问题
I need to fill pdf form in batch, so tried to write a python code to do it for me from a csv file. I used second answer in this question and it fills the forms fine, however when I open the filled forms the answers does not show unless the corresponding field is selected. Also the answers does not show when the form is printed. I looked into PyPDF2 documents to see if I can flatten the generated forms but this features has not been implemented yet even though has been asked for about a year ago. My preference is not to use pdftk so I can compile the script without the need for more dependency. When using the original code in the mentioned question, some fields show in the print and some doesn't which makes me confused on how they're working. Any help is appreciated.
Here's the code.
# -*- coding: utf-8 -*-
from collections import OrderedDict
from PyPDF2 import PdfFileWriter, PdfFileReader
def _getFields(obj, tree=None, retval=None, fileobj=None):
"""
Extracts field data if this PDF contains interactive form fields.
The *tree* and *retval* parameters are for recursive use.
:param fileobj: A file object (usually a text file) to write
a report to on all interactive form fields found.
:return: A dictionary where each key is a field name, and each
value is a :class:`Field<PyPDF2.generic.Field>` object. By
default, the mapping name is used for keys.
:rtype: dict, or ``None`` if form data could not be located.
"""
fieldAttributes = {'/FT': 'Field Type', '/Parent': 'Parent', '/T': 'Field Name', '/TU': 'Alternate Field Name',
'/TM': 'Mapping Name', '/Ff': 'Field Flags', '/V': 'Value', '/DV': 'Default Value'}
if retval is None:
retval = {} #OrderedDict()
catalog = obj.trailer["/Root"]
# get the AcroForm tree
if "/AcroForm" in catalog:
tree = catalog["/AcroForm"]
else:
return None
if tree is None:
return retval
obj._checkKids(tree, retval, fileobj)
for attr in fieldAttributes:
if attr in tree:
# Tree is a field
obj._buildField(tree, retval, fileobj, fieldAttributes)
break
if "/Fields" in tree:
fields = tree["/Fields"]
for f in fields:
field = f.getObject()
obj._buildField(field, retval, fileobj, fieldAttributes)
return retval
def get_form_fields(infile):
infile = PdfFileReader(open(infile, 'rb'))
fields = _getFields(infile)
return {k: v.get('/V', '') for k, v in fields.items()}
def update_form_values(infile, outfile, newvals=None):
pdf = PdfFileReader(open(infile, 'rb'))
writer = PdfFileWriter()
for i in range(pdf.getNumPages()):
page = pdf.getPage(i)
try:
if newvals:
writer.updatePageFormFieldValues(page, newvals)
else:
writer.updatePageFormFieldValues(page,
{k: f'#{i} {k}={v}'
for i, (k, v) in
enumerate(get_form_fields(infile).items())
})
writer.addPage(page)
except Exception as e:
print(repr(e))
writer.addPage(page)
with open(outfile, 'wb') as out:
writer.write(out)
if __name__ == '__main__':
import csv
import os
from glob import glob
cwd=os.getcwd()
outdir=os.path.join(cwd,'output')
csv_file_name=os.path.join(cwd,'formData.csv')
pdf_file_name=glob(os.path.join(cwd,'*.pdf'))[0]
if not pdf_file_name:
print('No pdf file found')
if not os.path.isdir(outdir):
os.mkdir(outdir)
if not os.path.isfile(csv_file_name):
fields=get_form_fields(pdf_file_name)
with open(csv_file_name,'w',newline='') as csv_file:
csvwriter=csv.writer(csv_file,delimiter=',')
csvwriter.writerow(['user label'])
csvwriter.writerow(['fields']+list(fields.keys()))
csvwriter.writerow(['Mr. X']+list(fields.values()))
else:
with open(csv_file_name,'r',newline='') as csv_file:
csvreader=csv.reader(csv_file,delimiter=',')
csvdata=list(csvreader)
fields=csvdata[1][1:]
for frmi in csvdata[2:]:
frmdict=dict(zip(fields,frmi[1:]))
outfile=os.path.join(outdir,frmi[0]+'.pdf')
update_form_values(pdf_file_name, outfile,frmdict)
回答1:
I had the same issue and apparently adding the "/NeedsAppearance" attribute to the PdfWriter object of the AcroForm fixed the problem (see https://github.com/mstamy2/PyPDF2/issues/355). With much help from ademidun (https://github.com/ademidun), I was able to populate a pdf form and have the values of the fields show properly. The following is an example:
from PyPDF2 import PdfFileWriter, PdfFileReader
from PyPDF2.generic import BooleanObject, NameObject, IndirectObject
def set_need_appearances_writer(writer):
# See 12.7.2 and 7.7.2 for more information:
# http://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/PDF32000_2008.pdf
try:
catalog = writer._root_object
# get the AcroForm tree and add "/NeedAppearances attribute
if "/AcroForm" not in catalog:
writer._root_object.update({
NameObject("/AcroForm"): IndirectObject(len(writer._objects), 0, writer)})
need_appearances = NameObject("/NeedAppearances")
writer._root_object["/AcroForm"][need_appearances] = BooleanObject(True)
return writer
except Exception as e:
print('set_need_appearances_writer() catch : ', repr(e))
return writer
infile = "myInputPdf.pdf"
outfile = "myOutputPdf.pdf"
inputStream = open(infile, "rb")
pdf_reader = PdfFileReader(inputStream, strict=False)
if "/AcroForm" in pdf_reader.trailer["/Root"]:
pdf_reader.trailer["/Root"]["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
pdf_writer = PdfFileWriter()
set_need_appearances_writer(pdf_writer)
if "/AcroForm" in pdf_writer._root_object:
pdf_writer._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
field_dictionary = {"Field1": "Value1", "Field2": "Value2"}
pdf_writer.addPage(pdf_reader.getPage(0))
pdf_writer.updatePageFormFieldValues(pdf_writer.getPage(0), field_dictionary)
outputStream = open(outfile, "wb")
pdf_writer.write(outputStream)
inputStream.close()
outputStream.close()
来源：https://stackoverflow.com/questions/47288578/pdf-form-filled-with-pypdf2-does-not-show-in-print