def decrypt_pdf(filename, password, decrypted_filename=None):
"""
将加密的文件及逆行解密，并生成一个无需密码pdf文件
:param filename: 原先加密的pdf文件
:param password: 对应的密码
:param decrypted_filename: 解密之后的文件名
:return:
"""
# 生成一个Reader和Writer
print('run jiemi')
pdf_reader = PdfManager.get_reader(filename, password)
if pdf_reader is None:
return
if not pdf_reader.isEncrypted:
print('文件没有被加密，无需操作！')
return
pdf_writer = PdfFileWriter()
pdf_writer.appendPagesFromReader(pdf_reader)
if decrypted_filename is None:
decrypted_filename = "".join(filename[:-4]) + '_' + 'decrypted' + '.pdf'
# 写入新文件
pdf_writer.write(open(decrypted_filename, 'wb'))
def decrypt_pdf(filename, password, decrypted_filename=None):
print("解密第1阶段")
pdf_reader = get_reader(filename, password)
if pdf_reader is None:
return
if not pdf_reader.isEncrypted:
print("文件没有被加密")
return
pdf_writer = PdfFileWriter()
pdf_writer.appendPagesFromReader(pdf_reader)
if decrypted_filename is None:
decrypted_filename = "".join(filename.split('.')[:-1] + '_decrypted.pdf')
pdf_writer.write(open(decrypted_filename, 'wb'))
def pdf_add_metadata(path, file, key, value, out_file, out_path=''):
if out_path == '':
out_path = path
with open(os.path.join(path, file), 'rb') as pdf:
try:
pdf_reader = PdfFileReader(pdf)
metadata = pdf_reader.getDocumentInfo()
print(metadata)
pdf_writer = PdfFileWriter()
pdf_writer.appendPagesFromReader(pdf_reader)
pdf_writer.addMetadata({
'/' + key: value,
# # '/Title': 'PDF in Python'
})
file_out = open(os.path.join(out_path, out_file), 'wb')
pdf_writer.write(file_out)
#
pdf.close()
file_out.close()
# print('File ' + os.path.basename(file) + ' has ' + str(pg) + ' page(s)')
except ValueError:
print(ValueError, 'rrrt')
def SaveButton(self, event):
input_filename = Path(self.input_file)
dlg = wx.FileDialog(self,
message="Save file as...",
defaultDir=os.getcwd(),
defaultFile=(f"{input_filename.with_suffix('')}+"
f"{self.no_pages.GetValue()}"),
wildcard=pdfs,
style=wx.FD_SAVE | wx.FD_OVERWRITE_PROMPT)
if not self.input_path:
self.error_message("Please select a pdf")
elif dlg.ShowModal() == wx.ID_OK:
output_path = dlg.GetPath()
pdf_writer = PdfFileWriter()
pdf_reader = PdfFileReader(self.input_path)
try:
blank_pages = int(self.no_pages.GetValue())
except ValueError:
self.error_message(
"The number of pages added must be an integer")
pdf_writer.appendPagesFromReader(pdf_reader)
for _ in range(blank_pages):
pdf_writer.addBlankPage()
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 generate_facturx_from_file(pdf_invoice,
facturx_xml,
facturx_level='autodetect',
check_xsd=True,
pdf_metadata=None,
output_pdf_file=None,
additional_attachments=None):
"""
Generate a Factur-X invoice from a regular PDF invoice and a factur-X XML
file. The method uses a file as input (regular PDF invoice) and re-writes
the file (Factur-X PDF invoice).
:param pdf_invoice: the regular PDF invoice as file path
(type string) or as file object
:type pdf_invoice: string or file
:param facturx_xml: the Factur-X XML
:type facturx_xml: bytes, string, file or etree object
:param facturx_level: the level of the Factur-X XML file. Default value
is 'autodetect'. The only advantage to specifiy a particular value instead
of using the autodetection is for a very very small perf improvement.
Possible values: minimum, basicwl, basic, en16931.
:type facturx_level: string
:param check_xsd: if enable, checks the Factur-X XML file against the XSD
(XML Schema Definition). If this step has already been performed
beforehand, you should disable this feature to avoid a double check
and get a small performance improvement.
:type check_xsd: boolean
:param pdf_metadata: Specify the metadata of the generated Factur-X PDF.
If pdf_metadata is None (default value), this lib will generate some
metadata in English by extracting relevant info from the Factur-X XML.
Here is an example for the pdf_metadata argument:
pdf_metadata = {
'author': 'Akretion',
'keywords': 'Factur-X, Invoice',
'title': 'Akretion: Invoice I1242',
'subject':
'Factur-X invoice I1242 dated 2017-08-17 issued by Akretion',
}
If you pass the pdf_metadata argument, you will not use the automatic
generation based on the extraction of the Factur-X XML file, which will
bring a very small perf improvement.
