Python PdfFileWriter.write方法代码示例

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
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()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
def createPDFHttpResponse(filepath, output_filename, user, access_time):
    """
    Creates a HttpResponse from a watermarked PDF file. Watermark contains the user who accessed the document
    and the time of access.

    :param filepath: Path to the file
    :param output_filename: File name sent to the user
    :param user:
    :param access_time:
    :return: HttpResponse with the file content, or HttpResponseNotFound
    
    """
    #Add access watermark
    buffer = StringIO()
    p = canvas.Canvas(buffer)
    p.drawString(0,0, "Downloaded by %s at %s" %(user, access_time.isoformat(' ')))
    p.showPage()
    p.save()
    buffer.seek(0)
    watermark = PdfFileReader(buffer)

    #Read the PDF to be accessed
    attachment = PdfFileReader(open(filepath, 'rb'))
    output = PdfFileWriter()

    #Attach watermark to each page
    for page in attachment.pages:
        page.mergePage(watermark.getPage(0))
        output.addPage(page)

    response = HttpResponse(mimetype='application/pdf')
    response['Content-Disposition'] = 'inline; filename=%s' % output_filename.encode('utf-8')
    output.write(response)
    return response

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
def merge(fppath, bppath, outputpath, no_delete, fed_backwards):
  fpfile = PdfFileReader(open(fppath))
  bpfile = PdfFileReader(open(bppath))

  outputfile = PdfFileWriter()

  outputpages = []
  for i in range(fpfile.getNumPages()):
    backpages = True
    try:
      outputpages.append(fpfile.getPage(i))
      if backpages:
        if fed_backwards:
          outputpages.append(bpfile.getPage(bpfile.getNumPages() - i - 1))
        else:
          outputpages.append(bpfile.getPage(i))
    except IndexError:
      backpages = False

  if not no_delete:
    outputpages = [page for page in outputpages if page.extractText() != '']

  [outputfile.addPage(page) for page in outputpages]

  outputfile.write(open(os.path.expanduser(outputpath), 'w'))

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
    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()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
def split_chapters(*t_args):
    """
    Split a large pdf into chunks (i.e. chapters)
    """    
    if len(t_args)>0:
        args=t_args[0]
        if len(args)<1:  
            print "usage: utils_pdf split_chapters configfile"
            return 
        from pyPdf import PdfFileWriter, PdfFileReader
        f = open(args[0])
        P = json.loads(f.read())
        f.close()
        input = PdfFileReader(file(P["source"], "rb"))
        i0 =  P["first_chapter_index"]
        ends = P["chapters_ends"]
        for i in xrange(0, len(ends)): 
            ch_num = i0+i
            fmt = P["chapter_fmt"] % (ch_num, )
            output = PdfFileWriter()
            if not os.path.exists(P["outputdir"]): 
                os.mkdir( P["outputdir"])
            fn_out = "%s/%s%s" % (P["outputdir"], P["chapter_prefix"], fmt)
            j0 = P["firstpage"] if i==0 else ends[i-1]
            for j in xrange(j0, ends[i]): 
                output.addPage(input.getPage(j))
            outputStream = file(fn_out, "wb")
            output.write(outputStream)
            outputStream.close()
            print "wrote %s" % (fn_out,)

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
def cat(infilenames, outputfilename, verbose):
	inputs = []
	for infilename in infilenames:
		print infilename
		if not os.path.exists(infilename):
			halp()
			print ("error: "+infilename+" does not exist... exiting nao")
			sys.exit(2) # pdf file is no pdf file...
	if os.path.exists(outputfilename):
		halp()
		print ("error: "+outputfilename+" does already exist... exiting nao")
		sys.exit(2) # pdf file is no pdf file...
	try: 
		for i in infilenames:
			inputs.append(PdfFileReader(file(i, "rb")))
	except:
		halp()
		sys.exit(2) # pdf file is no pdf file...
	
	i = 0
	output = PdfFileWriter()

	for pdf in inputs:
		for pagenr in range(pdf.getNumPages()):
			output.addPage(pdf.getPage(pagenr))
			i=i+1
	outputStream = file(outputfilename, "wb")
	output.write(outputStream)
	outputStream.close()
	if verbose: print (str(i)+" pages processed")

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
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

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
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

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
    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'))

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
  def concatenate_pdf(self,book_title):
		fileList = os.listdir(os.getcwd())
		num_chapters=0
		for i in range(1,40):
			if not fileList.__contains__(book_title+str(i)+".pdf"):
				num_chapters= i-1
				print "numero capitulos"+str(num_chapters)
				break

		print"Uniendo pfs..."
		output = PdfFileWriter()
		for i in range (1,num_chapters):
			f=open(book_title+str(i)+".pdf", "rb")
			num_pages=PdfFileReader(f).getNumPages()
			if num_pages==0:
				pdfOne = PdfFileReader(f).getPage(0)
				output.addPage(pdfOne)

			else:
				for a in range (0,num_pages):
					pdfOne = PdfFileReader(f).getPage(a)
					output.addPage(pdfOne)

		outputStream = file(r""+book_title+".pdf", "wb")
		output.write(outputStream)
		outputStream.close()

		print"Union finalizada"
		for i in range(1,num_chapters+1):
			print "borrando... capitulo: "+str(i)
			os.remove(book_title+str(i)+".pdf")

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
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)

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
  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()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
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()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
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)

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import write [as 别名]
def select(filesandranges, outputfilename, verbose):

 	if verbose: print (str(filesandranges)+"\noutput: "+str(outputfilename))

	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:
			fiel = PdfFileReader(file(pdf["name"], "rb"))
			for pagenr in pdf["pages"]:
				if (not (pagenr > fiel.getNumPages()) and not(pagenr < 1)):
					output.addPage(fiel.getPage(pagenr-1))
				else:
					print("one or more pages are not in the chosen PDF")
					halp()
					sys.exit(3) #wrong pages or ranges
 	except:
 		halp()
 		sys.exit(2) # pdf file is no pdf file...h
	if (not os.path.exists(outputfilename)):
		outputStream = file(outputfilename, "wb")
		output.write(outputStream)
		outputStream.close()
	else:
		print ("file exists, discontinuing operation")