【工具】PDF 元数据清洗工具说明

PDF 清除文档信息

使用说明

程序自动扫描当前路径下的 pdf 文档，判断文档信息是否需要清除

• 清除前
  

• 清除后
  

自定义配置

• 新建 config.ini 文件

[global]
NanjingAuthor   = ' '
NanjingProducer = ' '
NanjingCreator  = ' '

查看日志

• 日志路径：.\log
  

源码

开源地址: https://github.com/ChenDudo/PDFCleaner

# !/usr/bin/env python3
# -*-coding:utf-8 -*-
# @Author  : Chen Do

import configparser
from  PyPDF2 import PdfFileReader
from  PyPDF2 import PdfWriter
import os
import time
import sys
import io
import datetime

global NanjingAuthor
global NanjingProducer
global NanjingCreator

NanjingAuthor   = "Firmware Development Group"
NanjingProducer = "MindMotion Nanjing Ecosystem"
NanjingCreator  = "Chen Do"

global handle_num
output_file = []
handle_num = 0


def create_detail_day():
    # day_time = datetime.datetime.now().strftime('day'+'%Y_%m_%d')
    # hour_time = datetime.datetime.now().strftime('time' + "%H_%M_%S")
    detail_time = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')
    return detail_time

class Logger(object):
    def __init__(self, filename="Default.log", path=".\\"):
        # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
        self.terminal = sys.stdout
        self.log = open(os.path.join(path, filename), "a", encoding='utf8')

    def write(self, message):
        self.terminal.write(message)
        self.log.write(message)

    def flush(self):
        pass

def handle_doc(outputfilepath, filepath, filename):
    global handle_num
    global NanjingAuthor
    global NanjingProducer
    global NanjingCreator

    readfilepath = filepath + '\\' + filename
    outputfilepath = outputfilepath + '\\' + filename

    if not filename.endswith('.pdf'):
        print("[ERROR]\t\""+filename+'\" is not *.Pdf files!')
        return

    # reader & writer
    reader = PdfFileReader(readfilepath)
    writer = PdfWriter()

    # read meta
    meta = reader.metadata
    l_creation_data_raw = str(meta.creation_date_raw)
    l_modification_date_raw = str(meta.modification_date_raw)

    if (meta.producer == NanjingProducer) and (meta.author == NanjingAuthor) and (meta.creator == NanjingCreator):
        print("[WARN]\t\""+filename+'\" needn\'t to change!')
        return

    # Add all pages to the writer
    for page in reader.pages:
        writer.add_page(page)

    # Add the metadata
    writer.add_metadata(
        {
            "/Author": NanjingAuthor,
            "/Creator": NanjingCreator,
            "/Producer": NanjingProducer,
            "/CreationDate": l_creation_data_raw,
            "/ModDate": l_modification_date_raw
        }
    )

    # Save the new PDF to a file
    with open(outputfilepath, "wb") as f:
        writer.write(f)
        print('[INFO]\t'+'\"'+filename+"\" Done! "+'*'*36)

    # decoder handle number
    handle_num = handle_num + 1
    output_file.append(outputfilepath)


''' (config.ini) file module:
[global]
NanjingAuthor   = 'Firmware Development Group'
NanjingProducer = 'MindMotion Nanjing Ecosystem'
NanjingCreator  = 'Chen Do'
'''
def read_config_file(filepath):
    global NanjingAuthor
    global NanjingProducer
    global NanjingCreator
    conf_file = filepath + "\\config.ini"

    conf = configparser.ConfigParser()
    
    if os.path.exists(conf_file):
        conf.read(conf_file)
        if not "global" in conf:
            print("[WARN]\tNo global section in config file")
            pass
        else:
            if 'NanjingAuthor' in conf['global']:
                NanjingAuthor   = eval(conf.get("global", "NanjingAuthor"))
            if 'NanjingProducer' in conf["global"]:
                NanjingProducer = eval(conf.get("global", "NanjingProducer"))
            if 'NanjingCreator' in conf["global"]:
                NanjingCreator  = eval(conf.get("global", "NanjingCreator"))
    else:
        print("[ERROR]\tNo Config files, Use default config")
        # NanjingAuthor   = "Firmware Development Group"
        # NanjingProducer = "MindMotion Nanjing Ecosystem"
        # NanjingCreator  = "Chen Do"
    print("[info]\tNow Use following Config :")
    print("\t[Author]: " + NanjingAuthor)
    print("\t[Producer]: " + NanjingProducer)
    print("\t[Creator]: " + NanjingCreator)

• 下载链接

PDF Cleaner