如何在 PDF 中附加多个文件？

Question

我有一个对象列表：List = ['Doc1.xlsx','Doc2.csv','Doc3.pdf'] 及其名称列表：List1 = ['Doc1_name.xlsx','Doc2_name.csv','Doc3_name.pdf']。 我需要将它们附加到现有的 PDF 中。我尝试使用以下代码，该代码仅在我有一个附件时才有效。现在我正在尝试遍历附件以附加所有附件，但在Final.pdf 中将仅附加最后一个对象'Doc3.pdf'。

fileReader = PdfFileReader('Existing_pdf.pdf', 'rb')
fileWriter = PdfFileWriter()
fileWriter = appendPagesFromReader(fileReader)

for j in range(1, len(List)):
    fileWriter.addAtachment(List1[j],List[j])

with open('Final.pdf', 'wb') as output_pdf:
    fileWriter.write(output_pdf)

Answer 1

在我看来，addAttachment-Method 总是替换当前附件。

来自PyPDF2 Github中的pdf.py：

def addAttachment(self, fname, fdata):
    file_entry = DecodedStreamObject()
    file_entry.setData(fdata)
    file_entry.update({
            NameObject("/Type"): NameObject("/EmbeddedFile")
            })

    efEntry = DictionaryObject()
    efEntry.update({ NameObject("/F"):file_entry })

    filespec = DictionaryObject()
    filespec.update({
            NameObject("/Type"): NameObject("/Filespec"),
            NameObject("/F"): createStringObject(fname),  # Perhaps also try TextStringObject
            NameObject("/EF"): efEntry
            })

    embeddedFilesNamesDictionary = DictionaryObject()
    embeddedFilesNamesDictionary.update({
            NameObject("/Names"): ArrayObject([createStringObject(fname), filespec])
            })

    embeddedFilesDictionary = DictionaryObject()
    embeddedFilesDictionary.update({
            NameObject("/EmbeddedFiles"): embeddedFilesNamesDictionary
            })
    # Update the root
    self._root_object.update({
        NameObject("/Names"): embeddedFilesDictionary
        })

我相信的地方

self._root_object.update({
        NameObject("/Names"): embeddedFilesDictionary
        })

替换附件，而不是添加它。

编辑： 这个脚本对我有用，可以附加两个 .txt 文件。 它使用上面的addAttachment 方法，我稍微调整了它以启用附加多个文件。

from PyPDF2 import PdfFileReader, PdfFileWriter
from PyPDF2.generic import DecodedStreamObject, NameObject, DictionaryObject, createStringObject, ArrayObject


def appendAttachment(myPdfFileWriterObj, fname, fdata):
    # The entry for the file
    file_entry = DecodedStreamObject()
    file_entry.setData(fdata)
    file_entry.update({NameObject("/Type"): NameObject("/EmbeddedFile")})

    # The Filespec entry
    efEntry = DictionaryObject()
    efEntry.update({ NameObject("/F"):file_entry })

    filespec = DictionaryObject()
    filespec.update({NameObject("/Type"): NameObject("/Filespec"),NameObject("/F"): createStringObject(fname),NameObject("/EF"): efEntry})

    if "/Names" not in myPdfFileWriterObj._root_object.keys():
        # No files attached yet. Create the entry for the root, as it needs a reference to the Filespec
        embeddedFilesNamesDictionary = DictionaryObject()
        embeddedFilesNamesDictionary.update({NameObject("/Names"): ArrayObject([createStringObject(fname), filespec])})

        embeddedFilesDictionary = DictionaryObject()
        embeddedFilesDictionary.update({NameObject("/EmbeddedFiles"): embeddedFilesNamesDictionary})
        myPdfFileWriterObj._root_object.update({NameObject("/Names"): embeddedFilesDictionary})
    else:
        # There are files already attached. Append the new file.
        myPdfFileWriterObj._root_object["/Names"]["/EmbeddedFiles"]["/Names"].append(createStringObject(fname))
        myPdfFileWriterObj._root_object["/Names"]["/EmbeddedFiles"]["/Names"].append(filespec)


fr = PdfFileReader('dummy.pdf','rb')
fw = PdfFileWriter()
fw.appendPagesFromReader(fr)

my_attach_files = ['test.txt','test2.txt']
for my_test in my_attach_files:
    with open(my_test, 'rb') as my_test_attachment:
        my_test_data = my_test_attachment.read()
    appendAttachment(fw, my_test, my_test_data)

with open('dummy_new.pdf','wb') as file:
    fw.write(file)

希望这对你有用。