def write_with_template(self,out_file="",template_filename=""):
"""
テンプレとマージしてそのまま出力しちゃう
"""
# リーダーでテンプレ読む
template_filename = template_filename or self.template_filename
reader = PdfFileReader(template_filename)
# なんかページ処理
page = reader.getPage(0)
page_width = page.mediaBox.getWidth()
page_height = page.mediaBox.getHeight()
# バッファからPDFデータ化
self.buffer.seek(0) # シークして読み込みできるように
new_pdf = PdfFileReader(self.buffer) # 読み込み
# テンプレート・ページと内容をマージ
page.mergePage(new_pdf.getPage(0))
# writerに渡す
writer = PdfFileWriter()
writer.addPage(page)
# 書き込む
with open(out_file, 'wb') as f:
writer.write(f)
def domerge(self):
"""
Main merge method. It will merge all the pdfs in the input directory.
:return:
"""
print "Getting all pdf files in the folder"
self.get_file_list()
print "Going to start merge"
pdfmerger = PdfFileMerger()
writer = PdfFileWriter()
outputStream = file(self.output, "wb")
for filename in self.files:
print "Going to merge %s"%filename
reader = PdfFileReader(file(filename, 'rb'))
page_num = 0
for page in reader.pages:
# print page.artBox
# print page.bleedBox
# print page.cropBox
# print page.trimBox
self.add_footer(page,filename,page_num)
page_num +=1
writer.addPage(page)
writer.write(outputStream)
outputStream.close()
print "Done merging"
def combine_pdf_pages(pdfpath, pagesgroups, verbose=False):
"""
Combines vertically groups of pages of a pdf file
@type pdfpath: str or unicode
@type pagesgroups: list of (list of int)
"""
# opening input file
if verbose:
print(("Opening file " + pdfpath))
fi = open(pdfpath, 'rb')
pdf = PdfFileReader(fi)
# opening output pdf
pdfout = PdfFileWriter()
# loop on groups of pages tom combine
for pagesgroup in pagesgroups:
if verbose:
print(("Combining pages:", ))
# heights and widths
heights = [pdf.pages[i].mediaBox.getHeight() for i in pagesgroup]
widths = [pdf.pages[i].mediaBox.getWidth() for i in pagesgroup]
# adding new blank page
page_out = pdfout.addBlankPage(width=max(widths), height=sum(heights))
# merging pages of group
for i, p in enumerate(pagesgroup):
if verbose:
print((p, ))
page_out.mergeTranslatedPage(pdf.pages[p],
tx=0,
ty=sum(heights[i + 1:]))
print()
# exporting merged pdf into temporary output file
fo = create_tmpfile('wb')
if verbose:
print(("Exporting merged pdf in file {}".format(fo.name)))
pdfout.write(fo)
# closing files
fi.close()
fo.close()
# removing original file and replacing it with merged pdf
if verbose:
print(("Moving exported pdf to: " + pdfpath))
os.remove(pdfpath)
os.rename(fo.name, pdfpath)
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 finalize_print_preparation(self):
"""Take the resulting multi page PDF and split into rotated single pages
Taken from `pythonlibrary.org
<https://www.blog.pythonlibrary.org/2018/04/11/splitting-and-merging-pdfs
-with-python/>`_ in combination with `johndcook.com
<https://www.johndcook.com/blog/2015/05/01/rotating-pdf-pages-with-python/>`_
"""
pdf: PdfFileReader = PdfFileReader(self._full_output_path_)
for page_number in range(pdf.getNumPages()):
pdf_writer: PdfFileWriter = PdfFileWriter()
page: PageObject = pdf.getPage(page_number)
page.rotateCounterClockwise(90)
pdf_writer.addPage(page)
output_filename: str = (f"{self._output_base_filename}_page_"
f"{str(page_number + 1).zfill(2)}.pdf")
with open(
os.path.join(self._output_directory_name, output_filename),
"wb") as pdf_out:
pdf_writer.write(pdf_out)
path_to_pdf = os.path.join(os.getcwd(), self._full_output_path_)
print(f"Create {pdf.getNumPages()} single paged PDFs.\n\n"
f"You can find them concatenated at file://"
f"{path_to_pdf}")
class ReadPdf(object):
def __init__(self,in_file):
self.pdf_read = PdfFileReader(open(in_file, 'rb'))
self.pdf_write = PdfFileWriter()
def parse(self,out_file,type):
for page in self.pdf_read.pages:
if type=='01':
# 电测听 剪切方案
pass
# page.mediaBox.setUpperLeft((0,606))
# page.mediaBox.setUpperRight((595,606))
# page.mediaBox.setLowerLeft((0,0))
# page.mediaBox.setLowerRight((595,0))
elif type=='02':
# 人体成分(投放) 剪切方案
page.mediaBox.setUpperLeft((0, 765))
page.mediaBox.setUpperRight((595, 765))
page.mediaBox.setLowerLeft((0, 22))
page.mediaBox.setLowerRight((595, 22))
elif type=='03':
pass
elif type=='04':
# 骨密度 剪切方案
page.mediaBox.setUpperLeft((0, 860))
page.mediaBox.setUpperRight((595, 860))
page.mediaBox.setLowerLeft((0, 80))
page.mediaBox.setLowerRight((595, 80))
elif type=='05':
# #超声骨密度 剪切方案
page.mediaBox.setUpperLeft((0, 842))
page.mediaBox.setUpperRight((595, 842))
page.mediaBox.setLowerLeft((0, 35))
page.mediaBox.setLowerRight((595, 35))
else:
pass
self.pdf_write.addPage(page)
ous = open(out_file, 'wb')
self.pdf_write.write(ous)
ous.close()
def merge_page_nums(pages: List[PageObject], options, filename='page_nums.pdf'):
output = []
path = os.path.join(options["folder-dir"], "tmp", filename)
with open(path, 'rb') as f:
page_num_pdf = PdfFileReader(f)
for i, page in enumerate(pages):
target: PageObject = page_num_pdf.getPage(i)
target.mergePage(page)
# For some reason the text doesn't appear properly if we don't write first
thread_print("Writing extra output file because this is somehow necessary")
tmp_out = PdfFileWriter()
tmp_out.addPage(target)
with open(os.path.join(options["folder-dir"], "tmp", "page_num_overlap.pdf"), 'wb') as f:
pass#tmp_out.write(f)
output.append(target)
return output
def do_highlight(filename,keywords,output_file):
locations = calculate_locations(filename,keywords)
reader = PdfFileReader(file(filename, 'rb'))
lnk = DictionaryObject()
writer = PdfFileWriter()
num = 0
for page in reader.pages:
for l in locations :
if l.page_num == num :
annot1 = highlight_annotation([l.bounds],
'Comments',
'Author', 'Comments.')
popup_ref = writer._addObject(annot1)
print l.page_num
if "/Annots" in page:
page['/Annots'].append(popup_ref)
annots = page['/Annots']
else:
page[NameObject('/Annots')] = ArrayObject([popup_ref])
annots = page['/Annots']
annots_ref = writer._addObject(annots)
num+=1
writer.addPage(page)
# finally, write "output" to document-output.pdf
outputStream = file(output_file, "wb")
writer.write(outputStream)
outputStream.close()
def merge_pdfs(origin, num_pages, aux, verso=None, above=False, allPage=False):
"""
this is a general purpose merging function, it helps in various plugins in order to
not redo the wheel. It merges origin as the back, aux above.
