Python pyPdf.PdfFileWriter类代码示例

def into_half(src, dst):
	_src = file(src, 'rb')
	_dst = file(dst, 'wb')
	
	
	
	input = PdfFileReader(_src)

	output = PdfFileWriter()
	
	for i in range(input.getNumPages()):
		
		p = input.getPage(i)
		q = copy.copy(p)
		q.mediaBox = copy.copy(p.mediaBox)

		#x1, x2 = p.mediaBox.lowerLeft
		#x3, x4 = p.mediaBox.upperRight
		(w, h) = p.mediaBox.upperRight
		
		print w, h
		
		p.mediaBox.upperRight = (w/2, h)
		q.mediaBox.upperLeft = (w/2, h)

		output.addPage(p)
		output.addPage(q)

	output.write(_dst)
	_src.close()
	_dst.close()

    def buildPdf(self):
        to_pdffile = self._takeoff()
        ap_pdffile = self._airplane()
        ck_pdffile = self._checklist()

        output = PdfFileWriter()

        self.addAllPages(output, PdfFileReader(file(ck_pdffile, "rb")))
        self.addAllPages(output, PdfFileReader(file(to_pdffile, "rb")))
        self.addAllPages(output, PdfFileReader(file(ap_pdffile, "rb")))

        # Add AD Info Charts
        files = dict()

        for pdf in self.getExternalPdf(self.eVfrPath, self.__fligthplan.performance_takeoff.aerodrome.code):
            files[pdf] = file(pdf, "rb")
            files["%s_" % pdf] = PdfFileReader(files[pdf])
            if files["%s_" % pdf].getIsEncrypted():
                pdfCracked = PdfCracker().crack(pdf)
                files[pdf]  = file(pdfCracked, "rb")
                files["%s_" % pdf] = PdfFileReader(files[pdf])

            self.addAllPages(output=output, input=files["%s_" % pdf])

        # write out the merged file
        outputPdf = os.path.join(self.outputdir, 'flightplan %s.pdf' % self.__fligthplan.title)
        outputStream = file(outputPdf, "wb")
        output.write(outputStream)
        outputStream.close()

        npyscreen.notify_confirm(
            message="Your pretty Fligthplan has been created at\n\n%s" % outputPdf
        )

    def rewrite(self, context, font={'name': 'Times-Roman', 'size': 11}):

        packet = StringIO.StringIO()
        # create a new PDF with Reportlab
        can = canvas.Canvas(packet, pagesize=letter)
        can.setFont(font['name'], font['size'])
        for i in context:
            can.drawString(i['x'], i['y'], i['value'])
        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(self.path, "rb"))
        output = PdfFileWriter()
        # merge the new file with the existing
        page = existing_pdf.getPage(0)
        page.mergePage(new_pdf.getPage(0))
        output.addPage(page)
        # finally, write "output" to a real file
        outputStream = file(self.destination, "wb")
        output.write(outputStream)
        outputStream.close()

        return True

    def save(self, to):
        origin = self.get_origin()
        
        if not origin:
            raise RuntimeError("Please implement get_origin method or origin attribute")

        try:
            existing_pdf = PdfFileReader(file(origin, "rb"))
        except IOError:
            raise RuntimeError(u"Failed to open origin file")

        output = PdfFileWriter()
                
        for page_id, page_class in enumerate(self.pages):
            new_page = page_class(self.instance).save()
            
            base_page = existing_pdf.getPage(0)
            base_page.mergePage(new_page)
            output.addPage(base_page)

        if isinstance(to, basestring):
            outputStream = file(to, "wb")
        else:
            outputStream = to
        
        output.write(outputStream)
        outputStream.close()

    def add_omr_marks(self, pdf_data, is_latest_document):
        # Documentation
        # http://meteorite.unm.edu/site_media/pdf/reportlab-userguide.pdf
        # https://pythonhosted.org/PyPDF2/PdfFileReader.html
        # https://stackoverflow.com/a/17538003
        # https://gist.github.com/kzim44/5023021
        # https://www.blog.pythonlibrary.org/2013/07/16/
        #   pypdf-how-to-write-a-pdf-to-memory/
        self.ensure_one()

        pdf_buffer = StringIO.StringIO()
        pdf_buffer.write(pdf_data)

        existing_pdf = PdfFileReader(pdf_buffer)
        output = PdfFileWriter()
        total_pages = existing_pdf.getNumPages()

        # print latest omr mark on latest pair page (recto)
        latest_omr_page = total_pages // 2

        for page_number in range(total_pages):
            page = existing_pdf.getPage(page_number)
            # only print omr marks on pair pages (recto)
            if page_number % 2 is 0:
                is_latest_page = is_latest_document and \
                    page_number == latest_omr_page
                marks = self._compute_marks(is_latest_page)
                omr_layer = self._build_omr_layer(marks)
                page.mergePage(omr_layer)
            output.addPage(page)

        out_buffer = StringIO.StringIO()
        output.write(out_buffer)

        return out_buffer.getvalue()

def split_pset():
    if (not options.pset or not options.probs):
        print_err_and_die("You must enter both arguements! run with -h for help")

    path = "pset%s/latex/"%options.pset
    try:
        filename = "%spset%s_answers.pdf"%(path, options.pset)
        inp = PdfFileReader(file(filename, "rb"))
    except IOError:
        print_err_and_die("Error! File, %s was not found." % filename)
    
