Python常用文件操作

== 本系列记录办公时常用的Python文件操作 ==

1.TXT读写操作

1.1 读取文件名至TXT中

=== 读取文件夹名输出至txt文件===
def getfoderList(foderPath):
    fList=[fl for fl in os.listdir(foderPath) if os.path.isdir(os.path.join(foderPath,fl))]
    return fList
    
def writeFpToTxt(flist,foderPath):
    filepath=os.path.join(foderPath,"文件夹名.txt")
    with open(filepath,'w+') as txtf: #不存在则创建
        for f in flist:
            txtf.write(f+"\n")
    txtf.close()
    
if __name__ == "__main__":
    foderPath=r"Y:\BIM大赛"
    fl=getfoderList(foderPath)
    writeFpToTxt(fl,foderPath)
    

2.EXCEL读写操作

2.1 采用openpyxl读写填XLSX

import os,time
from openpyxl import Workbook,load_workbook
from openpyxl.styles import PatternFill,colors

=== 读取指定后缀文件名===
def getfileList(foderPath):
    flist = [fn.split('-')[0] for fn in os.listdir(foderPath) if(os.path.splitext(fn)[1] in [".doc",".docx",".pdf"])]#举例示意可进行的操作
    return flist
    
===查找文件名，更新汇总台账====
def updateExcel():
    foderpath=os.getcwd()#sys.path[0]
    wb=load_workbook(foderpath+r"\高企课题台账模板.xlsx")
    ws=wb['公司高企课题清单']#wb.sheetnames[0]
    l_l=getfileList(foderpath+r"\立项报告自查汇总")# 采用 1.1节 getfileList()方法

    i = 3
    while i<ws.max_row:
        c=str(i)
        cfill=PatternFill(fill_type='solid',fgColor='FF0000')
        cell_i=ws.cell(i,2).value.split('/')[0]
        if cell_i in l_l:#先行后列,索引下标
            ws['G'+c].value="是"
        else:
            ws['G'+c].value=""
            ws['G'+c].fill=cfill
        i+=1
    strTime=str(time.strftime("%Y-%m-%d", time.localtime()))
    wb.save(foderpath+r'\高企课题资料实时台账'+strTime+'.xlsx')

3. WORD文件操作

3.1 WORD批量转PDF

======文件夹下所有word转pdf========
def doc_pdf(foderPath):
    succ=0
    flist=list(filter(lambda x:x.endswith('.doc') or x.endswith('.docx'),os.listdir(foderPath)))
    word = Dispatch('Word.Application')
    ##word = gencache.EnsureDispatch('Word.Application')
    try:
        for fpath in flist:
            doc = word.Documents.Open(foderPath+"\\"+fpath, ReadOnly=1)
            pdf = foderPath+"\\"+fpath.split('.doc')[0] + '.pdf'
            doc.ExportAsFixedFormat(pdf, constants.wdExportFormatPDF, Item=constants.wdExportDocumentWithMarkup,
                                    CreateBookmarks=constants.wdExportCreateHeadingBookmarks)
            succ+=1
        print(str(succ)+'word file successfully converted to pdf file!')
    except Exception as e:
        print('Error,exception is:{}'.format(e))
    finally:
        word.Quit(constants.wdDoNotSaveChanges)

4. PDF文件操作

4.1 PDF文件合并

======文件夹下所有pdf文件用空白页补充为偶数页后再合并========
def mergePdfWithBlank(foderPath,blankpdfPath=os.getcwd()+"\\blank.pdf"):
    #flist = filter(lambda x: x.endswith('.pdf'), os.listdir(foderPath)).sort(key=lambda x: int(x[:-4]), reverse=False)
    optPageNums=0
    succ=0
    merger=PdfFileMerger()
    flist=glob.glob(foderPath+'\*.pdf')#空白页不能放在文件夹下
    try:
        blankpdf=PdfFileReader(open(blankpdfPath,'rb'))
        for file in flist:
            pdf=PdfFileReader(open(file,'rb'))
            pageNum=pdf.numPages+1
            optPageNums+=pageNum
            succ+=1
            if pageNum & 1:#是偶数
                merger.append(pdf)
            else:
                merger.append(pdf)
                merger.append(blankpdf)
                optPageNums += 1
        merger.write(os.path.join(foderPath,'合并.pdf'))
        print(succ+'pdf file successfully combined to <合并.pdf>pdf file!')
    except Exception as e:
        print('Error,exception is:{}'.format(e))  # 格式化e
    finally:
        merger.close()

========创建空白PDF文件========
def newBlankPdf(foderPath):
    word = gencache.EnsureDispatch('Word.Application')
    newdoc = word.Documents.Add
    blankpdfPath = os.path.join(foderPath, '空白.pdf')
    newdoc.SaveAs(blankpdfPath, FileFormat=17)
    newdoc.Close()
    word.Quit()
    return blankpdfPath

5. 主方法和脚本使用

======第3、4节主方法命令=======
if __name__ == "__main__":
    description = '\n' + '本脚本用来转换word并合并pdf文件，同时奇数页PDF插入空白页，输出的pdf文件(合并.pdf)按输入的pdf文件名生成书签\n使用示例如下：'
    description = description + '\n' + 'python Docs2pdf.py -f "0" -p "D:\pdf-files" '
    description = description + '\n' + "要合并的pdf文件所在的路径： D:\pdf-files"

parser = ArgumentParser(description=description, formatter_class=RawTextHelpFormatter)
parser.add_argument("-f","--function",dest="func",type=int,default=1,help="选择功能:\n 0  ---文件夹下word合并 \n 1 ---文件夹下word转pdf并合并pdf \n 2  ---文件夹下pdf合并")
parser.add_argument("-p", "--path", dest="path", default=r"C:\Users\30624\Desktop\Test", help="要操作的文件所在目录")
args = parser.parse_args()
if not args.func==1:
    args.func=int(input("选择功能:\n 0  ---文件夹下word合并 \n 1 ---文件夹下word转pdf并合并pdf \n 2  ---文件夹下pdf合并"))
    args.path=input("要合并的pdf文件所在的路径：如 D:\pdf-files")
if args.func==0:
    mergeDoc(args.path)
if args.func==1:
    doc_pdf(args.path)
    mergePdfWithBlank(args.path)
else:
    mergePdfWithBlank(args.path)

=====本脚本使用方法=======
# 方法一 cd /d 进入脚本路径，输入python Docs2pdf.py -f 1 -p "C:\Users\30624\Desktop\Test"
# 方法二 调出cmd，直接将脚本拖进去
# 方法三 进入Python脚本所在的文件夹，shift+右击，选择“在此处打开命令窗口”，按TAB键切换文件，选择目标python脚本