:type pdf_metadata: dict
:param output_pdf_file: File Path to the output Factur-X PDF file
:type output_pdf_file: string or unicode
:param additional_attachments: Specify the other files that you want to
embed in the PDF file. It is a dict where keys are filepath and value
is the description of the file (as unicode or string).
:type additional_attachments: dict
:return: Returns True. This method re-writes the input PDF invoice file,
unless if the output_pdf_file is provided.
:rtype: bool
"""
assert isinstance(facturx_xml, bytes)
xml_string = facturx_xml
facturx_level = facturx_level.lower()
additional_attachments_read = {}
if additional_attachments:
for attach_filepath, attach_desc in additional_attachments.items():
filename = os.path.basename(attach_filepath)
mod_timestamp = os.path.getmtime(attach_filepath)
mod_dt = datetime.fromtimestamp(mod_timestamp)
with open(attach_filepath, 'rb') as fa:
fa.seek(0)
additional_attachments_read[fa.read()] = {
'filename': filename,
'desc': attach_desc,
'mod_date': mod_dt,
}
fa.close()
original_pdf = PdfFileReader(pdf_invoice)
# Extract /OutputIntents obj from original invoice
output_intents = _get_original_output_intents(original_pdf)
new_pdf_filestream = PdfFileWriter()
new_pdf_filestream._header = b_("%PDF-1.6")
new_pdf_filestream.appendPagesFromReader(original_pdf)
original_pdf_id = original_pdf.trailer.get('/ID')
if original_pdf_id:
new_pdf_filestream._ID = original_pdf_id
# else : generate some ?
_facturx_update_metadata_add_attachment(
new_pdf_filestream,
xml_string,
pdf_metadata,
facturx_level,
output_intents=output_intents,
additional_attachments=additional_attachments_read)
if output_pdf_file:
with open(output_pdf_file, 'wb') as output_f:
new_pdf_filestream.write(output_f)
output_f.close()
else:
with open(pdf_invoice, 'wb') as f:
new_pdf_filestream.write(f)
f.close()
return True
def generate_facturx_from_file(pdf_invoice,
facturx_xml,
facturx_level='autodetect',
check_xsd=True,
pdf_metadata=None,
output_pdf_file=None,
additional_attachments=None,
attachments=None):
"""
Generate a Factur-X invoice from a regular PDF invoice and a factur-X XML
file. The method uses a file as input (regular PDF invoice) and re-writes
the file (Factur-X PDF invoice).
:param pdf_invoice: the regular PDF invoice as file path
(type string) or as file object
:type pdf_invoice: string or file
:param facturx_xml: the Factur-X XML
:type facturx_xml: bytes, string, file or etree object
:param facturx_level: the level of the Factur-X XML file. Default value
is 'autodetect'. The only advantage to specifiy a particular value instead
of using the autodetection is for a very very small perf improvement.
Possible values: minimum, basicwl, basic, en16931.
:type facturx_level: string
:param check_xsd: if enable, checks the Factur-X XML file against the XSD
(XML Schema Definition). If this step has already been performed
beforehand, you should disable this feature to avoid a double check
and get a small performance improvement.
:type check_xsd: boolean
:param pdf_metadata: Specify the metadata of the generated Factur-X PDF.
If pdf_metadata is None (default value), this lib will generate some
metadata in English by extracting relevant info from the Factur-X XML.
Here is an example for the pdf_metadata argument:
pdf_metadata = {
'author': 'Akretion',
'keywords': 'Factur-X, Invoice',
'title': 'Akretion: Invoice I1242',
'subject':
'Factur-X invoice I1242 dated 2017-08-17 issued by Akretion',
}
If you pass the pdf_metadata argument, you will not use the automatic
generation based on the extraction of the Factur-X XML file, which will
bring a very small perf improvement.
:type pdf_metadata: dict
:param output_pdf_file: File Path to the output Factur-X PDF file
:type output_pdf_file: string or unicode
:param attachments: Specify the other files that you want to
embed in the PDF file. It is a dict where key is the filename and value
is a dict. In this dict, keys are 'filepath' (value is the full file path)
or 'filedata' (value is the encoded file),
'description' (text description, optional) and
'modification_datetime' (modification date and time as datetime object, optional).
'creation_datetime' (creation date and time as datetime object, optional).
:type attachments: dict
:param additional_attachments: DEPRECATED. Use attachments instead.
Undocumented.
:return: Returns True. This method re-writes the input PDF invoice file,
unless if the output_pdf_file is provided.