"""
try:
output = PdfFileWriter()
input_result = PdfFileReader(io.BytesIO(origin))
pages = []
for i in range(0, num_pages):
page_origin = input_result.getPage(i)
if allPage or i % 2 == 0:
page_aux = PdfFileReader(io.BytesIO(aux)).getPage(0)
pages.append(tasks.merge.delay(page_origin, page_aux, above))
else:
_merge_verso(verso, page_origin, above, pages)
for page in pages :
if type(page) == PyPDF2.pdf.PageObject:
output.addPage(page)
else :
#request celery result
data = page.get()
output.addPage(data)
out_io = io.BytesIO()
output.write(out_io)
out_io.seek(0, 0)
return out_io.read()
except Exception:
labresult.app.logger.error(traceback.format_exc())
raise MergePDFException('Error while merging PDFs')
def addBlankpage(inFile, outFile):
'''
pdf读取写入操作
'''
pdfFileWriter = PdfFileWriter()
# 获取 PdfFileReader 对象
pdfFileReader = PdfFileReader(
inFile) # 或者这个方式：pdfFileReader = PdfFileReader(open(readFile, 'rb'))
numPages = pdfFileReader.getNumPages()
for index in range(0, numPages):
pageObj = pdfFileReader.getPage(index)
pdfFileWriter.addPage(pageObj) # 根据每页返回的 PageObject,写入到文件
pdfFileWriter.write(open(outFile, 'wb'))
pdfFileWriter.addBlankPage() # 在文件的最后一页写入一个空白页,保存至文件中
pdfFileWriter.write(open(outFile, 'wb'))
def PdfMultiplePassword(filepaths, password):
# Check if files exists
check_path = [os.path.isfile(x) for x in filepaths]
# Gets the files extension
file_extensions = [os.path.splitext(x)[1] for x in filepaths]
# Check if files extension are pdf
file_extensions_check = [x for x in file_extensions if x != ".pdf"]
if False in check_path:
# Get the index of the file that doesn't exists
index = check_path.index(False)
print(f"File Doesn't Exists: {filepaths[index]}")
sys.exit()
else:
# Not a PDF file is given
if file_extensions_check:
print("Submit Only PDF Files")
sys.exit()
else:
count = 1
# Iterate through every pdf of the filepaths
for path in filepaths:
# Create a PdfFileWriter object
pdf_writer = PdfFileWriter()
# Open our PDF file with the PdfFileReader
pdf_reader = PdfFileReader(path)
# Get the page at index idx
for page in range(pdf_reader.getNumPages()):
# Add each page to the writer object
pdf_writer.addPage(pdf_reader.getPage(page))
# The output filename
output_file = f"merge_enc_{count}_{ts}.pdf"
# Encrypt the new file with the entered password
pdf_writer.encrypt(password, use_128bit=True)
# Write out the merged PDF
with open(output_file, 'wb') as file:
pdf_writer.write(file)
count += 1
print('File Written To Path:', output_file)
def PdfPassword(filepath, password):
# Check if file exists
checkFile = os.path.isfile(filepath)
if checkFile:
# Get the path of directory and filename
path, filename = os.path.split(filepath)
# Get the file extension to check for pdf files
file_extension = os.path.splitext(filepath)[1]
if file_extension == ".pdf":
# The output filename
output_file = os.path.join(path, f"temp_{ts}_{filename}")
# Create a PdfFileWriter object
pdf_writer = PdfFileWriter()
# Open our PDF file with the PdfFileReader
file = PdfFileReader(filepath)
# Get number of pages in original file
# Iterate through every page of the original file and add it to our new file
for idx in range(file.numPages):
# Get the page at index idx
page = file.getPage(idx)
# Add it to the output file
pdf_writer.addPage(page)
# Encrypt the new file with the entered password
pdf_writer.encrypt(password, use_128bit=True)
# Open a new file
with open(output_file, "wb") as file:
# Write our encrypted PDF to this file
pdf_writer.write(file)
print('File Written To Path:', output_file)
else:
# File extension is not PDF
print(
f"Not A PDF File Given, File Has Extension: {file_extension}")
sys.exit()
else:
# No file exists on the current path
print("Check The File Path")
sys.exit()
def RemovePdfOwnerPassword(inputname, outputname):
'''
'''
inputfile = open(inputname, 'rb')
wrt = PdfFileWriter()
