def split(input_path, page_ranges, output_name):
"""
Extracts the specified page ranges from a pdf.
Enter the input paths, then the desired page ranges (as single page numbers or hyphen separated ranges) and finally the output path.
The output pdfs will be named '<output_name>_p<page_range>'.
"""
for page_range in page_ranges:
input_pdf = PdfFileReader(input_path)
pdf_writer = PdfFileWriter()
start, stop = format_range(page_range)
for page in range(start, stop):
pdf_writer.addPage(input_pdf.getPage(page))
output = f"{output_name}_p{page_range}.pdf"
with open(output, 'wb') as output_pdf:
pdf_writer.write(output_pdf)
def split_pdf(self, path: str, name_of_split: str):
"""
切分pdf文件
path: 原始文件存放路径
name_of_split:切分后的文件名，不包含后缀
"""
pdf = PdfFileReader(path)
pdf_writer = PdfFileWriter()
for page in range(pdf.getNumPages()):
pdf_writer.addPage(pdf.getPage(page))
output = self.processed + name_of_split + str(page) + ".pdf"
with open(output, 'wb') as output_pdf:
pdf_writer.write(output_pdf)
# print("切分完成！")
return "切分完成！"
def addBlankpage():
# PDF写入操作
readFile = './01.pdf'
outFile = './01_new.pdf'
pdfFileWriter = PdfFileWriter()
# 获取 PdfFileReader 对象
pdfFileReader = PdfFileReader(readFile) # 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 add_watermark(orig_cover, key):
c = canvas.Canvas('watermark.pdf')
if key == 0:
c.drawImage(CONST_ENGLISH, 190, 220)
elif key == 1:
c.drawImage(CONST_MATH, 220, 220)
elif key == 2:
c.drawImage(CONST_READING, 190, 220)
elif key == 3:
c.drawImage(CONST_SCIENCE, 190, 220)
c.save()
watermark = PdfFileReader(open("watermark.pdf", "rb"))
orig_cover.mergePage(watermark.getPage(0))
os.remove("watermark.pdf")
return orig_cover
def pdfConcat(inputFiles, outputFileName, testPath):
pdfWriter = PdfFileWriter()
temp = open(testPath, 'rb')
pdf = PdfFileReader(temp)
pdfWriter.addPage(pdf.getPage(0))
for filePath in inputFiles:
f = open(filePath, 'rb')
pdfReader = PdfFileReader(f)
for page in pdfReader.pages[1:]:
pdfWriter.addPage(page)
with open(outputFileName, 'wb') as out:
pdfWriter.write(out)
temp.close()
def add_page(self, path: str):
"""
添加空白页面
path:文件完整路径
"""
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(path)
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
pdf_writer.addBlankPage() # 插入空白页面
with open("./processed/add_blank.pdf", "wb") as f:
pdf_writer.write(f)
# print("加入空白页完成！")
return "添加空白页完成！"
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()
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 merge_doc(self):
'''合并封面和文件'''
self.file_lists = list(
zip(self.doc_code, self.name_list, self.final_names))
for pdfnames in self.file_lists:
output = PdfFileWriter()
for pdfname in pdfnames[0:2]:
input = PdfFileReader(open(pdfname, "rb"), strict=False)
pageCount = input.getNumPages()
for iPage in range(0, pageCount):
output.addPage(input.getPage(iPage))
pdfoutname = str(pdfnames[2])
outputStream = open(pdfoutname, "wb")
output.write(outputStream)
outputStream.close()
print("文件合并完成：", pdfoutname)
print("文件合并完成！")
print("=><=" * 25)
def decrypt_pdf(input_file: str, password: str):
"""
Decrypts a file using PyPDF4 library.
Precondition: A file is already encrypted
"""
pdf_reader = PdfFileReader(open(input_file, 'rb'), strict=False)
if not pdf_reader.isEncrypted:
print(f"PDF File {input_file} not encrypted")
return False, None, None
pdf_reader.decrypt(password=password)
pdf_writer = PdfFileWriter()
try:
for page_number in range(pdf_reader.numPages):
pdf_writer.addPage(pdf_reader.getPage(page_number))
except utils.PdfReadError as e:
print(f"Error reading PDF File {input_file} = {e}")
return False, None, None
return True, pdf_reader, pdf_writer
def merge_pdfs(paths, output):
pdf_writer = PdfFileWriter()
for path in paths:
print(f'path {path[1]} {path[0]}')
pdf_reader = PdfFileReader(path[0])
for idx in range(pdf_reader.getNumPages()):
page = pdf_reader.getPage(idx)
if USE_SCALING:
if path[1] == 'A4':
print('scaling...')