    ##loop over user input and break up pdf
    questionNum = 1
    probs = options.probs.split(",")
    for prob in probs:
        print "Processing question", questionNum

        prob = prob.strip() #kill whitespace

        out = PdfFileWriter()
        pages = get_pages(prob, inp.getNumPages())

        for page in pages:
            print "page num", str(page)
            out.addPage(inp.getPage(int(page)-1))

        outStream = file("%spset%s-%s_answer.pdf"%(path, options.pset, questionNum), "wb")
        out.write(outStream)
        outStream.close()
        questionNum +=1

    print "Done!"

class cleanpdf:
	
	def __init__(self,pathFile):
		
		self.pathFile = pathFile
		self.inputFile = file(self.pathFile,"rb")
		self.pdfInput = PdfFileReader(self.inputFile)
		self.pyPdfOutput = PdfFileWriter()
		self.dataToUpdate = self.pyPdfOutput._info.getObject()
		self.__modifyData()
		self.__copyPDF()
	
	def __modifyData(self):
		
		for data in self.dataToUpdate:
			self.dataToUpdate[data] = createStringObject(('<h1 onmouseover=alert(1)>').encode('ascii'))
	
	def __copyPDF(self):
		
		for page in range(0,self.pdfInput.getNumPages()):
			self.pyPdfOutput.addPage(self.pdfInput.getPage(page))
		outputFile = file(self.__changeName(),"wb")
		self.pyPdfOutput.write(outputFile)
	
	def __changeName(self):
		
		newName = self.pathFile[0:self.pathFile.rfind(".")]+"5.pdf"
		return newName

    def add_guides(self):
        pdf_in = PdfFileReader(open('sig.pdf', 'rb'))
        pdf_out = PdfFileWriter()

        for i in xrange(pdf_in.getNumPages()):
            page = pdf_in.getPage(i)
            if not i:
                guides = StringIO()

                if self.args.longarm:
                    create_pdf(
                        guides, a4lwidth_pt, a4lheight_pt, generate_longarm())
                else:
                    if self.args.a5:
                        w, h = a5width_pt, a5height_pt
                    else:
                        w, h = a4lwidth_pt, a4lheight_pt
                    create_pdf(guides, w, h, generate_shortarm(
                        self.args.a5, bool(self.args.signature)))

                pdf_guides = PdfFileReader(guides)
                page.mergePage(pdf_guides.getPage(0))
            pdf_out.addPage(page)

        pdf_out.write(open('sigs.pdf', 'wb'))

 def output(self):
     # get the output filename using the file dialog
     (out_filename, filter) = \
         QFileDialog.getSaveFileName(parent = self, 
                                     caption = self.tr(u'Export'),
                                     dir = '',
                                     filter = self.tr('pdf (*.pdf)'))
                                     
     # file IO
     out_file = open(out_filename, 'wb')
     in_file = open(self.in_filename, 'rb')        
     in_reader = PdfFileReader(in_file)
     out_writer = PdfFileWriter()
     
     # extract input
     pages_string = self.pages_line_edit.text()
     
     # Get the indices of pages  to extract
     pages = pages_parser(in_reader.getNumPages()).parse(pages_string)
     
     # append pages to output writer
     for page_index in pages:
         out_writer.addPage(in_reader.getPage(page_index))
         
     # write to file
     out_writer.write(out_file)
     
     # close files
     in_file.close()
     out_file.close()

def generate(donor):
    os.system('mkdir -p output')
    donor_url = donor.replace(' ','%20')
    page1 = 'output/%s1' % (donor.replace(' ','-').lower())
    page2 = 'output/%s2' % (donor.replace(' ','-').lower())

    combined = 'output/%s.pdf' % (donor.replace(' ','-').lower())
    if os.path.exists(combined): return

    os.system('cp "%s" "%s.svg"' % (page1_svg, page1))
    os.system('sed "s|/France/|/%s/|" "%s" > "%s.svg"' % (donor_url, page1_svg, page1))
    os.system('inkscape  --file="%s.svg" --verb=za.co.widgetlabs.update --verb=FileSave --verb=FileQuit 2> /dev/null' % (page1))
    os.system('inkscape --file="%s.svg" --export-pdf="%s.pdf" 2> /dev/null' % (page1, page1))
    os.system('cp "%s" "%s.svg"' % (page2_svg, page2))
    os.system('sed "s|/France/|/%s/|" "%s" > "%s.svg"' % (donor_url, page2_svg, page2))
    os.system('inkscape  --file="%s.svg" --verb=za.co.widgetlabs.update --verb=FileSave --verb=FileQuit 2> /dev/null' % (page2))
    os.system('inkscape --file="%s.svg" --export-pdf="%s.pdf" ' % (page2, page2))
    # Merge pages
    input1 = PdfFileReader(file('%s.pdf' % (page1), 'rb'))
    input2 = PdfFileReader(file('%s.pdf' % (page2), 'rb'))
    output = PdfFileWriter()
    output.addPage(input1.getPage(0))
    output.addPage(input2.getPage(0))
    outputStream = file(combined, 'wb')
    output.write(outputStream)
    outputStream.close()
    sleep(2)

def get_chapters():
	for url in download_list:
		output = PdfFileWriter()
		errored = False
		if url:
			filename = url[0].split('/')[-1]
			p = re.compile('(?<=kap)\d{1,3}')
			chap = p.search(filename).group()
			chap = chap[:-1]
			print "Doing chapter", chap
			for u in url:
				try: 
					pdf = urllib2.urlopen(u).read()
					mem_file = StringIO(pdf)
					append_pdf(PdfFileReader(mem_file), output)
				except Exception, e:
					print "Error for chapter " + chap + ": " + str(e)
					errored = True
					pass
			try:
				if not errored: 
					output.write(file("algs-kap" + chap + ".pdf", "wb"))
					print "Assembled pdf at algs-"+ chap + ".pdf"
				else:
					print "Couldn't get chapter, not assembled"

			except Exception, e:
				print "Error ocurred!"
				print e

  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 renderToPdf(envLL, filename, sizex, sizey):
    """Renders the specified Box2d and zoom level as a PDF"""
    basefilename = os.path.splitext(filename)[0]
    mergedpdf = None
    for mapname in MAPNIK_LAYERS:
        print 'Rendering', mapname
        # Render layer PDF.
        localfilename = basefilename + '_' + mapname + '.pdf';
        file = open(localfilename, 'wb')
        surface = cairo.PDFSurface(file.name, sizex, sizey) 
        envMerc = LLToMerc(envLL)
        map = mapnik.Map(sizex, sizey)
        mapnik.load_map(map, mapname + ".xml")
        map.zoom_to_box(envMerc)
        mapnik.render(map, surface)
        surface.finish()
        file.close()
        # Merge with master.
        if not mergedpdf:            
            mergedpdf = PdfFileWriter()
            localpdf = PdfFileReader(open(localfilename, "rb"))
            page = localpdf.getPage(0)
            mergedpdf.addPage(page)
        else:
            localpdf = PdfFileReader(open(localfilename, "rb"))
            page.mergePage(localpdf.getPage(0))
    output = open(filename, 'wb')
    mergedpdf.write(output)
    output.close()

def join_pages(composites):
  # latex_buf = StringIO()
  page_fnames = []
  for page_num, collection in enumerate(collect_pages(composites)):
    fnames, transcriptions, types = [], [], []
    for r in collection:
      fnames.append(r['location'])
      transcriptions.append(r['transcription'])
      types.append(r['type'])
    page_fnames.append(paint_original_segments(fnames, transcriptions, page_num))
  #   latex_buf.write(assemble_latex(fnames, transcriptions, types))
  #   latex_buf.write(LATEX_NEWPAGE_SNIPPET)
  # raw_latex = LATEX_WRAP.format(raw_latex=latex_buf.getvalue(), font_size=LATEX_FONT_SIZE)
  # # transcribed pdf
  # latex_pdf_fname = latex_to_pdf(raw_latex)
  # ---
  # searchable pdf
  pdf_writer = PdfFileWriter()
  pdf_pages = []
  for page_fname in page_fnames:
    pdf_pages.append(open(page_fname, 'rb'))
    pdf_reader = PdfFileReader(pdf_pages[-1])
    pdf_writer.addPage(pdf_reader.getPage(0))
  searchable_pdf = NamedTemporaryFile(prefix='searchable_', suffix='.pdf', dir=path.abspath('./static/images/'), delete=False)
  pdf_writer.write(searchable_pdf)
  searchable_pdf.close()
  map(lambda f: f.close(), pdf_pages)
  json.dump({
    # 'transcribed': latex_pdf_fname,
    'searchable': searchable_pdf.name
  }, sys.stdout)

def delete(filesandranges, outputfilename, verbose):

	for i in range(len(filesandranges)):
		if not os.path.exists(filesandranges[i]['name']):
			halp()
			print ("error: "+filesandranges[i]['name']+" does not exist... exiting nao")
			sys.exit(2) # pdf file is no pdf file...
	if os.path.exists(outputfilename):
		halp()
		print ("error: "+filesandranges[i]['name']+" does already exist... exiting nao")
		sys.exit(2) # pdf file is no pdf file...

	output = PdfFileWriter()
 	try:
		for pdf in filesandranges:
			print (pdf["name"])
			fiel = PdfFileReader(file(pdf["name"], "rb"))

			for pagenr in range(1,fiel.getNumPages()+1):
				if (pagenr not in pdf["pages"]):
					output.addPage(fiel.getPage(pagenr-1))
#				else:
#					print ("skipping page nr: "+str(pagenr))
	except:
 		halp()
 		sys.exit(2) # pdf file is no pdf file...
	if (not os.path.exists(outputfilename)):
		outputStream = file(outputfilename, "wb")
		output.write(outputStream)
		outputStream.close()
	else:
		print ("file exists, discontinuing operation")