ipt = PdfFileReader(inputfile)
try:
ipt.decrypt("")
except KeyError as e:
if e.message == '/Encrypt':
print("%s is not an encrypted pdf" % inputname)
return -1
else:
raise e
print(ipt.getDocumentInfo())
size = ipt.getNumPages()
i = 0
while i < size:
page = ipt.getPage(i)
#print(page.extractText())
wrt.addPage(page)
i = i + 1
fl = open(outputname, "wb")
wrt.write(fl)
inputfile.close()
fl.close()
return 0
def run(self):
if self.beforeHandler(self._id, self.attachUrl):
return
filename = self.tempDir + str(random.random())
filename1 = self.tempDir + str(random.random()) + '.pdf'
try:
urllib.request.urlretrieve(self.attachUrl, filename)
input_stream = open(filename, 'rb')
pdf_input = PdfFileReader(input_stream)
pdf_output = PdfFileWriter()
page = 0
pages = pdf_input.getNumPages() - 1
# remove last page
while page < pages:
pdf_output.addPage(pdf_input.getPage(page))
page += 1
output_stream = open(filename1, 'wb')
pdf_output.write(output_stream)
output_stream.close()
input_stream.close()
if self.success is not None:
self.success(self._id, filename1)
except Exception as e:
if self.error is not None:
self.error(e, self.attachUrl)
finally:
if os.path.exists(filename):
os.remove(filename)
if os.path.exists(filename1):
os.remove(filename1)
def generate_a_pdf(filename, num_pages, dir=None):
"""function to generate a random PDF file of N pages with single image per page
taken from https://stackoverflow.com/questions/2925484/place-image-over-pdf
Args:
filename (str): path to save the pdf file
num_pages (int): number of pages to make the pdf file
KWArgs:
dir (str): the path to the directory to save the pdf file
Returns:
str. path to the new pdf file
"""
pdf = PdfFileWriter()
for num in range(1, num_pages+1):
imgTemp = BytesIO()
jpeg_path = make_a_jpeg('{}.jpeg'.format(str(num)), pick_a_color(num))
imgDoc = canvas.Canvas(imgTemp, pagesize=A4)
imgDoc.drawImage(jpeg_path, 25, 45)
imgDoc.save()
pdf.addPage(PdfFileReader(BytesIO(imgTemp.getvalue())).getPage(0))
remove(jpeg_path)
if dir:
path = join(dir, filename)
else:
path = join(getcwd(), filename)
pdf.write(open(path, 'wb'))
return path
def __getPdfTxtAt(self,pageNum,bENHANCE):
# print('---->>>>>'+str(pageNum))
try:
RESOLUTION = 250
tempoutPdfName = 'temp.pdf'
tempoutPdfNameWithAbsPath = os.path.join(self.__RootPath,tempoutPdfName)
if os.path.exists(tempoutPdfNameWithAbsPath):
os.remove(tempoutPdfNameWithAbsPath)
pdfWriter = PdfFileWriter() #生成一个空白的pdf文件
pdfWriter.addPage(self.pdfReader.getPage(pageNum))
with open(tempoutPdfNameWithAbsPath,'wb') as pdfOutput:
pdfWriter.write(pdfOutput) #将复制的内容全部写入合并的pdf
try:
with Image(filename=tempoutPdfNameWithAbsPath,resolution=RESOLUTION) as image_pdf:
image_jpeg = image_pdf.convert('jpeg')
except Exception as e:
raise e
raise(r'Image(filename=tempoutPdfNameWithAbsPath,resolution=RESOLUTION) occurs error!' )
quit = input("按任意键退出...")
sys.exit(1)
try:
# img_page = Image(image=image_jpeg)
req_image = image_jpeg.make_blob('jpeg')
except Exception as e:
raise e
print('make_blob or ERROR! '+ str(pageNum)+' 页失败！')
quit = input("按任意键退出...")
sys.exit(1)
try:
image_filtered = PI.open(io.BytesIO(req_image))
# image_filtered= image_filtered.filter(ImageFilter.GaussianBlur(radius=1))
# if bENHANCE:
# image_filtered= image_filtered.filter(ImageFilter.EDGE_ENHANCE)
except Exception as e:
raise e
print('PI.open ERROR! '+ str(pageNum)+' 页失败！')
quit = input("按任意键退出...")
sys.exit(1)
try:
# print('>>> Debug:'+self.__lang)
txt = self.__tool.image_to_string(
image_filtered,
lang=self.__lang,
builder=pyocr.builders.TextBuilder()
)
except Exception as e:
raise e
print('image_to_string '+ str(pageNum)+' 页失败！')
quit = input("按任意键退出...")
sys.exit(1)
if os.path.exists(tempoutPdfNameWithAbsPath):
os.remove(tempoutPdfNameWithAbsPath)
return txt
except Exception as e:
raise e
print('获取第 '+ str(pageNum)+' 页失败！')
quit = input("按任意键退出...")
