def test_sel_range(self):
"""Test select of more pages from a PDF file."""
run_stapler(['cat', 'A=' + FIVEPAGE_PDF, 'A2-4', self.outputfile])
self.assertTrue(os.path.isfile(self.outputfile))
with open(self.outputfile, 'rb') as outputfile:
pdf = PdfFileReader(outputfile)
self.assertEqual(pdf.getNumPages(), 3)
def convert_to_text(self):
f = open(self.input_file, 'rb')
pdf = PdfFileReader(f)
page = pdf.getPage(0)
text = page.extractText()
f.close()
return text
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 test_del_range(self):
"""Test del command for inverse select multiple pages."""
run_stapler(['del', 'A=' + FIVEPAGE_PDF, 'A2-4', self.outputfile])
self.assertTrue(os.path.isfile(self.outputfile))
with open(self.outputfile, 'rb') as outputfile:
pdf = PdfFileReader(outputfile)
self.assertEqual(pdf.getNumPages(), 2)
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 test_zip(self):
"""Test zip."""
run_stapler(['zip', 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 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 _create_pdf_from_rtf_files(self):
pdfs = []
self.progress.emit(0)
for count, file in enumerate(self.files):
changed_file = change_filetype(file, "pdf", self.engine)
pdfs.append(changed_file)
self.progress.emit(count + 1)
merger = PdfFileMerger()
pages = []
chapters = []
for file in pdfs:
read_pdf = PdfFileReader(file)
txt = read_pdf.getPage(0)
page_content = txt.extractText()
try:
chapter = helper_functions.get_chapter_from_pdf_txt(
page_content)
chapters.append(chapter)
except:
chapter = os.path.basename(file)
chapter = chapter.split(".")[0]
chapter = chapter.replace("_", " ")
chapters.append(chapter)
pages.append(read_pdf.getNumPages())
merger.append(fileobj=file)
self.pages = pages
self.chapters = chapters
if not self.create_toc:
merger.write(self.master_file_name)
else:
merger.write("tmp.pdf")
merger.close()
self.trash += pdfs
def extract_pdf_pypdf2(pdf_path):
with open(pdf_path, 'rb') as f:
pdf = PdfFileReader(f)
if pdf.isEncrypted:
pdf.decrypt('')
page_obj = pdf.getPage(2)
return page_obj.extractText()
def metadata(path: Path) -> Metadata:
"""
Reads a given PDF file and produces a Metadata object.
:param path: path to a PDF file
:return: the metadata extracted from the PDF file
"""
with path.open('rb') as f:
reader = PdfFileReader(f)
info = reader.getDocumentInfo()
page_count = reader.getNumPages()
typer.echo(f'PDF metadata: {info}', err=True)
# Decide which possible title to use:
# - the title annotated in the PDF metadata
# - the title read by pdftitle (largest text on the first page)
# - the file name without extension
pdftitle_title = pdftitle.get_title_from_file(str(path))
typer.echo(f'Title according to pdftitle: {pdftitle_title}', err=True)
title_candidates = [t for t in [info.title, pdftitle_title, path.stem] if t is not None]
# The current heuristic is just to use the longest of the three candidates
title = max(title_candidates, key=len)
return Metadata(
title=title,
author=info.author,
page_count=page_count
)
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 translate(self):
'''读取pdf内容，并翻译，写入txt文件'''
f = open(self.fullPath, 'rb')
pdf = PdfFileReader(f)
index = 0
for i in range(0, pdf.getNumPages()):
extractedText = pdf.getPage(i).extractText()
content = extractedText.split('\n')
content = self.removeBlankFromList(content)
# 拼接之后的文本，如果单词间歇超过一个空格的，认为是需要换行处理的
content_list = self.enter_symbol(content)
for line in content_list:
line = line.strip()
if line:
ret = translate_func(line)
trans = ret if ret else '翻译失败'
self.write(line + '\n')
self.write(trans)
index += 1
print(index, end=' ', flush=True)
f.close()
Logger().write(self.fileName + '翻译完成，新文档：' + self.new_fullPath)
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 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 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
class PdfInput:
def __init__(self, filename):
self.filename = filename
self.stream = open(filename, "rb")
self.pdf_reader = PdfFileReader(self.stream)
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.close()
def close(self):
self.stream.close()
def get_number_of_pages(self):
return self.pdf_reader.getNumPages()
def get_page_text(self, pageno):
page = self.pdf_reader.getPage(pageno - 1)
return page.extractText()
def get_page_image(self, pageno):
with tempfile.NamedTemporaryFile() as tmp_file:
with self._open_page_image(pageno, tmp_file.name) as image:
image.load()
return image
def get_page_png_file(self, pageno):
tmp_file = tempfile.NamedTemporaryFile(suffix=".png")
with self._open_page_image(pageno, tmp_file.name) as image:
image.save(tmp_file)
return tmp_file
def _open_page_image(self, pageno, image_file):
print("pdf -> png...", file=sys.stderr)
subprocess.run([
"gs",
"-sDEVICE=png16m",
"-dNOPAUSE",
"-dFirstPage={}".format(pageno),
"-dLastPage={}".format(pageno),
"-sOutputFile={}".format(image_file),
"-r300",
"-q",
self.filename,
"-c",
"quit"],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL)
return load(image_file)
def getPdffileBookmark(filename, bookmark_file_savepath):
pdf = PdfFileReader(open(filename, "rb"))
pagecount = pdf.getNumPages()
print('pagecount:', pagecount)
pageLabels = {
} #真实页码的索引 indirectRef “{'/Type': '/Fit', '/Page': IndirectObject(7871, 0), '/Title': '封面'}”
for i in range(pagecount):
page = pdf.getPage(i)
pageLabels[page.indirectRef.idnum] = i + 1
# print(page.indirectRef.idnum,i+1)
bookmark_file = codecs.open(bookmark_file_savepath, 'w', encoding='utf-8')
title = []
pagedir = []
bookmark_jibie = []
outlines = pdf.getOutlines()
print(outlines)
index = 0
jibie = 0
for outline in outlines:
index += 1
jibie = 0
print(len(outline), outline)
if type(outline) == PyPDF2.generic.Destination:
# print('dict--------')
# print(list(outline.keys()))
# for x,j in enumerate(list(outline.keys())):
# print(str(outline[j]))
# print(outline['/Title'])
# print(outline['/Type'])
# print(outline.page.idnum)
bookmark_file.write(outline['/Title'] + '\t' +
str(pageLabels[outline.page.idnum]) + '\r\n')
if type(outline) == list:
# print('list')
jibie = 1
for i, outline in enumerate(outline):
if type(outline) == PyPDF2.generic.Destination:
bookmark_file.write('\t' * jibie + outline['/Title'] +
'\t' +
str(pageLabels[outline.page.idnum]) +
'\r\n')
elif type(outline) == list:
jibie = 2
for i, o in enumerate(outline):
if type(outline) == PyPDF2.generic.Destination:
bookmark_file.write(
'\t' * jibie + outline['/Title'] + '\t' +
str(pageLabels[outline.page.idnum]) + '\r\n')
# print('\n')
# if index>=3:
# break
bookmark_file.close()
def test_split(self):
"""Make sure a file is properly split into pages."""
run_stapler(['split', FIVEPAGE_PDF])
filelist = os.listdir(self.tmpdir)
self.assertEqual(len(filelist), 5)
for f in os.listdir(self.tmpdir):
with open(os.path.join(self.tmpdir, f), 'rb') as pdf_file:
pdf = PdfFileReader(pdf_file)
self.assertEqual(pdf.getNumPages(), 1)
def convertPDFAlternative(self, path):
from PyPDF2.pdf import PdfFileReader
if not os.path.exists(path):
return False
pdf = PdfFileReader(open(path, "rb"))
for i in range(0, pdf.getNumPages()):
print(i)
extractedText = pdf.getPage(i).extractText()
self.pages.append(extractedText)
return True
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 _extract_pdf_forms(self, fname):
"""Extracts interactive form fields data from a PDF file.
Parameters:
fname (str): Path to PDF file.
Returns:
dict: Form fields data extracted.
"""
f = PdfFileReader(fname)
return f.getFields()
def getDataUsingPyPdf2(filename):
pdf = PdfFileReader(open(filename, "rb"))
content = ""
for i in range(0, pdf.getNumPages()):
#print(str(i))
extractedText = pdf.getPage(i).extractText()
content += extractedText + "\n"
content = " ".join(content.replace("\xa0", " ").strip().split())
return content.encode("ascii", "ignore")
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 __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 __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 set_bglj(self, filename):
if filename.endswith('.pdf'):
self.user_data['bgms'] = '1'
# 获取PDF 页码
try:
pdf_read_obj = PdfFileReader(filename)
self.user_data['bgym'] = pdf_read_obj.getNumPages()
except Exception as e:
self.user_data['bgym'] = 0
print("获取报告页码出错，错误信息：%s" % e)
else:
self.user_data['bgms'] = '0'
self.user_data['bglj'] = self.cur_dir
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 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 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 calculate_locations(filename,keywords):
locations = []
fp = open(filename, 'rb')
parser = PDFParser(fp)
# Create a PDF document object that stores the document structure.
# Supply the password for initialization.
document = PDFDocument(parser)
# Check if the document allows text extraction. If not, abort.
if not document.is_extractable:
raise PDFTextExtractionNotAllowed
# Create a PDF resource manager object that stores shared resources.
rsrcmgr = PDFResourceManager()
# Create a PDF device object.
device = PDFDevice(rsrcmgr)
# Create a PDF interpreter object.
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
for page in PDFPage.create_pages(document):
interpreter.process_page(page)
#Set parameters for analysis.
laparams = LAParams()
# Create a PDF page aggregator object.
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
pages = PDFPage.create_pages(document)
pagenum = 0
reader = PdfFileReader(file(filename,"rb"))
for page in pages:
interpreter.process_page(page)
# receive the LTPage object for the page.
layout = device.get_result()
page = reader.getPage(pagenum)
x = page.trimBox[0].as_numeric()
y = page.trimBox[1].as_numeric()
#Handling special case
if (x > 0 and y < 0):
x = 0
# print "At page = %s X = %s , y = %s"%(pagenum,x,y)
for keyword in keywords:
print '********************************'
co_ordinates = get_location(keyword,layout,x,y)
print'Keyword %s , location %s'%(keyword,co_ordinates)
print '********************************'
if co_ordinates != None :
for location in co_ordinates:
print "PageNum-->%s"%pagenum
l = LocationKeeper(keyword,location,pagenum)
locations.append(l)
pagenum+=1
return locations
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 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 enumerate_pages(files, options, style=0, start=None, page_map=None, write_pages=False, no_filler_before=None, verbose=False):
pages = []
if start == None:
start = 1 if style == 0 else 'A'
counter = start
# Read filler pages if filler needs to be interlaced
filler = None
if no_filler_before: filler = add_filler(options)
valid_filler_indeces = []
for file in files:
check_stop_script()
try:
# Save page num assignment to map
if page_map != None: page_map[counter] = file
if filler and file not in no_filler_before: valid_filler_indeces.append(len(pages))
# Read input file
input = PdfFileReader(open(file, 'rb'))
num_pages = input.getNumPages()
page_num = f'{counter}'
# Add all the pages to the list
for i in range(num_pages):
input_page: PageObject = input.getPage(i)
# Verify that it has the proper dimensions
mediabox = input_page.mediaBox
if not validate_mediabox(mediabox, options):
thread_print(f'WARNING: Page {i + 1} in "{file}" has incorrect dimensions\nExpected {options["page-size"]["width"]} x {options["page-size"]["height"]}, received {float(mediabox.getWidth()) / inch} x {float(mediabox.getHeight()) / inch}.')
continue
# Calculate this page number
if not write_pages: continue
if num_pages > 1: page_num = f'{counter}.{i + 1}'
pages.append(add_page_num(input_page, page_num, options) if options["enumerate-pages"] else input_page)
except OSError:
thread_print(f'Error when parsing "{file}"')
# Increment Counter
counter = (counter + 1) if style == 0 else (chr(ord(counter) + 1))
# Interlace filler (if applicable)
if filler: interlace_filler(pages, filler, valid_filler_indeces)
return pages
def getPDFInformation(filepath):
"""
Read information of pdf file (title, author)
:param filepath: filepath to pdf file
:return: dict with title and author information
"""
with open(filepath, 'rb') as f:
reader = PdfFileReader(f)
info = reader.getDocumentInfo()
ret = {}
if "/Title" in info:
ret['title'] = info['/Title']
else:
ret['title'] = filepath.split('/')[-1]
if "/Author" in info:
ret['author'] = info['/Author']
else:
ret['author'] = ""
return ret
def getFormFields(filepath):
"""
Get field information of pdf file
:param filepath: filepath to pdf file
:return: list with tuples of (field name, field type) as counter to find multi fields
"""
fields = []
with open(filepath, 'rb') as f:
reader = PdfFileReader(f)
for k, v in reader.getFields().iteritems():
if re.search('^\s*[0-9]', v['/T']):
fields.append(("_".join(v['/T'].split('_')[1:]), FIELDTYPES[v['/FT']]))
else:
fields.append((v['/T'], FIELDTYPES[v['/FT']]))
ret = OrderedDict()
for k, v in iter(sorted(Counter(fields).iteritems())):
ret[k[0].encode('utf-8')] = (k[1].encode('utf-8'), v)
return ret
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
