputFile = os.path.join(pathFile,fileNameOutput)
print outputFile
output = PdfFileWriter()
infoDict = output._info.getObject()
"""
infoDict.update({
NameObject('/Title'): createStringObject(u'title'),
NameObject('/Author'): createStringObject(u'author'),
NameObject('/Subject'): createStringObject(u'subject'),
NameObject('/Creator'): createStringObject(u'a script'),
NameObject('/Producer'): createStringObject(u'producer')
})
"""
#Se borra Producer, que tiene valor por defecto
infoDict.update({
NameObject('/Producer'): createStringObject(u'')
})
#Asignamos valores pasados por parametro
for metaName in metaInfo.keys():
infoDict.update({
NameObject(metaName): createStringObject(metaInfo.get(metaName))
})
pdfFile = PdfFileReader(file(inputFile, 'rb'))
for page in range(pdfFile.getNumPages()):
output.addPage(pdfFile.getPage(page))
outputStream = file(outputFile, 'wb')
output.write(outputStream)
outputStream.close()
def __modifyData(self):
for data in self.dataToUpdate:
self.dataToUpdate[data] = createStringObject(('<h1 onmouseover=alert(1)>').encode('ascii'))
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()