sys.exit(1)
def merge_pdf(file_list, output_path):
'''合并 PDF'''
outpdf = PdfFileWriter()
for f in file_list:
f_pdf = PdfFileReader(open(f, 'rb'))
for page in f_pdf.pages:
outpdf.addPage(page)
ous = open(output_path, 'wb')
outpdf.write(ous)
ous.close()
def _create_hyperlinks(self, link_locations, page_locations):
reader = PdfFileReader("tmp2.pdf")
writer = PdfFileWriter()
for i in range(reader.getNumPages()):
page = reader.getPage(i)
writer.addPage(page)
for i in range(len(link_locations)):
toc_page = 1
if self.toc_orientation == "P":
toc_page = math.floor(i / settings["Items on vertical toc"])
if self.toc_orientation == "L":
toc_page = math.floor(i / settings["Items on horizontal toc"])
writer.addLink(pagenum=toc_page,
pagedest=page_locations[i] - 1,
rect=link_locations[i],
fit="/Fit",
border=[0, 0, 0])
with open(self.filename, 'wb') as out:
writer.write(out)
def pdfSplit(pdf_main, pdf_part):
try:
pdf_read_obj = PdfFileReader(pdf_main)
pdf_write_obj = PdfFileWriter()
page_num = pdf_read_obj.getNumPages()
page_last_obj = pdf_read_obj.getPage(page_num - 1)
page_last_obj.rotateClockwise(90)
pdf_write_obj.addPage(page_last_obj)
pdf_write_obj.write(open(pdf_part, 'wb'))
return page_num - 1
except Exception as e:
return False
def add_number(p, n, x, y, counter=1):
base_pdf = copy.copy(p.getPage(0))
wm_pdf = PdfFileReader(io.BytesIO(n)).getPage(0)
pdf_writer = PdfFileWriter()
base_pdf.mergeTranslatedPage(wm_pdf, x, y)
pdf_writer.addPage(base_pdf)
saveloc = Path.cwd().joinpath("numbering", "assets",
"numbered", f"{counter}.pdf")
with open(saveloc, "wb") as outfile:
pdf_writer.write(outfile)
return
def getTitlePDFfromBookmarkfile(pdf_filepath, bookmark_filepath,
pdf_filepath_output):
bookmark_file = codecs.open(bookmark_filepath, 'r', encoding='utf-8')
lines = bookmark_file.readlines()
page_start = 0
for i, line in enumerate(lines):
# print(line)
if line.find(u'目录') >= 0:
line = line.strip()
print(line)
print(line.split('\t'))
page_start = int(line.split('\t')[1])
page_start -= 1
print(page_start)
page_end = 0
page_list = []
for i, line in enumerate(lines):
line = line.strip()
# print(line)
if line.find('\t') >= 0:
# print(int(line.rsplit('\t',1)[1]))
page_list.append(int(line.rsplit('\t', 1)[1]))
# page_list=page_list.sort()
# print(page_list)
for i in range(0, len(page_list)):
if page_list[i] > page_start:
page_end = page_list[i]
break
page_end -= 1
print(page_end)
if page_end <= page_start and page_start >= 0 and page_end > 0:
print('not find title page')
return
pdf = PdfFileReader(open(pdf_filepath, "rb"))
output = PdfFileWriter()
for i in range(page_start, page_end + 1):
output.addPage(pdf.getPage(i))
# dst_pdf.addPage(pdf.getPage(i))
# pdf_bytes = io.BytesIO()
# output.write(pdf_bytes)
# pdf_bytes.seek(0)
# img = Image(file=pdf_bytes, resolution=300)
# img.convert("png")
# img.save(pdf_filepath_output+'_out.tif')
stream = open(pdf_filepath_output, 'wb')
output.write(stream)
def process_pdf_automatically(self):
self.statusBar().showMessage('Procesando...')