:rtype: bool
"""
start_chrono = datetime.now()
logger.debug('generate_facturx_from_file with factur-x lib %s',
__version__)
logger.debug('1st arg pdf_invoice type=%s', type(pdf_invoice))
logger.debug('2nd arg facturx_xml type=%s', type(facturx_xml))
logger.debug('optional arg facturx_level=%s', facturx_level)
logger.debug('optional arg check_xsd=%s', check_xsd)
logger.debug('optional arg pdf_metadata=%s', pdf_metadata)
logger.debug('optional arg additional_attachments=%s',
additional_attachments)
if not pdf_invoice:
raise ValueError('Missing pdf_invoice argument')
if not facturx_xml:
raise ValueError('Missing facturx_xml argument')
if not isinstance(facturx_level, (str, unicode)):
raise ValueError('Wrong facturx_level argument')
if not isinstance(check_xsd, bool):
raise ValueError('check_xsd argument must be a boolean')
if not isinstance(pdf_metadata, (type(None), dict)):
raise ValueError('pdf_metadata argument must be a dict or None')
if not isinstance(pdf_metadata, (dict, type(None))):
raise ValueError('pdf_metadata argument must be a dict or None')
if not isinstance(additional_attachments, (dict, type(None))):
raise ValueError(
'additional_attachments argument must be a dict or None')
if not isinstance(output_pdf_file, (type(None), str, unicode)):
raise ValueError('output_pdf_file argument must be a string or None')
if isinstance(pdf_invoice, (str, unicode)):
file_type = 'path'
else:
file_type = 'file'
xml_root = None
# in Python3, xml_string is a byte
if isinstance(facturx_xml, (str, bytes)):
xml_string = facturx_xml
elif isinstance(facturx_xml, unicode):
xml_string = facturx_xml.encode('utf8')
elif isinstance(facturx_xml, type(etree.Element('pouet'))):
xml_root = facturx_xml
xml_string = etree.tostring(xml_root,
pretty_print=True,
encoding='UTF-8',
xml_declaration=True)
elif isinstance(facturx_xml, file):
facturx_xml.seek(0)
xml_string = facturx_xml.read()
facturx_xml.close()
else:
raise TypeError(
"The second argument of the method generate_facturx must be "
"either a string, an etree.Element() object or a file "
"(it is a %s)." % type(facturx_xml))
# The additional_attachments arg is deprecated
if attachments is None:
attachments = {}
if additional_attachments and not attachments:
logger.warning(
'The argument additional_attachments is deprecated. '
'It will be removed in future versions. Use the argument '
'attachments instead.')
for attach_filepath, attach_desc in additional_attachments.items():
filename = os.path.basename(attach_filepath)
mod_timestamp = os.path.getmtime(attach_filepath)
mod_dt = datetime.fromtimestamp(mod_timestamp)
with open(attach_filepath, 'rb') as fa:
fa.seek(0)
attachments[filename] = {
'filedata': fa.read(),
'description': attach_desc,
'modification_datetime': mod_dt,
}
fa.close()
if attachments:
for filename, fadict in attachments.items():
if filename in [FACTURX_FILENAME] + ZUGFERD_FILENAMES:
logger.warning(
'You cannot provide as attachment a file named %s. '
'This file will NOT be attached.', filename)
attachments.pop(filename)
continue
if fadict.get('filepath') and not fadict.get('filedata'):
with open(fadict['filepath'], 'rb') as fa:
fa.seek(0)
fadict['filedata'] = fa.read()
fa.close()
# As explained here
# https://stackoverflow.com/questions/237079/how-to-get-file-creation-modification-date-times-in-python
# creation date is not easy to get.
# So we only implement getting the modification date
if not fadict.get('modification_datetime'):
mod_timestamp = os.path.getmtime(fadict['filepath'])
fadict['modification_datetime'] = datetime.fromtimestamp(
mod_timestamp)
if pdf_metadata is None:
if xml_root is None:
xml_root = etree.fromstring(xml_string)
base_info = _extract_base_info(xml_root)
pdf_metadata = _base_info2pdf_metadata(base_info)
else:
# clean-up pdf_metadata dict
for key, value in pdf_metadata.items():
if not isinstance(value, (str, unicode)):
pdf_metadata[key] = ''
facturx_level = facturx_level.lower()
if facturx_level not in FACTURX_LEVEL2xsd:
if xml_root is None:
xml_root = etree.fromstring(xml_string)
logger.debug('Factur-X level will be autodetected')
facturx_level = get_facturx_level(xml_root)
if check_xsd:
check_facturx_xsd(xml_string,
flavor='factur-x',
facturx_level=facturx_level)
original_pdf = PdfFileReader(pdf_invoice)
# Extract /OutputIntents obj from original invoice
output_intents = _get_original_output_intents(original_pdf)
new_pdf_filestream = PdfFileWriter()
new_pdf_filestream._header = b_("%PDF-1.6")
new_pdf_filestream.appendPagesFromReader(original_pdf)
original_pdf_id = original_pdf.trailer.get('/ID')
logger.debug('original_pdf_id=%s', original_pdf_id)
if original_pdf_id:
