Python PdfFileWriter.getNumPages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 getNumPages [as 别名]
    def test_two_on_one_page(self):
        # Build a document with two pages
        pdf = PdfFileReader(self.get_pdf_stream())
        output = PdfFileWriter()
        output.addPage(pdf.getPage(0))
        output.addPage(pdf.getPage(0))
        assert output.getNumPages() == 2
        assert output.getPage(0).extractText().count('Test') ==  1
        buf = StringIO()
        output.write(buf)
        buf.seek(0)

        rv = self.app.get('/')
        self.assertEquals(rv.status_code, 200)

        rv = self.app.post('/handleform',
                           data={'file': (buf, 'test.pdf')})

        rv = self.combine_and_download(pages_sheet='2')

        pdf_download = PdfFileReader(StringIO(rv.data))
        self.assertEquals(pdf_download.getPage(0).extractText().count('Test'),
                          2)
        self.assertEquals(pdf_download.getNumPages(), 1)

        self.clean_up()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
def consume_files(filelist):
    i = 0
    while (len(filelist) > 0):
        output = PdfFileWriter()
        merge_pages_better(output, filelist)
        outputstream = file(PREFIX_STR+str(i)+'.pdf', 'wb')
        print "%s%d.pdf has %d pages" % (PREFIX_STR, i, output.getNumPages())
        i = i + 1
        output.write(outputstream)
        outputstream.close()
    return 1

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
def merge_pdf(url_list):
    # Download each PDF and merge them into one giant PDF, post this giant PDF to anonfiles.com, add URL to scraperwiki database
    output = PdfFileWriter()
    for url in url_list:

        if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/083.pdf":
             url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/83.pdf"
             url[1] = "83.pdf"
        if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/039.pdf":
             url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/39.pdf"
             url[1] = "39.pdf"
        if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/021.pdf":
             url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/21.pdf"
             url[1] = "21.pdf"
        if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/016S.pdf":
             url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/16S.pdf"
             url[1] = "16S.pdf"
        if url[0] == "http://www.cota.com/assets/Riding-Cota/Schedules/Current/015.pdf":
             url[0] = "http://www.cota.com/assets/Riding-Cota/Schedules/Current/15.pdf"
             url[1] = "15.pdf"

        pdf_file = os.system("wget %s" % url[0])
        input1 = PdfFileReader(file('/tmp/%s' % url[1], "rb"))
        numPages  = input1.getNumPages()
        print "number of pages = %s" % (numPages)
        page1 = input1.getPage(0)
        page2 = input1.getPage(1)
        output.addPage(page1)
        output.addPage(page2)

        if numPages == 3:
            page3 = input1.getPage(2)
            output.addPage(page3)

    final_page_count = output.getNumPages()
    print "Number of Pages in Final = %s" % (final_page_count)

    outputStream = file("/tmp/bus.pdf", "wb")
    output.write(outputStream)
    outputStream.close()

    reply = os.system('curl -kF "[email protected];filename=bus.pdf" https://anonfiles.com/api/hotlink -o "reply.txt"')

    with open('reply.txt', 'r') as f:
        read_data = f.read()

    data_dict = {
                   'Title':'Link to COTA Bus Schedule',
                   'URL':read_data,
                }
    scraperwiki.sqlite.save(unique_keys=['Title', 'URL'], data=data_dict)

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
def splitPDF(inputpdf, output_fn, start, end):
    """ from the input pdf creates a new pdf file with the name output_fn
    containing only the pages of the pdf from start to end
    """    
    
    outputpdf = PdfFileWriter()
    print 'added pages ',
    for i in xrange(start, end):
        outputpdf.addPage(inputpdf.getPage(i))
        print str(i) + ',',
    print 'finished. printed', outputpdf.getNumPages(), 'pages'
    
    outstream = file(output_fn, 'wb')
    outputpdf.write(outstream)
    outstream.close()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
def merge_pdfs(output_name, files):
    """ Merges files in the order given. Make sure to sort first."""
    output = PdfFileWriter()
    for f in files:
        try:
            i = PdfFileReader(file(f, "rb"))
        except IOError as e:
            print(e)
        except PdfReadError as e:
            print(e)
        else:
            for p in i.pages:
                output.addPage(p)
    if output.getNumPages():
        ostream = file(output_name, "wb")
        output.write(ostream)
        ostream.close()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
    def test_page_ranges(self):
        rv = self.app.get('/')
        self.assertEquals(rv.status_code, 200)

        pdf = PdfFileReader(self.get_pdf_stream())

        # Build a document with twenty pages
        output = PdfFileWriter()
        page = pdf.getPage(0)
        for i in range(1, 21):
            new_page = CombineTestCase.replace_text(page, 'Test', 'Test %d' % i)
            output.addPage(new_page)
        assert output.getNumPages() == 20

        buf = StringIO()
        output.write(buf)
        buf.seek(0)

        rv = self.app.post('/handleform',
                           data={'file': (buf, 'test.pdf')},
                           follow_redirects=True)

        ids = self.extract_ids_from_main_page(rv.data)
        pages_kw = 'pages_%d' % ids[0]
        rv = self.combine_and_download(**{pages_kw: '-5, 10, 12-14, 18-'})

        pdf_download = PdfFileReader(StringIO(rv.data))