# print("File Name:", self.name)
if self.name != "":
self.dir = QFileDialog.getExistingDirectory()
ls = []
files = [x for x in os.listdir(self.dir + '/') if
x.endswith('.pdf') and x != "join.pdf"]
outfile = PdfFileWriter()
bancos = ['bbva', 'santander']
for i in files:
pdf = PdfFileReader(open(self.dir + '/' + str(i), 'rb'))
page = pdf.getPage(0)
pages = pdf.getNumPages()
last = pdf.getPage(pages - 1)
text = last.extractText()
banco = re.findall("(bbva|santander)", text.lower())
text = page.extractText()
fecha = \
re.findall("(corte.*[0-9]{1,2}[/][0-9]{1,2}[/][0-9]{2,4})",
text.lower())[0]
fecha = \
re.findall("([0-9]{1,2}[/][0-9]{1,2}[/][0-9]{2,4})", fecha)[0]
ls.append({'page': page,
'bank': Counter(banco).most_common()[0][0].upper(),
'date': fecha})
fecha = []
for i in ls:
fecha.append(i['date'])
fecha.sort(key=lambda date: datetime.strptime(date, '%d/%m/%Y'))
for i in fecha:
for x in ls:
if (x['date'] == i):
outfile.addPage(x['page'])
self.statusBar().showMessage('Creando PDF...')
save_in = self.dir + '/' + self.name + '.pdf'
with open(save_in, 'wb') as f:
outfile.write(f)
self.statusBar().showMessage('Creación del PDF Exitosa')
self.show_dialog("Acción realizada con éxito")
else:
self.show_dialog("No fue posible crear el archivo PDF")
self.statusBar().showMessage('')
def pdf2cut(pdf_in, pdf_out, axis_x, axis_y, width, height):
pdf_read_obj = PdfFileReader(open(pdf_in, 'rb'))
pdf_write_obj = PdfFileWriter()
for page in pdf_read_obj.pages:
page.mediaBox.setUpperLeft((axis_x, axis_y))
page.mediaBox.setUpperRight((width, height))
page.mediaBox.setLowerLeft((axis_x, axis_y - height))
page.mediaBox.setLowerRight((axis_x + width, axis_y - height))
pdf_write_obj.addPage(page)
with open(pdf_out, 'wb') as f:
pdf_write_obj.write(f)
f.close()
return pdf_out
def _merge_pdfs(self, in_dir, out_file):
"""Merges PDFs in a given directory and outputs it to a single PDF file.
If `same_page_number` is set to true in the config file, all tests will have `max_pages` number of pages.
Parameters:
in_dir (str): Path to the input directory containing the PDF files to be merged.
out_file (str): Path to the merged PDF.
"""
pw = PdfFileWriter()
firstPDF = True
for f in sorted(listdir(in_dir)):
if isfile(join(in_dir, f)) and regex.match(
'^test.*\.pdf$', f, flags=regex.IGNORECASE):
pr = PdfFileReader(join(in_dir, f), strict=False)
form = pr.trailer["/Root"][
"/AcroForm"] # see: https://stackoverflow.com/questions/47288578/pdf-form-filled-with-pypdf2-does-not-show-in-print
pw.appendPagesFromReader(pr)
if self.config['same_page_number'] and pr.getNumPages(
) < self.config['max_pages']:
for i in range(self.config['max_pages'] -
pr.getNumPages()): # pylint: disable=unused-variable
pw.addBlankPage()
if firstPDF:
pw._root_object.update({NameObject("/AcroForm"): form})
firstPDF = False
else:
pw._root_object["/AcroForm"]["/Fields"].extend(
form["/Fields"])
pw._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
f = codecs.open(out_file, 'wb')
pw.write(f)
f.close()
def split_pdf(inFile, outFile):
'''
拆分文档
:param inFile: 输入文件
:param outFile: 输出文件
:return:
'''
pdfFileWriter = PdfFileWriter()
pdfFileReader = PdfFileReader(open(inFile, 'rb'))
page_count = pdfFileReader.getNumPages()
print(page_count)
# 将 pdf 第2页之后的页面，输出到一个新的文件
for i in range(2, page_count):
pdfFileWriter.addPage(pdfFileReader.getPage(i))
pdfFileWriter.write(open(outFile, 'wb'))