page.scaleTo(812, 595)
else:
print('merge as is...')
pdf_writer.addPage(page)
with open(output, 'wb') as out:
pdf_writer.write(out)
def parse(pdf_file):
"""解析PDF文本，并保存到TXT文件中"""
fp = open(pdf_file, 'rb')
# 来创建一个pdf文档分析器
parser = PDFParser(fp)
# 创建一个PDF文档对象存储文档结构
document = PDFDocument(parser)
# 检查文件是否允许文本提取
if not document.is_extractable:
print('nono')
raise PDFTextExtractionNotAllowed
else:
# 创建一个PDF资源管理器对象来存储共赏资源
rsrcmgr = PDFResourceManager()
# 设定参数进行分析
laparams = LAParams()
# 创建一个PDF设备对象
# device=PDFDevice(rsrcmgr)
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
# 创建一个PDF解释器对象
interpreter = PDFPageInterpreter(rsrcmgr, device)
# 处理每一页
pageindex = []
i = 0
pattern = re.compile("微信")
for page in PDFPage.create_pages(document):
interpreter.process_page(page)
# # 接受该页面的LTPage对象
layout = device.get_result() # return text image line curve
for x in layout:
if isinstance(x, LTText):
if pattern.search(x.get_text()):
pageindex.append(i)
i += 1
pdf_output = PdfFileWriter()
pdf_input = PdfFileReader(fp)
# 获取 pdf 共用多少页
for j in pageindex:
pdf_output.addPage(pdf_input.getPage(j))
final_path = os.path.join(r"C:\Users\big\Desktop\final.pdf")
with open(final_path, "wb") as f:
pdf_output.write(f)
fp.close()
def merge_pdf(self, file_list, outpdf):
"""
合并pdf文件
outpdf: 输出的pdf名称，不包含路径,如：merge_res.pdf
"""
pdf_writer = PdfFileWriter()
for eve in file_list:
pdf_reader = PdfFileReader(eve)
for page in range(pdf_reader.getNumPages()):
# 将每一页添加到writer对象中
pdf_writer.addPage(pdf_reader.getPage(page))
# 写入合并的pdf文件
with open(self.processed + outpdf, "wb") as f:
pdf_writer.write(f)
# print("合并完成！")
return "合并完成！"
def merge_pdfs(paths, output):
"""Combine individually downloaded dashboard files into a compile report. Optionally scales the PDF."""
pdf_writer = PdfFileWriter()
for path in paths:
file_log.debug(f'path {path[1]} {path[0]}')
pdf_reader = PdfFileReader(path[0])
for idx in range(pdf_reader.getNumPages()):
page = pdf_reader.getPage(idx)
if USE_SCALING:
if path[1] == 'A4':
file_log.debug('scaling...')
page.scaleTo(812, 595)
else:
file_log.debug('merge as is...')
pdf_writer.addPage(page)
with open(output, 'wb') as out:
pdf_writer.write(out)
def extractImages():
# parser = argparse.ArgumentParser(prog='PDFtoImage',description='Extracting images from PDF')
# parser.add_argument('infile', help='Enter name for input source PDF file')
# args = parser.parse_args()
# fileName= args.infile
filePDF = join(workDir, fileName + ext)
pdfReader = PdfFileReader(open(filePDF, "rb"))
for pgNum in range(pdfReader.numPages):
page = pdfReader.getPage(pgNum)
xObject = page['/Resources']['/XObject'].getObject()
for obj in xObject:
if xObject[obj]['/Subtype'] == '/Image':
size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
data = xObject[obj].getData()
if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
mode = "RGB"
else:
mode = "P"
if xObject[obj]['/Filter'] == '/FlateDecode':
img = Image.frombytes(mode, size, data)
outFile = join(workDir, f'{pgNum}_{fileName}{png}')
img.save(outFile)
elif xObject[obj]['/Filter'] == '/DCTDecode':
