python 将单个文件转换为多个 pdf 文件，但第二个文件直到最后一个文件内容从上一个文件合并

Question

我要做的是从选定目录中读取所有 pdf 文件，然后我对从目录中获得的所有 pdf 执行 for loop。然后我用给定的密码保护文件。

假设我有 5 个文件需要用给定的密码保护。使用正确内容成功保护的第一个文件。但是第二个文件直到五个文件内容都与之前的文件内容合并。

第二个文件中的示例有第一个文件内容和第二个文件内容。第三个文件内容中有第一个文件，第二个文件和第三个文件内容。

这是代码：

import os
import datetime
from PyPDF2 import PdfFileReader, PdfFileWriter

def is_encrypted(filename: str) -> bool:
    with open(filename, 'rb') as f:
        pdf_reader = PdfFileReader(f, strict=False)
        return pdf_reader.isEncrypted

curdate = datetime.date.today()
folder = os.getcwd()+"\"+curdate.strftime("%d-%m-%Y")

pdf2merge = []

for filename in os.listdir(folder):
    #print(filename)
    if filename.endswith('.pdf'):
        pdf2merge.append(filename)
    
pdf2merge.sort()

pdf_writer = PdfFileWriter()

for counter, filename in enumerate(pdf2merge):
    path_file = folder+'/'+filename
    splitExt = filename.split('.')
    splitExt.pop()
    joinName = '_'.join(splitExt)
    splitFile = joinName.split('_')
    password = splitFile.pop()
    enc_filename = str('_'.join(splitFile))+".pdf"
    output_file = "payslip-encrypted/"+enc_filename

    if is_encrypted(path_file):
        print("PDF File "+filename+" is already encrypted.")

    try:
        pdfFile = open(path_file, 'rb')
        pdf_reader = PdfFileReader(pdfFile, strict=False)

        for page_number in range(pdf_reader.numPages):
            pdf_writer.addPage(pdf_reader.getPage(page_number))
    except utils.PdfReadError:
        print("Error while reading PDF file "+filename)

    pdf_writer.encrypt(user_pwd=password, use_128bit=True)

    pdfOut = open(output_file, "wb")
    pdf_writer.write(pdfOut)
    pdfOut.close()
    pdfFile.close()

    print("PDF file "+os.getcwd()+"\payslip-encrypted\"+enc_filename+" encrypted successfully")

请更正代码，确保每个文件的内容都是正确的

Answer 1

只需将 pdf_writer = PdfFileWriter() 移入循环。

import os
import datetime
from PyPDF2 import PdfFileReader, PdfFileWriter

def is_encrypted(filename: str) -> bool:
    with open(filename, 'rb') as f:
        pdf_reader = PdfFileReader(f, strict=False)
        return pdf_reader.isEncrypted

curdate = datetime.date.today()
folder = os.getcwd()+"/"+curdate.strftime("%d-%m-%Y")

pdf2merge = []

for filename in os.listdir(folder):
    #print(filename)
    if filename.endswith('.pdf'):
        pdf2merge.append(filename)
    
pdf2merge.sort()

for filename in pdf2merge:
    pdf_writer = PdfFileWriter()
    
    path_file = folder+'/'+filename
    splitExt = filename.split('.')
    splitExt.pop()
    joinName = '_'.join(splitExt)
    splitFile = joinName.split('_')
    password = splitFile.pop()
    enc_filename = str('_'.join(splitFile))+".pdf"
    output_file = "payslip-encrypted/"+enc_filename

    if is_encrypted(path_file):
        print("PDF File "+filename+" is already encrypted.")

    try:
        pdfFile = open(path_file, 'rb')
        pdf_reader = PdfFileReader(pdfFile, strict=False)

        for page_number in range(pdf_reader.numPages):
            pdf_writer.addPage(pdf_reader.getPage(page_number))
    except utils.PdfReadError:
        print("Error while reading PDF file "+filename)

    pdf_writer.encrypt(user_pwd=password, use_128bit=True)

    pdfOut = open(output_file, "wb")
    pdf_writer.write(pdfOut)
    pdfOut.close()
    pdfFile.close()

    print("PDF file "+os.getcwd()+"\payslip-encrypted\"+enc_filename+" encrypted successfully")

python 将单个文件转换为多个 pdf 文件，但第二个文件直到最后一个文件内容从上一个文件合并

python convert single file into multiple pdf file, but second file until the end file content merged from previous file

python

pdf

encryption