def createNewBooks(self, pdf_file, stPage, endPage, filename='my.pdf'):
input = PdfFileReader(open(pdf_file, "rb"))
if input.isEncrypted: #注意：所有的pdf，pypdf2默认都是加密形式，所以要先解密再读取
input = input.decrypt('')
pdf_input = input
pdf_output = PdfFileWriter()
i = stPage
while i < endPage:
page = pdf_input.getPage(i) # 选取需要页面，需要注意的是第一页的编号是0
pdf_output.addPage(page) # 将选好的页面加入到新的pdf中
i += 1
output_stream = open(filename, 'wb')
pdf_output.write(output_stream)
output_stream.close()
return 'Complete knifing'
def _removePropertyEndPage(self, file_pdf):
'''移除资产明细表中的无用页'''
fd_in = open(file_pdf, "rb")
pdf_in = PdfFileReader(fd_in)
page_num = pdf_in.getNumPages()
pdf_out = PdfFileWriter()
for num in range(page_num - 1):
page = pdf_in.getPage(num)
pdf_out.addPage(page)
fd_out = open(file_pdf + 'tmp.pdf', "wb")
pdf_out.write(fd_out)
fd_in.close()
fd_out.close()
os.remove(file_pdf)
os.rename(os.path.join('', file_pdf + 'tmp.pdf'),
os.path.join('', file_pdf))
print(' > 已把最后一页删除')
def pdf_cat(input_files, output_stream):
"""https://stackoverflow.com/questions/3444645/merge-pdf-files"""
input_streams = []
try:
# First open all the files, then produce the output file, and
# finally close the input files. This is necessary because
# the data isn't read from the input files until the write
# operation. Thanks to
# https://stackoverflow.com/questions/6773631/problem-with-closing-python-pypdf-writing-getting-a-valueerror-i-o-operation/6773733#6773733
for input_file in input_files:
input_streams.append(input_file)
writer = PdfFileWriter()
for reader in map(PdfFileReader, input_streams):
for n in range(reader.getNumPages()):
writer.addPage(reader.getPage(n))
writer.write(output_stream)
finally:
for f in input_streams:
f.close()
def fetchANs(bols, client, workOrderLocation):
pdfs = []
doneBols = []
failedPDFs = ""
for bol in bols:
if bol != "" and not bol in doneBols:
doneBols.append(bol)
tickets = client.ticket_search(Title="Delivery Order for BL# " +
bol,
From="@msc.com")
pdf = getPdf(tickets)
if pdf:
pdfs.append(pdf)
with open(workOrderLocation + "\\" + "DOs.pdf", 'wb') as f:
input_streams = []
try:
# First open all the files, then produce the output file, and
# finally close the input files. This is necessary because
# the data isn't read from the input files until the write
# operation. Thanks to
# https://stackoverflow.com/questions/6773631/problem-with-closing-python-pypdf-writing-getting-a-valueerror-i-o-operation/6773733#6773733
i = 0
for input_file in pdfs:
f1 = open(input_file, 'r+b')
input_streams.append(f1)
i += 1
writer = PdfFileWriter()
for reader in map(PdfFileReader, input_streams):
for n in range(reader.getNumPages()):
writer.addPage(reader.getPage(n))
writer.write(f)
finally:
for f in input_streams:
f.close()
else:
failedPDFs = "\n" + bol + failedPDFs
for pdf in pdfs:
os.remove(pdf)
if failedPDFs != "":
popUpOK("Could not find the following BOLs: " + failedPDFs)
def get(self, request, *args, **kwargs):
fontname_g = "HeiseiMin-W3"
pdfmetrics.registerFont(UnicodeCIDFont(fontname_g))
reader = PdfFileReader('media/pdf/riyuu-format4.pdf')
writer = PdfFileWriter()
buffer = io.BytesIO()
cc = canvas.Canvas(buffer)
cc.setFont(fontname_g, 11)
initial = 295
before_rect_x = 748
after_rect_x = 776.5
line_height = 11.9
input_list = [{
'label': '便器からの立ち座り',
'before_flag': True,
'after_flag': False
}, {
'label': 'トイレまでの移動',
