def set_up_meta(self, control_sum):
writer = pdfrw.PdfWriter()
for page in pdfrw.PdfReader(self.path).pages:
writer.addPage(page)
writer.trailer.Info = pdfrw.IndirectPdfDict(Owner=self.user_id,
ControlSum=control_sum,
SignedBy='')
writer.write(self.path)
def make_output(self):
# generate the output string
ostr = libxmp.core._remove_trailing_whitespace(
self.md.serialize_to_str().replace("\ufeff", ""))
# assemble the output dictionary
output_dict = pdfrw.IndirectPdfDict(Type=pdfrw.PdfName("Metadata"),
Subtype=pdfrw.PdfName("XML"))
output_dict.stream = ostr.encode("utf-8").decode("latin-1")
return output_dict
def pdfInfo(self):
return pdfrw.IndirectPdfDict(
Title=self.title,
Author=self.author,
Subject=self.subject,
Keywords=self.keywords,
Creator=self.creator,
Producer=self.producer,
CreationDate=self.pdftime(),
ModDate=self.pdftime(),
)
def __init__(self):
# load the sRGB2014 ICC color profile
iccpath = pathlib.Path(
__file__).absolute().parent / "icc" / "sRGB2014.icc"
srgb = ImageCms.getOpenProfile(str(iccpath))
# construct the correct pdf dict. first the output profile
# N=3 is required for RGB colorspaces
op = pdfrw.IndirectPdfDict(N=3, Alternate=pdfrw.PdfName("DeviceRGB"))
op.stream = srgb.tobytes().decode("latin-1")
# then the outputintents array
oi = pdfrw.IndirectPdfDict(
Type=pdfrw.PdfName("OutputIntent"),
S=pdfrw.PdfName("GTS_PDFA1"),
OutputConditionIdentifier="sRGB",
DestOutputProfile=op,
Info=srgb.profile.profile_description,
# I am not sure whether this is correct, but it doesn't fail
RegistryName="http://color.org/srgbprofiles.xalter")
self.output_intent = [oi]
return template_pdf
def build_datadict(in_file):
o = []
with open(in_file) as file:
reader = csv.DictReader(file, delimiter=',')
for row in reader:
m = {}
for f in FIELDS:
if row[f] and not row[f].isspace() and not row[f] is None:
m[f] = row[f]
if m:
m['Date'] = "January 25th, 2020"
o.append(m)
return o
if __name__ == '__main__':
data = build_datadict(IN_FILE)
writer = pdfrw.PdfWriter()
writer.trailer.Info = pdfrw.IndirectPdfDict(Title='Combined PDF')
# Iterate array of 'data_dict's
for d in data:
this_pages = modify_form(TEMPLATE_FILE, d) # fill the form
this_pages.Root.AcroForm.update(
pdfrw.PdfDict(NeedAppearances=pdfrw.PdfObject(
'true'))) # maintain appearances
writer.addpages(this_pages.pages) # merge into single pdf
writer.write(IN_FILE.split(".")[0] + ".pdf")
flag = sys.argv[1]
if flag == "-c": # combine
import pdfrw
import natsort
writer = pdfrw.PdfWriter()
for file in natsort.natsorted(os.listdir(f"{script_root}/data")):
if file.endswith(".pdf"):
print(file)
pdf_path = f"{script_root}/data/{file}"
writer.addpages(pdfrw.PdfReader(pdf_path).pages)
writer.trailer.Info = pdfrw.IndirectPdfDict(Title="")
writer.write(f"{script_root}/data/combined.pdf")
elif flag == "-o": # ocr
import ocrmypdf
for file in os.listdir(f"{script_root}/data"):
if file.endswith(".pdf"):
print(file)
pdf_path = f"{script_root}/data/{file}"
pid = os.fork()
if pid > 0: # parent process
os.waitpid(pid, 0) # wait for child process to end
elif pid == 0: # child process
ocrmypdf.ocr(
input_file=pdf_path,