def merge(self, pdf_one, pdf_two, filename='my.pdf', output_dir='D:/pdf/'):
'''
function:#pdfone为扫描的正面；#pdftwo为扫描的背面；#本函数实现将两个扫描文件按原有的顺序合并起来
:param pdf_one:
:param pdf_two:
:param filename:
:param output_dir:
:return:
'''
input_one = open(pdf_one, 'rb')
input_two = open(pdf_two, 'rb')
pdf_input_one = PdfFileReader(input_one)
pdf_input_two = PdfFileReader(input_two)
numOne = pdf_input_one.getNumPages()
numTwo = pdf_input_two.getNumPages()
print(numOne, numTwo)
pdf_output = PdfFileWriter()
index_one = 0
index_two = numTwo - 1
while True:
if index_one == numOne: break
print(index_one, index_two)
page1 = pdf_input_one.getPage(index_one)
pdf_output.addPage(page1)
page2 = pdf_input_two.getPage(index_two)
pdf_output.addPage(page2)
index_one += 1
index_two -= 1
pdf_name = output_dir + filename
output_stream = open(pdf_name, 'wb')
pdf_output.write(output_stream)
output_stream.close()
input_one.close()
input_two.close()
print('Done!')
def generate_images(path, save_dir_name, is_train):
if not os.path.exists('png_files/'):
os.mkdir('png_files/')
train_images = 'train_images/'
test_images = 'test_images/'
if is_train:
save_directory_path = 'png_files/'+ train_images + save_dir_name + '_annotated_images'
else:
save_directory_path = 'png_files/' + test_images + save_dir_name + '_annotated_images'
if not os.path.exists(save_directory_path):
os.makedirs(save_directory_path)
filename = path
print("Converting " + filename + " from pdf to PNG...")
reader = PdfFileReader(open(filename, mode="rb"))
try:
page_number = reader.getNumPages()
except:
page_number = reader.getNumPages() #PyPDF2 bug
with tempfile.TemporaryDirectory() as path:
images_from_path = convert_from_path(filename, dpi=72, output_folder=path, last_page=page_number, first_page=0)
i = 0
for page in images_from_path:
base_filename = os.path.splitext(os.path.basename(filename))[0] + '_' + str(i + 1) + '.png'
page.save(os.path.join(save_directory_path, base_filename), 'PNG')
i += 1
print('PDF file successfully converted.')
def test_cat(self):
"""Make sure files are properly concatenated."""
run_stapler(['cat', ONEPAGE_PDF, FIVEPAGE_PDF, self.outputfile])
self.assertTrue(os.path.isfile(self.outputfile))
with open(self.outputfile, 'rb') as outputfile:
pdf = PdfFileReader(outputfile)
self.assertEqual(pdf.getNumPages(), 6)
def PdfPrettyPrint(inputname, outputname):
inputfile = open(inputname, 'rb')
wrt = PdfFileWriter()
ipt = PdfFileReader(inputfile)
#print ipt.getDocumentInfo()
pdfnums = ipt.getNumPages()
#print pdfnums
i = 0
while i < pdfnums:
page = ipt.getPage(i)
wrt.addPage(page)
if i + 2 < pdfnums:
page = ipt.getPage(i + 2)
wrt.addPage(page)
else:
wrt.addBlankPage()
if i + 1 < pdfnums:
page = ipt.getPage(i + 1)
page.rotateClockwise(180)
wrt.addPage(page)
else:
wrt.addBlankPage()
if i + 3 < pdfnums:
page = ipt.getPage(i + 3)
page.rotateClockwise(180)
wrt.addPage(page)
else:
wrt.addBlankPage()
i = i + 4
fl = open(outputname, "wb")
wrt.write(fl)
inputfile.close()
fl.close()
return True
def readPDFfile(infile):
pdf = PdfFileReader(infile, "rb"))
content = ""
num = pdf.getNumPages()
for i in range(0, num):
extractedText = pdf.getPage(i).extractText()
content += extractedText + "\n"
return content
def getDataUsingPyPdf2(filename):
pdf = PdfFileReader(open(filename, "rb"))
content = ""
num = pdf.getNumPages()
for i in range(0, num):
