往"某度文库"上传资源之前,请先做好这些...想到一句好玩的话:知道是你干的，只是懒得抓你!如果你喜欢python,喜欢故事,请点赞或关注我!您的支持是对作者最大的鼓励！

import PyPDF2
from PyPDF2 import PdfFileReader
import sys
import os
import re

#获取目录下所有的pdf文件目录
def getFiles():

    files = os.listdir()

    # 如果输入了单个pdf文件,则只输出单个pdf元数据
    try:
        if sys.argv[1]:
            files = [sys.argv[1]]
    except:
        pass

    pdf_files = list()

    for file_name in files:
        try:
            result = re.match(r".*\.pdf$", file_name)
            
            if result:
                pdf_files.append(file_name)
        except Exception as e:
            pass


    return pdf_files


# 打印文件的元信息
def printMeta(files):
        for filename in files:
            try:
                pdfFile= PdfFileReader(open(filename, "rb"))
                docInfo = pdfFile.getDocumentInfo()
                print ("===文件%s的元信息为:"%filename)
                for metaItem in docInfo:
                    print(metaItem,":",docInfo[metaItem])
            except Exception as e:
                print("---文件%s元数据无法读取,已经跳过!"%filename)

if __name__ == "__main__":
    filenames = getFiles()
    printMeta(filenames)

import sys
import os
import re
from PyPDF2 import PdfFileReader, PdfFileWriter

#获取目录下所有的pdf文件
def getFiles():
    files = os.listdir()
    pdf_files = list()

    for file_name in files:
        try:
            result = re.match(r".*\.pdf$", file_name)
            
            if result:
                pdf_files.append(file_name)
        except Exception as e:
            pass

    return pdf_files


def get_page_num(file_name):
    #获取一个pdfFileReader对象
    my_pdf = PdfFileReader(open(file_name,"rb"))

    # 获取页数
    page_num = my_pdf.getNumPages()
    print("PDF文件%s的页数为%s"%(file_name, page_num))
    return page_num

    

def create_new_pdf(file_names):
    try:
        os.mkdir("./pure")
    except Exception as e:
        pass
    
    for file_name in file_names:

        try:
            # 获取原pdf的信息
            my_pdf = PdfFileReader(open(file_name,"rb"))

            # 创建一个PdfFileWriter对象
            new_pdf = PdfFileWriter()
            
            for i in range(0, get_page_num(file_name)):
                
                page_info = my_pdf.getPage(i)

                new_pdf.addPage(page_info)

            new_pdf.write(open("./pure/%s"%file_name, "wb"))
            print("文件%s已清除元数据!"%file_name)
        except Exception as e:
            print("文件%s编码有问题,已自动跳过!"%file_name)



if __name__ == "__main__":
    create_new_pdf(getFiles());