img = Image.open(io.BytesIO(data))
outFile = join(workDir, f'{pgNum}_{fileName}{jpg}')
img.save(outFile)
# img = open(join(workDir, f'{pgNum} {fileName}{jpg}'), "wb")
# img.write(data)
# img.close()
elif xObject[obj]['/Filter'] == '/JPXDecode':
img = open(join(workDir, f'{pgNum} {fileName}{jp2}'), "wb")
img.write(data)
img.close()
elif xObject[obj]['/Filter'] == '/CCITTFaxDecode':
img = open(join(workDir, f'{pgNum} {fileName}{tiff}'),
"wb")
img.write(data)
img.close()
def pdf_to_pdfs(pdf_folder, page_count):
"""
将单页的pdf文件合并成整个文件
:param pdf_folder:
:param page_count:
:return:
"""
# 创建一个pdf空白文档
pdf_writer = PdfFileWriter()
pdf_file_path = '{}/{}.pdf'.format(pdf_folder, 'combine')
# 读取每页的pdf
for page_index in range(page_count):
page_pdf_file = '{}/{}.pdf'.format(pdf_folder, page_index)
# 读取单页的pdf
# 开始进行pdf 到 image的转换
reader = PdfFileReader(page_pdf_file, strict=False)
pdf_writer.addPage(reader.getPage(0))
page_index += 1
# 保存
pdf_writer.write(open(pdf_file_path, 'wb'))
def test_change(fs):
path = str(Path(__file__).parent.joinpath('test.pdf'))
fs.add_real_file(path, read_only=False)
acc = PDFAccessor(path)
acc.edit(SetTitleCmd(path, 'Why Donuts Are Great'))
acc.edit(
SetCreatedCmd(path,
datetime.fromisoformat('1999-02-04T06:08:10+00:00')))
acc.edit(AddTagCmd(path, 'tag3'))
acc.edit(DelTagCmd(path, 'tag2'))
assert acc.save()
with open(path, 'rb') as file:
pdf = PdfFileReader(file)
assert 'I like donuts' in pdf.getPage(0).extractText()
# Make sure we didn't destroy preexisting metadata
assert pdf.getDocumentInfo()['/Creator'] == 'Pages'
info = PDFAccessor(path).info()
assert info.title == 'Why Donuts Are Great'
assert info.created == datetime.fromisoformat('1999-02-04T06:08:10+00:00')
assert info.tags == {'tag1', 'tag3'}
def fetch_stuff(pno):
pg = r.content_sync(startview=pno, nviews=1, mode="pdf").value
reader = PdfFileReader(BytesIO(pg))
data, type_ = extract_image(reader.getPage(2))
ocr = r.ocr_data_sync(view=pno).value
soup = BeautifulSoup(ocr.decode())
upper_bound = [0, 0]
lower_bound = [0, 0]
page = soup.find("page")
height, width = int(page.get("height")), int(page.get("width"))
xscale = data.height / height
yscale = data.width / width
height *= yscale
printspace = soup.find("printspace")
text_height = round(int(printspace.get("height")) * yscale)
text_width = round(int(printspace.get("width")) * xscale)
vpos = int(printspace.get("vpos")) * yscale
hpos = int(printspace.get("hpos")) * xscale
upper = Point(round(hpos), round(vpos))
return upper, text_height, text_width, data, height
def MergePDF(filepath):
try:
in_file_path = filepath + r"\input\\"
pdf_fileName = getFileName(in_file_path)
for pdfnames in pdf_fileName:
output = PdfFileWriter()
for pdfname in pdfnames:
input = PdfFileReader(open(pdfname, "rb"))
pageCount = input.getNumPages()
for iPage in range(0, pageCount):
output.addPage(input.getPage(iPage))
pdfoutname = str(pdfnames[0]).replace("input", "output")
outputStream = open(pdfoutname, "wb")
output.write(outputStream)
outputStream.close()
messagebox.showinfo("Complete!", "Complete!")