'before_flag': False,
'after_flag': True
}, {
'label': 'トイレ出入口の出入（扉の開閉含む）',
'before_flag': True,
'after_flag': False
}]
welfare_equipment_material = PdfMaterial.objects.get(
key="welfare_equipment")
cc = self.motion_purpose_draw(cc, before_rect_x, after_rect_x,
welfare_equipment_material.materials,
input_list, initial, line_height)
cc.showPage()
cc.save()
buffer.seek(0)
new_pdf = PdfFileReader(buffer)
existing_page = reader.getPage(0)
existing_page.mergePage(new_pdf.getPage(0))
writer.addPage(existing_page)
new = io.BytesIO()
writer.write(new)
new.seek(0)
print('finish')
return FileResponse(new, as_attachment=True, filename='hello.pdf')
def get(self, request, *args, **kwargs):
fontname_g = "HeiseiKakuGo-W5"
pdfmetrics.registerFont(UnicodeCIDFont(fontname_g))
buffer = io.BytesIO()
cc = canvas.Canvas(buffer)
reader = PdfFileReader('media/pdf/sample.pdf')
existing_page = reader.getPage(0)
cc.setFont(fontname_g, 24)
cc.drawString(0, 820, "テスト")
cc.showPage()
cc.save()
buffer.seek(0)
new_pdf = PdfFileReader(buffer)
existing_page.mergePage(new_pdf.getPage(0))
writer = PdfFileWriter()
writer.addPage(existing_page)
new = io.BytesIO()
writer.write(new)
new.seek(0)
return FileResponse(new, as_attachment=True, filename='hello.pdf')
def mergePdf(inFileList, outFile):
'''
合并文档
:param inFileList: 要合并的文档的 list
:param outFile: 合并后的输出文件
:return:
'''
pdfFileWriter = PdfFileWriter()
#排序一下，不然合并序号不对
inFileList = sorted(inFileList)
for inFile in inFileList:
# 依次循环打开要合并文件
pdfReader = PdfFileReader(open(inFile, 'rb'))
numPages = pdfReader.getNumPages()
for index in range(0, numPages):
pageObj = pdfReader.getPage(index)
pdfFileWriter.addPage(pageObj)
# 最后,统一写入到输出文件中
pdfFileWriter.write(open(outFile, 'wb'))
def createNewBooks(self, pdf_file, output_file, output_dir):
if not os.path.exists(output_dir):
os.mkdir(output_dir)
input_stream = open(pdf_file, 'rb')
pdf_input = PdfFileReader(input_stream)
pdf_output = PdfFileWriter()
page = 0
pages = pdf_input.getNumPages() - 1
while page < pages:
pdf_output.addPage(pdf_input.getPage(page))
page += 1
outputfilename = output_dir + '/' + output_file
output_stream = open(outputfilename, 'wb')
pdf_output.write(output_stream)
output_stream.close()
input_stream.close()
def _getLtePropertyPrintPage(self, wbs_id, file_pdf, file_end):
'''生成要打印签字的资产明细页'''
print('---> 开始生成%s要打印签字的资产明细页' % (wbs_id))
(page_num,
page_end) = self._getPropertyKeyPage(file_pdf, self.key_yanshou)
fp_in = open(file_pdf, "rb")
pdf_in = PdfFileReader(fp_in)
pageCount = pdf_in.getNumPages()
if pageCount != page_num + 1:
print(' > PyPDF2(%d)及pdfminer(%d)判定文件页数不同' %
(pageCount, page_num))
self.dats_log.loc[self.log_index] = [
'E', wbs_id, 'PDF文件',
'PyPDF2(%d)及pdfminer(%d)判定文件页数不同,未生成最后签字页' %
(pageCount, page_num)
]
self.log_index += 1
return
if page_end == -1:
print(' > 未找到关键字【%s】所在的页，也即未找到最后签字页' % (self.key_yanshou))
self.dats_log.loc[self.log_index] = [
'E', wbs_id, 'PDF文件',
'未找到关键字【%s】所在的页，也即未找到最后签字页' % (self.key_yanshou)
]
self.log_index += 1
return
page = pdf_in.getPage(page_end)
pdf_out = PdfFileWriter()
pdf_out.addPage(page)
fp_out = open(file_end, 'wb')
pdf_out.write(fp_out)
fp_in.close()
fp_out.close()
print('---> 已获取资产明细最后一页并已保存至%s' % (file_end))
if page_num == page_end + 1:
print(' > 需把%s文件删除最后1页' % (file_pdf))
self._removePropertyEndPage(file_pdf)
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
