我需要批量填写pdf表单,所以尝试从csv文件中为我编写python代码。我在这个question中使用了第二个答案,它很好地填充了表单,但是当我打开填充的表单时,答案将不会显示,除非选择了相应的字段。此外,当打印表单时,答案不会显示。我查看了PyPDF2文档,看看是否可以将生成的表单夷为平地,但是这些特性还没有实现,即使在大约一年前就已经被要求实现了。我倾向于不使用pdftk,这样我就可以编译脚本,而不需要更多的依赖。当在上述问题中使用原始代码时,有些字段显示在打印中,而有些字段没有显示,这使我对它们的工作方式感到困惑。任何帮助都是非常感谢的。
这是密码。
# -*- 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)
发布于 2018-01-25 20:49:17
我也有同样的问题,显然将"/NeedsAppearance“属性添加到AcroForm的PdfWriter对象中解决了问题(参见https://github.com/mstamy2/PyPDF2/issues/355)。在ademidun (https://github.com/ademidun)的帮助下,我能够填充一个pdf表单,并正确地显示字段的值。以下是一个例子:
from PyPDF2 import PdfFileReader, PdfFileWriter
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
reader = PdfFileReader("myInputPdf.pdf", strict=False)
if "/AcroForm" in reader.trailer["/Root"]:
reader.trailer["/Root"]["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)}
)
writer = PdfFileWriter()
set_need_appearances_writer(writer)
if "/AcroForm" in writer._root_object:
writer._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)}
)
field_dictionary = {"Field1": "Value1", "Field2": "Value2"}
writer.addPage(reader.getPage(0))
writer.updatePageFormFieldValues(writer.getPage(0), field_dictionary)
with open("myOutputPdf.pdf", "wb") as fp:
writer.write(fp)
发布于 2022-09-08 22:43:56
表单字段在填写后没有显示的根本原因是没有将值添加到流中。添加"NeedAppearances“会告诉PDF阅读器它需要更新外观,在这种情况下,它需要为每个字段值创建一个流,但并不是所有的PDF阅读器都会遵守这一点,而且这些字段可能看起来仍然是空白的,或者具有默认值。
确保为任何阅读器更新字段的最佳解决方案是为每个字段创建一个流,并将其添加到字段的XObject中。
下面是单行文本字段的示例解决方案。它还对流进行编码,更新默认值,并将字段设置为只读,这些字段都是可选的。
# Example data.
data = {
"field_name": "some value"
}
# Get template.
template = PdfReader("template-form.pdf", strict=False)
# Initialize writer.
writer = PdfWriter()
# Add the template page.
writer.add_page(template.pages[0])
# Get page annotations.
page_annotations = writer.pages[0][PageAttributes.ANNOTS]
# Loop through page annotations (fields).
for index in range(len(page_annotations)): # type: ignore
# Get annotation object.
annotation = page_annotations[index].get_object() # type: ignore
# Get existing values needed to create the new stream and update the field.
field = annotation.get(NameObject("/T"))
new_value = data.get(field, 'N/A')
ap = annotation.get(AnnotationDictionaryAttributes.AP)
x_object = ap.get(NameObject("/N")).get_object()
font = annotation.get(InteractiveFormDictEntries.DA)
rect = annotation.get(AnnotationDictionaryAttributes.Rect)
# Calculate the text position.
font_size = float(font.split(" ")[1])
w = round(float(rect[2] - rect[0] - 2), 2)
h = round(float(rect[3] - rect[1] - 2), 2)
text_position_h = h / 2 - font_size / 3 # approximation
# Create a new XObject stream.
new_stream = f'''
/Tx BMC
q
1 1 {w} {h} re W n
BT
{font}
2 {text_position_h} Td
({new_value}) Tj
ET
Q
EMC
'''
# Add Filter type to XObject.
x_object.update(
{
NameObject(StreamAttributes.FILTER): NameObject(FilterTypes.FLATE_DECODE)
}
)
# Update and encode XObject stream.
x_object._data = FlateDecode.encode(encode_pdfdocencoding(new_stream))
# Update annotation dictionary.
annotation.update(
{
# Update Value.
NameObject(FieldDictionaryAttributes.V): TextStringObject(
new_value
),
# Update Default Value.
NameObject(FieldDictionaryAttributes.DV): TextStringObject(
new_value
),
# Set Read Only flag.
NameObject(FieldDictionaryAttributes.Ff): NumberObject(
FieldFlag(1)
)
}
)
# Clone document root & metadata from template.
# This is required so that the document doesn't try to save before closing.
writer.clone_reader_document_root(template)
# write "output".
with open(f"output.pdf", "wb") as output_stream:
writer.write(output_stream) # type: ignore
感谢在这里讨论的烦躁和其他人:https://github.com/py-pdf/PyPDF2/issues/355。
发布于 2021-02-26 15:16:49
这就是我在Python3.8和PyPDF4上的工作原理(但我认为它也适用于PyPDF2):
#!/usr/bin/env python3
from PyPDF4.generic import NameObject
from PyPDF4.generic import TextStringObject
from PyPDF4.pdf import PdfFileReader
from PyPDF4.pdf import PdfFileWriter
import random
import sys
reader = PdfFileReader(sys.argv[1])
writer = PdfFileWriter()
# Try to "clone" the original one (note the library has cloneDocumentFromReader)
# but the render pdf is blank.
writer.appendPagesFromReader(reader)
writer._info = reader.trailer["/Info"]
reader_trailer = reader.trailer["/Root"]
writer._root_object.update(
{
key: reader_trailer[key]
for key in reader_trailer
if key in ("/AcroForm", "/Lang", "/MarkInfo")
}
)
page = writer.getPage(0)
params = {"Foo": "Bar"}
# Inspired by updatePageFormFieldValues but also handles checkboxes.
for annot in page["/Annots"]:
writer_annot = annot.getObject()
field = writer_annot["/T"]
if writer_annot["/FT"] == "/Btn":
value = params.get(field, random.getrandbits(1))
if value:
writer_annot.update(
{
NameObject("/AS"): NameObject("/On"),
NameObject("/V"): NameObject("/On"),
}
)
elif writer_annot["/FT"] == "/Tx":
value = params.get(field, field)
writer_annot.update(
{
NameObject("/V"): TextStringObject(value),
}
)
with open(sys.argv[2], "wb") as f:
writer.write(f)
这将更新文本字段和复选框。
我认为关键部分是从原始文件中复制一些部分:
reader_trailer = reader.trailer["/Root"]
writer._root_object.update(
{
key: reader_trailer[key]
for key in reader_trailer
if key in ("/AcroForm", "/Lang", "/MarkInfo")
}
)
注意:请在其他地方分享此解决方案。关于这个话题,我咨询了很多这样的问题。
https://stackoverflow.com/questions/47288578
复制相似问题