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。

以下代码使用另一个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以PDF格式打印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。我想自动完成该过程，但我尝试的所有内容仍然允许该文本框可编辑。

Answer 1

将pdf转换为图像的一种简单方法，而不是将这些图像转换为pdf的方法。

您需要pdf2image和PIL

像这样

from pdf2image import convert_from_path 
from PIL import Image

images = convert_from_path('temp.pdf') 
im1 = images[0]

pdf1_filename = "flattened.pdf"

im1.save(pdf1_filename, "PDF" ,resolution=100.0, save_all=True, append_images=images)

Answer 2

使用pdfrw（How to Populate Fillable PDF's with Python）将输入内容的表格弄平时，我发现我不得不使用generate_fdf（pdftk flatten loses fillable field data）添加额外的步骤。

os.system('pdftk '+outtemp+' generate_fdf output '+outfdf)
os.system('pdftk '+outtemp+' fill_form '+outfdf+' output '+outpdf)

之所以使用此解决方案，是因为我能够在Mac上使用ghostscript的pdf2ps和ps2pdf来平整文件，但是当我在Amazon Linux实例上运行该文件时，分辨率较低。我不知道为什么会这样，所以转到了pdftk解决方案。

Answer 3

对于Adobe Docs，可以将“可编辑表单”字段的位位置更改为1，以使该字段为“只读”。我在这里提供了完整的解决方案，但它使用的是Django：

https://stackoverflow.com/a/55301804/8382028

Adobe Docs（第552页）：

https://www.adobe.com/content/dam/acom/en/devnet/pdf/pdfs/pdf_reference_archives/PDFReference.pdf

使用PyPDF2填充字段，然后遍历注释以更改位的位置：

from io import BytesIO
import PyPDF2
from PyPDF2.generic import BooleanObject, NameObject, IndirectObject, NumberObject

# open the pdf
input_stream = open("YourPDF.pdf", "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 = dict() # this is a dict of your form values

pdf_writer.addPage(pdf_reader.getPage(0))
page = pdf_writer.getPage(0)
# update form fields
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:
        if writer_annot.get('/T') == field:
            writer_annot.update({
                NameObject("/Ff"): NumberObject(1)    # make ReadOnly
            })
output_stream = BytesIO()
pdf_writer.write(output_stream)

# output_stream is your flattened PDF


def set_need_appearances_writer(writer):
    # basically used to ensured there are not 
    # overlapping form fields, which makes printing hard
    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

Answer 4

一种适用于Windows的解决方案，它可以转换许多pdf页面并也可以平化chackbox的值。由于某些原因，@ ViaTech代码在我的电脑上不起作用（Windows7 python 3.8）

遵循@ViaTech指示，并广泛使用this post中的@hchillon代码

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


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)
        return writer

    except Exception as e:
        print('set_need_appearances_writer() catch : ', repr(e))
        return writer



class PdfFileFiller(object):

    def __init__(self, infile):

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

    # newvals and newchecks have keys have to be filled. '' is not accepted
    def update_form_values(self, outfile, newvals=None, newchecks=None):

        self.pdf2 = MyPdfFileWriter()


        trailer = self.pdf.trailer["/Root"]["/AcroForm"]
        self.pdf2._root_object.update({
            NameObject('/AcroForm'): trailer})

        set_need_appearances_writer(self.pdf2)
        if "/AcroForm" in self.pdf2._root_object:
            self.pdf2._root_object["/AcroForm"].update(
            {NameObject("/NeedAppearances"): BooleanObject(True)})

        for i in range(self.pdf.getNumPages()):
            self.pdf2.addPage(self.pdf.getPage(i))

            self.pdf2.updatePageFormFieldValues(self.pdf2.getPage(i), newvals)
            for j in range(0, len(self.pdf.getPage(i)['/Annots'])):
                writer_annot = self.pdf.getPage(i)['/Annots'][j].getObject()
                for field in newvals:
                    writer_annot.update({NameObject("/Ff"): NumberObject(1)})

            self.pdf2.updatePageFormCheckboxValues(self.pdf2.getPage(i), newchecks)

        with open(outfile, 'wb') as out:
            self.pdf2.write(out)


class MyPdfFileWriter(PdfFileWriter):

    def __init__(self):
        super().__init__()

    def updatePageFormCheckboxValues(self, page, fields):

        for j in range(0, len(page['/Annots'])):
            writer_annot = page['/Annots'][j].getObject()
            for field in fields:
                writer_annot.update({NameObject("/Ff"): NumberObject(1)})




origin = ## Put input pdf path here
destination = ## Put output pdf path here, even if the file does not exist yet

newchecks = {} # A dict with all checkbox values that need to be changed
newvals = {'':''} # A dict with all entry values that need to be changed
# newvals dict has to be equal to {'':''} in case that no changes are needed

c = PdfFileFiller(origin)
c.update_form_values(outfile=destination, newvals=newvals, newchecks=newchecks)
print('PDF has been created\n')

使用Python生成拼合PDF

4 个答案: