Python Django PDF 表单域展开

Question

Python Django PDF 表单域展开

5

我有一个项目需要填写预先制作好的PDF文件，我认为最合理的解决方案是将预先制作好的PDF文件转换成PDF表单，这样就可以在表单标签中输入值，然后我可以浏览PDF表单中的标签，并将它们与值的字典进行匹配。

我已经使用了PyPDF2完成了这个任务。总体上，我拍摄了一个Web表单图像，然后打开Acrobat并基于图像中看到的字段创建了一个PDF表单，然后使用PyPDF2来填写PDF表单字段，但问题在于，在某些浏览器（如Firefox）中打印这些填好的值似乎存在故障。

我该如何将我的PDF表单转换为标准/平面PDF，以便保留预填的值，但丢失可编辑的字段（因为我认为这是问题所在）？

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': 'mail@mail.com',
        '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

- ViaTech

1个回答

网页内容由stack overflow 提供, 点击上面的

可以查看英文原文，
原文链接

- ViaTech · Accepted Answer

解决方案非常简单，当您有疑问时，请阅读文档。在这种情况下，Adobe文档指出我只需将字段标志的位位置更改为1，使字段变为只读，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': 'mail@mail.com\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