        # Test ranges
        ranges = [1, 2, 3, 4, 5, 10, 12, 13, 14, 18, 19, 20]

        self.assert_(all(
            (('Test %d' % page) in pdf_download.getPage(i).extractText())
                        for i, page in enumerate(ranges)))

        self.assertEquals(pdf_download.getNumPages(), len(ranges))

        self.clean_up()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
for x in range(len(INPUT)) :
  hackfile = 'editionHack/hack{0}.pdf'.format(x+OFFSET)
  goodfile = 'editionHack/'+INPUT[x]+".pdf"
  output = PdfFileWriter()
  input1 = PdfFileReader(file(goodfile, "rb"))
  page1 = input1.getPage(0)
  watermark = PdfFileReader(file(hackfile, "rb"))
  page1.mergePage(watermark.getPage(0))
  output.addPage(page1)
  outputStream = file("editionHack/finalPage{0}.pdf".format(x+OFFSET), "wb")
  print "finalPage{0}.pdf".format(x+OFFSET)
  output.write(outputStream)
  outputStream.close()

output = PdfFileWriter()
for x in range(3,11) :
  input1 = PdfFileReader(file('editionHack/finalPage{0}.pdf'.format(x), "rb"))
  output.addPage(input1.getPage(0))

input1 = PdfFileReader(file('sitOzfarsWysr_a4.pdf', "rb"))
for x in range(input1.getNumPages()) :
  output.addPage(input1.getPage(x))

if output.getNumPages() % 2 == 1 :
  input1 = PdfFileReader(file('editionHack/blankPage.pdf', "rb"))
  output.addPage(input1.getPage(0))

outputStream = file("editionHack/sowInterior.pdf".format(x), "wb")
output.write(outputStream)
outputStream.close()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
  })
# Add It
output._addObject(properties)
# Add back the one we deleted first
output._addObject(item)

address = PdfFileReader(file("input\\address\\"+fname, "rb"))
location = PdfFileReader(file("input\\location\\"+fname, "rb"))

print "Location Pages:", location.numPages
print "Address Pages:", address.numPages

if location.numPages > 1 :
  print "Location has more than 1 page, exiting..."
  sys.exit()
  
page = location.getPage(0)
for i in xrange(address.numPages):
  #print ".",
  output.addPage(address.getPage(i))
  output.addPage(page)

# output should be double address
print "Output Pages:", output.getNumPages()

#if output.getNumPages() == (address.numPages *2):
if output.getNumPages() > 0:
  outStream = file("output\\"+fname, "wb")
  output.write(outStream)
  outStream.close()
  print "Generation Complete"

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
# This is the pyPdf library. Install with: $ pip install pyPdf
from pyPdf import PdfFileWriter, PdfFileReader

# Open a writer object
output = PdfFileWriter() 
# Load the pdf file(s) you want to input pages from
input1 = PdfFileReader(file("test.pdf", "rb"))

# Add some pages from your source/input files to the writer object
output.addPage(input1.getPage(8))
output.addPage(input1.getPage(15))

# For kicks, print the number of pages added to the console
print "number of pages is: %s " % output.getNumPages()

# Explain the kind of file this will be when outputted
outputStream = file("assembled_pdf.pdf", "wb")

# Write the actual output file
output.write(outputStream)

# Close the output file
outputStream.close()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
        
        page2 = output_pdf.addBlankPage(x/2, y)
        page2.mergeTranslatedPage(p, -x/2, 0)
        
        split_count = split_count + 1
    else:
        # Portrait, fine on its own
        output_pdf.addPage(p)
    
    progress.animate(amount=i)
    
progress.animate(amount=pages)

print 'Total pages: %d -> %d ' % (
    pages,
    output_pdf.getNumPages()
)
if split_count:
    print '/-{ %d }-\\ double spreads split apart' % split_count

print 'Writing... here is a bird to keep you company'

def write_file():
    # Write the file
    output_file = file(input_base + '.split' + input_ext, "wb")
    output_pdf.write(output_file)
    output_file.close()

t = threading.Thread(target=write_file)
t.start()

# 需要导入模块: from pyPdf import PdfFileWriter [as 别名]
# 或者: from pyPdf.PdfFileWriter import getNumPages [as 别名]
   batchnames.append("batch"+str(i)+".pdf")


# Loop through HouseDistricts
for i in range(1,100):
      output = PdfFileWriter()
      outputfilename = "pdfs/HD"+str(i)+".pdf"
      for b in batchnames:
         input_pdf = PdfFileReader(file("pdfs/"+b, "rb"))
         with open('csvs/district_data.csv', 'rb') as csvfile:
            district_reader = csv.reader(csvfile, delimiter=',', quotechar='"')
            for row in district_reader:
               if row[0] == b:
                  if row[9]== str(i):
                    output.addPage(input_pdf.getPage(int(row[1])-1))
      if output.getNumPages() >0:
         outputStream = file(outputfilename, "wb")
         output.write(outputStream)
         outputStream.close()
         print "There are %s form letters from %s " % (output.getNumPages(), outputfilename)


# Loop through SenateDistricts
for i in range(1,34):
      output = PdfFileWriter()
      outputfilename = "pdfs/SD"+str(i)+".pdf"
      for b in batchnames:
         input_pdf = PdfFileReader(file("pdfs/"+b, "rb"))
         with open('csvs/district_data.csv', 'rb') as csvfile:
            district_reader = csv.reader(csvfile, delimiter=',', quotechar='"')
            for row in district_reader: