我有一个项目,我需要填写预制的PDF,并且想到的最合理的解决方案是将预制的PDF制作成PDF格式,以便有输入值应该去的标签,然后我可以查看PDF中的表单标签,并将它们与值字典对齐。
我用PyPDF2完成了这个。总的来说,我拍了一张网页表格,然后打开Acrobat并根据图片中看到的字段创建了一个PDF表格,然后使用PyPDF2填写PDF表格字段,但需要注意的是打印那些填写的值似乎在某些浏览器中,Firefox就是其中之一。
如何将我的PDF表格转换为标准/平面PDF,以便保留预先填充的值,但丢失可编辑字段(因为我认为这是问题)?
from io import BytesIO
import PyPDF2
from django.http import HttpResponse
from PyPDF2.generic import BooleanObject, NameObject, IndirectObject
def pdf_view(request):
template = 'templates/template.pdf'
outfile = "templates/test.pdf"
input_stream = open(template, "rb")
pdf_reader = PyPDF2.PdfFileReader(input_stream, strict=False)
if "/AcroForm" in pdf_reader.trailer["/Root"]:
pdf_reader.trailer["/Root"]["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
pdf_writer = PyPDF2.PdfFileWriter()
set_need_appearances_writer(pdf_writer)
if "/AcroForm" in pdf_writer._root_object:
# Acro form is form field, set needs appearances to fix printing issues
pdf_writer._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
data_dict = {
'first_name': 'John',
'last_name': 'Smith',
'email': '[email protected]',
'phone': '889-998-9967',
'company': 'Amazing Inc.',
'job_title': 'Dev',
'street': '123 Main Way',
'city': 'Johannesburg',
'state': 'New Mexico',
'zip': 96705,
'country': 'USA',
'topic': 'Who cares...'
}
pdf_writer.addPage(pdf_reader.getPage(0))
pdf_writer.updatePageFormFieldValues(pdf_writer.getPage(0), data_dict)
output_stream = BytesIO()
pdf_writer.write(output_stream)
# print(fill_in_pdf(template, data_dict).getvalue())
# fill_in_pdf(template, data_dict).getvalue()
response = HttpResponse(output_stream.getvalue(), content_type='application/pdf')
response['Content-Disposition'] = 'inline; filename="completed.pdf"'
input_stream.close()
return response
def set_need_appearances_writer(writer):
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)
except Exception as e:
print('set_need_appearances_writer() catch : ', repr(e))
return writer
解决方案非常简单,有疑问时请阅读文档(第552/978页):
https://www.adobe.com/content/dam/acom/en/devnet/pdf/pdfs/pdf_reference_archives/PDFReference.pdf
我需要做的就是将字段标志的位位置更改为1,使字段ReadOnly,如下所示:
from io import BytesIO
import PyPDF2
from django.http import HttpResponse
from PyPDF2.generic import BooleanObject, NameObject, IndirectObject, NumberObject
def pdf(request):
template = 'templates/template.pdf'
outfile = "templates/test.pdf"
input_stream = open(template, "rb")
pdf_reader = PyPDF2.PdfFileReader(input_stream, strict=False)
if "/AcroForm" in pdf_reader.trailer["/Root"]:
pdf_reader.trailer["/Root"]["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
pdf_writer = PyPDF2.PdfFileWriter()
set_need_appearances_writer(pdf_writer)
if "/AcroForm" in pdf_writer._root_object:
# Acro form is form field, set needs appearances to fix printing issues
pdf_writer._root_object["/AcroForm"].update(
{NameObject("/NeedAppearances"): BooleanObject(True)})
data_dict = {
'first_name': 'John\n',
'last_name': 'Smith\n',
'email': '[email protected]\n',
'phone': '889-998-9967\n',
'company': 'Amazing Inc.\n',
'job_title': 'Dev\n',
'street': '123 Main Way\n',
'city': 'Johannesburg\n',
'state': 'New Mexico\n',
'zip': 96705,
'country': 'USA\n',
'topic': 'Who cares...\n'
}
pdf_writer.addPage(pdf_reader.getPage(0))
page = pdf_writer.getPage(0)
pdf_writer.updatePageFormFieldValues(page, data_dict)
for j in range(0, len(page['/Annots'])):
writer_annot = page['/Annots'][j].getObject()
for field in data_dict:
# -----------------------------------------------------BOOYAH!
if writer_annot.get('/T') == field:
writer_annot.update({
NameObject("/Ff"): NumberObject(1)
})
# -----------------------------------------------------
output_stream = BytesIO()
pdf_writer.write(output_stream)
response = HttpResponse(output_stream.getvalue(), content_type='application/pdf')
response['Content-Disposition'] = 'inline; filename="completed.pdf"'
input_stream.close()
return response
def set_need_appearances_writer(writer):
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)
except Exception as e:
print('set_need_appearances_writer() catch : ', repr(e))
return writer