new_pdf_filestream._ID = original_pdf_id
# else : generate some ?
_facturx_update_metadata_add_attachment(new_pdf_filestream,
xml_string,
pdf_metadata,
facturx_level,
output_intents=output_intents,
additional_attachments=attachments)
if output_pdf_file:
with open(output_pdf_file, 'wb') as output_f:
new_pdf_filestream.write(output_f)
output_f.close()
else:
if file_type == 'path':
with open(pdf_invoice, 'wb') as f:
new_pdf_filestream.write(f)
f.close()
elif file_type == 'file':
new_pdf_filestream.write(pdf_invoice)
logger.info('%s file added to PDF invoice', FACTURX_FILENAME)
end_chrono = datetime.now()
logger.info('Factur-X invoice generated in %s seconds',
(end_chrono - start_chrono).total_seconds())
return True
# -*- coding:utf-8 -*-
# Author:Liu Hongliang
from PyPDF4 import PdfFileReader, PdfFileWriter
source_file = open("f:\\c1.pdf", "rb")
fin = PdfFileReader(source_file)
info = dict(fin.getDocumentInfo())
info['/ModDate'] = info['/CreationDate']
print(info)
dest_file = open("f:\\c2.pdf", "wb")
fout = PdfFileWriter()
fout.addMetadata(info)
fout.appendPagesFromReader(fin)
fout.write(dest_file)
source_file.close()
dest_file.close()
embeddedFilesDictionary.update(
{NameObject("/EmbeddedFiles"): embeddedFilesNamesDictionary})
myPdfFileWriterObj._root_object.update(
{NameObject("/Names"): embeddedFilesDictionary})
else:
myPdfFileWriterObj._root_object["/Names"]["/EmbeddedFiles"][
"/Names"].append(createStringObject(fname))
myPdfFileWriterObj._root_object["/Names"]["/EmbeddedFiles"][
"/Names"].append(filespec)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('config', help='Path to config file.')
args = parser.parse_args()
with open(args.config) as f:
config = json.load(f)
fr = PdfFileReader(config['dstFileName'], 'rb')
fw = PdfFileWriter()
fw.appendPagesFromReader(fr)
for key in config['pdfInfo']:
fw.addMetadata({key: config['pdfInfo'][key]})
for oneAttachment in config['pdfAttachments']:
with open(oneAttachment['srcFileName'], 'rb') as oneAttachmentFile:
attachmentData = oneAttachmentFile.read()
appendAttachment(fw, oneAttachment['attFileName'], attachmentData)
with open(config['dstFileName'] + '.finalized.pdf', 'wb') as file:
fw.write(file)
def process_the_pdf():
confirm = tk.messagebox.askyesno("Doing the thing",
"Are you sure you want to do the thing?")
if confirm == True:
try:
pdf = Pdfread(pdf_path.get())
wf = Pdfwrite()
wf.appendPagesFromReader(pdf)
for i in range(blank_start.get()):
wf.insertBlankPage(0)
for i in range(end_blank_pages.get()):
wf.addBlankPage()
# ! --> here's where the shuffle goes, pos save temp pdf here?
list_pages = []
for i in range(wf.getNumPages()):
list_pages.append(i)
list_sigs_pages = []
for group in chunker(list_pages, sig_thickness_x4.get()):
list_sigs_pages.append(group)
newpageorder = shufoutput(list_sigs_pages)
newpdf = Pdfwrite()
for page in newpageorder:
newpdf.addPage(wf.getPage(page))
temp = Pdfwrite()
# up2 = turninto2up(newpdf)
temp = newpdf
destpath = pdf_output_path.get()
with open(destpath, 'wb+') as out:
temp.write(out)
up2in = Pdfread(destpath)
up2 = Pdfwrite()
for i in range(up2in.getNumPages()):
temp = up2in.getPage(i)
up2.addPage(temp)
up2 = frasers2up(up2)
# up2 = turninto2up(up2in)
with open(destpath, "wb+") as up2out:
up2.write(up2out)
tk.messagebox.showinfo(
"Finished", "Finished, and maybe it even worked this time!")
except FileNotFoundError:
tk.messagebox.showerror(
"File not found",
"Either the input file or the output files is wrong.\nOr both of them. Who knows?"
)
pass
else:
pass
