使用Python生成拼合PDF

Question

当我从任何源PDF中打印PDF时,文件大小会下降并删除表单中显示的文本框.简而言之,它会使文件变平.这是我想要实现的行为.

下面的代码使用另一个PDF作为源(我想要展平的那个)来创建PDF,它也会写入文本框形式.

我可以在没有文本框的情况下获得PDF,将其展平吗？就像Adobe在PDF上打印PDF一样.

我的其他代码看起来像这样减去一些东西:

import os
import StringIO
from pyPdf import PdfFileWriter, PdfFileReader
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter

directory = os.path.join(os.getcwd(), "source")  # dir we are interested in
fif = [f for f in os.listdir(directory) if f[-3:] == 'pdf'] # get the PDFs
for i in fif:
    packet = StringIO.StringIO()
    can = canvas.Canvas(packet, pagesize=letter)
    can.rotate(-90)
    can.save()

    packet.seek(0)
    new_pdf = PdfFileReader(packet)
    fname = os.path.join('source', i)
    existing_pdf = PdfFileReader(file(fname, "rb"))
    output = PdfFileWriter()
    nump = existing_pdf.getNumPages()
    page = existing_pdf.getPage(0)
    for l in range(nump):
        output.addPage(existing_pdf.getPage(l))
    page.mergePage(new_pdf.getPage(0))
    outputStream = file("out-"+i, "wb")
    output.write(outputStream)
    outputStream.close()
    print fName + " written as", i

总结: 我有一个pdf,我添加了一个文本框,覆盖信息并添加新信息,然后我从该pdf打印pdf.文本框不再可编辑或可移动.我想自动执行该过程,但我尝试的所有内容仍允许该文本框可编辑.

Answer 1

如果安装OS包是一个选项,那么您可以使用pdftk它的python包装器,pypdftk如下所示:

import pypdftk
pypdftk.fill_form('filled.pdf', out_file='flattened.pdf', flatten=True)

你还需要安装pdftk包,在Ubuntu上可以这样做:

sudo apt-get install pdftk

该pypdftk库可以从PyPI下载:

pip install pypdftk

Answer 2

根据 Adob​​e Docs，您可以将可编辑表单字段的位位置更改为 1 以使字段只读，请参阅文档管理 - PDF 第 1 部分 - 12.7.2 交互式表单词典和此处了解详细信息。

我提供了一个替代解决方案，但使用Django.

用于PyPDF2填充字段，然后循环注释以更改位位置。这是一个适用于第一页的示例：

from io import BytesIO

from PyPDF2 import PdfFileReader, PdfFileWriter
from PyPDF2.generic import BooleanObject, NameObject, NumberObject

# open the pdf
input_stream = open("YourPDF.pdf", "rb")
reader = PdfFileReader(input_stream, strict=False)
if "/AcroForm" in reader.trailer["/Root"]:
    reader.trailer["/Root"]["/AcroForm"].update(
        {NameObject("/NeedAppearances"): BooleanObject(True)}
    )

writer = PdfFileWriter()
writer.set_need_appearances_writer()
if "/AcroForm" in writer._root_object:
    # Acro form is form field, set needs appearances to fix printing issues
    writer._root_object["/AcroForm"].update(
        {NameObject("/NeedAppearances"): BooleanObject(True)}
    )

data_dict = dict()  # this is a dict of your form values

writer.addPage(reader.getPage(0))
page = writer.getPage(0)
# update form fields
writer.updatePageFormFieldValues(page, data_dict)
for j in range(0, len(page["/Annots"])):
    writer_annot = page["/Annots"][j].getObject()
    for field in data_dict:
        if writer_annot.get("/T") == field:
            # make ReadOnly:
            writer_annot.update({NameObject("/Ff"): NumberObject(1)})

# output_stream is your flattened PDF
output_stream = BytesIO()
writer.write(output_stream)
input_stream.close()

更新

正如@MartinThoma 在评论中指出的那样，PyPDF2它已经结束并且不再被维护（他是维护者）。一切又回到了pypdf包裹。不过，还好，随着 的更新pypdf，我所做的只是交换软件包，代码的工作原理是一样的......我没想到会这样！

pypdf与最初编写此代码时相比，我已经稍微更新了代码，但这里是使用更新而不是更新的版本PyPDF2：

from io import BytesIO

import pypdf
from pypdf.generic import NameObject, NumberObject, BooleanObject, IndirectObject


def fill_with_pypdf(file, data):
    """
    Used to fill PDF with PyPDF.
    To fill, PDF form must have field name values that match the dictionary keys

    :param file: The PDF being written to
    :param data: The data dictionary being written to the PDF Fields
    :return:
    """
    with open(file, "rb") as input_stream:
        # you don't actually need to wrap the BinaryIO in BytesIO but pycharm complained
        pdf_reader = pypdf.PdfReader(BytesIO(input_stream.read()), strict=False)

        data = {f"{{{{ {k} }}}}": v for k, v in data.items()}
        print(data)

        if "/AcroForm" in pdf_reader.trailer["/Root"]:
            print('here')
            pdf_reader.trailer["/Root"]["/AcroForm"].update(
                {NameObject("/NeedAppearances"): BooleanObject(True)})

        writer = pypdf.PdfWriter()
        # alter NeedAppearances
        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))

        if "/AcroForm" in writer._root_object:
            # Acro form is form field, set needs appearances to fix printing issues
            writer._root_object["/AcroForm"].update(
                {NameObject("/NeedAppearances"): BooleanObject(True)})

        # loop over all pages
        for page_num in range(len(pdf_reader.pages)):
            writer.add_page(pdf_reader.pages[page_num])
            page = writer.pages[page_num]
            # loop over annotations, but ensure they are there first...
            if page.get('/Annots'):
                # update field values
                writer.update_page_form_field_values(page, data)
                for j in range(0, len(page['/Annots'])):
                    writer_annot = page['/Annots'][j].get_object()
                    # flatten all the fields by setting bit position to 1
                    # use loop below if only specific fields need to be flattened.
                    writer_annot.update({
                        NameObject("/Ff"): NumberObject(1)  # changing bit position to 1 flattens field
                    })
        output_stream = BytesIO()
        writer.write(output_stream)
        print('done')
        return output_stream.getvalue()