except Exception as err:
print("Something went wrong")
print(err)
sys.exit()
def add_encryption(input_pdf, output_pdf, password):
"""
PDF加密
:param input_pdf:
:param output_pdf:
:param password:
:return:
"""
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(input_pdf)
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
pdf_writer.encrypt(user_pwd=password, owner_pwd=None,
use_128bit=True)
with open(output_pdf, 'wb') as fh:
pdf_writer.write(fh)
def encrypt_pdf(self, inputpdf, outpdf, password):
"""
加密pdf
inputpdf: 输入的pdf名称，包含路径
outpdf: 输出的pdf名称，不包含路径
"""
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(inputpdf)
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
pdf_writer.encrypt(user_pwd=password, use_128bit=True)
# 默认为40bit加密
with open(self.processed + outpdf, 'wb') as f:
pdf_writer.write(f)
# print("文档加密完成！")
return "文档加密完成！"
def SaveButton(self, event):
dlg = wx.FileDialog(self,
message="Save file as...",
defaultDir=os.getcwd(),
defaultFile="",
wildcard=pdfs,
style=wx.FD_SAVE | wx.FD_OVERWRITE_PROMPT)
input_paths = [
self.files_and_paths[file]
for file in self.input_files.GetStrings()
]
if len(input_paths) < 2:
error_dlg = wx.MessageDialog(
self, "Please select at least two pdfs to join",
"Something went wrong...", wx.OK | wx.ICON_ERROR)
error_dlg.ShowModal()
error_dlg.Destroy()
elif dlg.ShowModal() == wx.ID_OK:
output_path = dlg.GetPath()
pdf_writer = PdfFileWriter()
for path in input_paths:
pdf_reader = PdfFileReader(path)
for page in range(pdf_reader.getNumPages()):
pdf_writer.addPage(pdf_reader.getPage(page))
with open(output_path, 'wb') as output:
pdf_writer.write(output)
success_dlg = wx.MessageDialog(
self, f"""You created {dlg.GetFilename()} and saved it at
{dlg.GetPath()}.""", "Success!", wx.OK | wx.ICON_INFORMATION)
success_dlg.ShowModal()
success_dlg.Destroy()
dlg.Destroy()
self.clear_func()
def encrypt_pdf(input_file: str, password: str):
"""
Encrypts a file using PyPDF4 library.
Precondition: File is not encrypted.
"""
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(open(input_file, 'rb'), strict=False)
if pdf_reader.isEncrypted:
print(f"PDF File {input_file} already encrypted")
return False, None, None
try:
# To encrypt all the pages of the input file, you need to loop over all of them
# and to add them to the writer.
for page_number in range(pdf_reader.numPages):
pdf_writer.addPage(pdf_reader.getPage(page_number))
except utils.PdfReadError as e:
print(f"Error reading PDF File {input_file} = {e}")
return False, None, None
# The default is 128 bit encryption (if false then 40 bit encryption).
pdf_writer.encrypt(user_pwd=password, owner_pwd=None, use_128bit=True)
return True, pdf_reader, pdf_writer
def pdfConcat(each_section, new_filename, test_path): pdf_writer = PdfFileWriter() temp = open(test_path, 'rb') pdf = PdfFileReader(temp) pdf_writer.addPage(pdf.getPage(0)) for file_path in each_section: f = open(file_path , 'rb') pdf_reader = PdfFileReader(f) for page in pdf_reader.pages[1:]: pdf_writer.addPage(page) local_filename = os.path.join(CONST_LOCAL, new_filename) with open(local_filename, 'wb') as out: pdf_writer.write(out) # upload_dropbox(local_filename, output_filename) temp.close()
def pdf_merge(files_paths, file_name):
pdf_writer = PdfFileWriter()
descs = get_files_descriptors(files_paths)
for fd in descs:
try:
pdf_reader = PdfFileReader(fd)
except Exception:
print('Cant read file')
for page in range(pdf_reader.getNumPages()):
try:
pdf_writer.addPage(pdf_reader.getPage(page))
except Exception:
print('Cant merge file')
with open(file_name, 'wb') as f:
try:
pdf_writer.write(f)
except Exception:
print('Cant write file')
finally:
close_file_descriptors(descs)
print('All descriptors are closed')
def test():
sql = "INSERT INTO letters (words) VALUES (%s)"
filename='dan_brown.pdf'
print('...Starting..........')
#urllib.request.urlretrieve(name, filename)
pdf = PdfFileReader(open(filename, "rb"))
info = pdf.getDocumentInfo()
print(info)
info = pdf.getNumPages()
print("Numbers of pages {} ". format(info))
for i in range(info):
x=pdf.getPage(i)
text=x.extractText()
lines = (line.strip() for line in text.splitlines())
# break multi-headlines into a line each
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
# drop blank lines
text = '\n'.join(chunk for chunk in chunks if chunk)
#print(text)
data=text.split("\n")
for line in data:
#print((words))
words=line.split(" ")
for letter in words:
print("--{}--". format(letter))
mycursor.execute(sql, (letter, ))
#rd=str(words)
#print('-{}-'. format(rd))
#print(len(rd))
#lr=rd.split()
# data=text.split("\n")
#print("--{}--". format(text) )
#mycursor.execute(sql, (pid,i,text, ))
print('Finish')
mydb.commit()
def encrypt_single_pdf(input_file, output_file, password):
"""Encrypt single pdf as another file
Args:
input_file: input file path name
output_file: output file path name
password: password used when encryption
Return: None
"""
with open(input_file, 'rb') as input_stream:
reader = PdfFileReader(input_stream)
writer = PdfFileWriter()
#writer.appendPagesFromReader(reader)
for page in range(reader.getNumPages()):
writer.addPage(reader.getPage(page))
writer.encrypt(password)
for page in range(reader.getNumPages()):
a = writer.getPage(page)
#a.scaleTo(480, 270)
with open(output_file, 'wb') as output_stream:
writer.write(output_stream)
def remove_noise(inputFile):
template_id = "TID" + str(uuid.uuid4().node)
outputFile = template_id + '.' + inputFile.split('.')[-1]
with open('./static/img/' + inputFile, "rb") as f:
source = PdfFileReader(f, "rb")
output = PdfFileWriter()
for page in range(source.getNumPages()):
page = source.getPage(page)
content_object = page["/Contents"].getObject()
content = ContentStream(content_object, source)
for operands, operator in content.operations:
if operator == b_("Tf") or operator == b_("Tj"):
operands[0] = TextStringObject('')
page.__setitem__(NameObject('/Contents'), content)
output.addPage(page)
# try:
with open('./static/template/' + outputFile, "wb") as outputStream:
output.write(outputStream)
return template_id
def SaveButton(self, event):
dlg = wx.FileDialog(self,
message="Save file as...",
defaultDir=os.getcwd(),
defaultFile="",
wildcard=pdfs,
style=wx.FD_SAVE | wx.FD_OVERWRITE_PROMPT)
if not self.input_path:
error_dlg = wx.MessageDialog(self, "Please select a pdf to rotate",
"Something went wrong...",
wx.OK | wx.ICON_ERROR)
error_dlg.ShowModal()
error_dlg.Destroy()
elif dlg.ShowModal() == wx.ID_OK:
selection = self.set_degrees.GetSelection()
degrees = int(self.degrees_list[selection])
output_path = dlg.GetPath()
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(self.input_path)
for page in range(pdf_reader.getNumPages()):
original = pdf_reader.getPage(page)
pdf_writer.addPage(original.rotateClockwise(degrees))
with open(output_path, 'wb') as output:
pdf_writer.write(output)
success_dlg = wx.MessageDialog(
self, f"""You created {dlg.GetFilename()} and saved it at
{dlg.GetPath()}.""", "Success!", wx.OK | wx.ICON_INFORMATION)
success_dlg.ShowModal()
success_dlg.Destroy()
dlg.Destroy()
self.clear_func()
def merge_doc(self):
'''合并封面和文件'''
file_lists = list(zip(self.doc_codes, self.name_lists))
for pdfnames in file_lists:
try:
output = PdfFileWriter()
for pdfname in pdfnames:
input = PdfFileReader(open(pdfname, "rb"), strict=False)
pageCount = input.getNumPages()
for iPage in range(0, pageCount):
output.addPage(input.getPage(iPage))
pdfoutname = str(pdfnames[1]).replace("input", "output")
outputStream = open(pdfoutname, "wb")
output.write(outputStream)
outputStream.close()
print("文件合并完成：", pdfoutname)
except Exception as err:
messagebox.showerror("Warning!", err)
with open(os.path.join(os.getcwd(), "error.txt"), "a") as f:
traceback.print_exc(file=f)
print(err)
continue
print("文件合并完成！")
print("=><=" * 25)
# can_2.drawString(85, 141, "Torino")
#
# can_2.drawString(180, 209, user["Cognome"].capitalize())
# can_2.drawString(350, 209, user["Nome"].capitalize())
#
# can_2.save()
#
# packet_2.seek(0)
# new_pdf_2 = PdfFileReader(packet_2)
# read your existing PDF
existing_pdf = PdfFileReader(open("./assets/partecip.pdf", "rb"))
output = PdfFileWriter()
# add the "watermark" (which is the new pdf) on the existing page_1
page_1 = existing_pdf.getPage(0)
page_1.mergePage(new_pdf_1.getPage(0))
output.addPage(page_1)
# page_2 = existing_pdf.getPage(1)
# page_2.mergePage(new_pdf_2.getPage(0))
# output.addPage(page_2)
# output.addPage(existing_pdf.getPage(1))
# finally, write "output" to a real file
right_folder = "other/" if box != "crossfittorino" else "cfto/"
outputStream = open(
"assets/" + right_folder + user["Cognome"].replace(" ", "").lower() +
user["Nome"].replace(" ", "") + ".pdf", "wb")