extractedText = pdf.getPage(i).extractText()
content += extractedText + "\n"
return content
def searchPDF(filename,search_term):
search_term = search_term.lower()
pages = []
pdf = PdfFileReader(open(filename, "rb"))
for i in range(0, pdf.getNumPages()):
content = pdf.getPage(i).extractText().lower()
if(search_term in content):
pages.append(i + 1)
return pages;
def __init__(self, path):
self.path = path
self.pages = None
self.meta_data = None
try:
with open(self.path,'rb') as fp:
pdf = PdfFileReader(fp)
self.meta_data = pdf.getDocumentInfo()
self.pages = pdf.getNumPages()
except (IOError,TypeError) as e:
print(e)
except:
print("Unexpected error:", sys.exc_info()[0])
def clickOK():
File = PdfFileReader(open(selectPDF.get() + '.pdf', 'rb'))
page_cound = File.getNumPages()
pprint.pprint(page_cound)
ageList = []
for i in range(0, page_cound):
try:
if i == entry1.get():
ageList.append(File.getPage(i).extractText())
pprint.pprint(ageList[int(0)])
except:
print("except")
def generate_images_for_lecture(self, lecture_instance, file_pdf):
pdf_im = PdfFileReader(file_pdf)
for page_num in range(pdf_im.getNumPages()):
page_file_name = file_pdf.path+'['+str(page_num)+']'
print(page_file_name)
im = PythonMagick.Image(page_file_name)
image_lecture_page = Image()
image_lecture_page.lecture = lecture_instance
image_file_name = basename(file_pdf.name)+"-page-"+str(page_num)+".jpeg"
image_lecture_page.image.save(image_file_name, File(im))
print("here")
print(image_lecture_page)
def crop(pdf_in, pdf_out):
"""
Параметры
pdf_in - абсолютный путь к пдф
pdf_out - абсолютный путь для исходящего пдф
:return: status
"""
""" Временно к функции добавлен второй параметр - pdf_out. В продакшн она должна сохранять результат кропа
в тот же файл
"""
status = True
# Словарь с размерами бумаги для каждой страницы
papers = analyze_papersize(pdf_in) # like {1: ('Speedmaster', 900, 640), 2: ('Dominant', 640, 450)}
# TODO Доработать временное решение кропа в отсутствии инфы о размере бумаги.
if papers == {}:
perl_crop = "perl pdfcrop.pl {} {}".format(pdf_in, pdf_out)
os.system(perl_crop)
return status
input = PdfFileReader(file(pdf_in, "rb"))
output = PdfFileWriter()
# Количество страниц
pages_qty = input.getNumPages()
for index in range(pages_qty):
paper_machine = papers[index+1][0]
paper_w = papers[index+1][1]
paper_h = papers[index+1][2]
for m in PrintingPress._registry:
if paper_machine == m.name:
machine = m
plate_w = machine.plate_w
plate_h = machine.plate_h
page = input.getPage(index)
""" EXAMLE
# The resulting document has a trim box that is 200x200 points
# and starts at 25,25 points inside the media box.
# The crop box is 25 points inside the trim box.
print mm(page.mediaBox.getUpperRight_x()), mm(page.mediaBox.getUpperRight_y())
page.trimBox.lowerLeft = (25, 25)
page.trimBox.upperRight = (225, 225)
page.cropBox.lowerLeft = (50, 50)
page.cropBox.upperRight = (200, 200)
"""
print 'Crop page {} to paper {}x{}'.format(index+1, paper_w, paper_h)
page.mediaBox.lowerLeft = ((pt(plate_w - paper_w)/2), pt(machine.klapan)) # отступ слева, отступ снизу
page.mediaBox.upperRight = (pt(paper_w + (plate_w - paper_w)/2), pt(paper_h + machine.klapan)) # ширина+отступ, высота+отступ
output.addPage(page)
outputstream = file(pdf_out, "wb")
output.write(outputstream)
outputstream.close()
return status
