基于python 3.7和pypdf2开发的pdf文件合并工具代码

#https://blog.csdn.net/kmesky/article/details/102695520 #coding=utf8 import tkinter as tk from tkinter import ttk from tkinter import filedialog from tkinter import messagebox #弹窗库 from PyPDF2 import PdfFileReader, PdfFileWriter import os MERGE_NONE = 0 MERGE_FILES = 1 MERGE_FOLDER = 2 def get_screen_size(window): return window.winfo_screenwidth(), window.winfo_screenheight() def get_window_size(window): return window.winfo_reqwidth(), window.winfo_reqheight() def center_window(root, width, height): screenwidth = root.winfo_screenwidth() screenheight = root.winfo_screenheight() size = '%dx%d+%d+%d' % (width, height, (screenwidth - width)/2, (screenheight - height)/2) root.geometry(size) root.resizable(0,0) # Create instance win = tk.Tk() # Add a title win.title("PDF Merger") win.iconbitmap("pdfMerger.ico") #设定600*450居中,不可调整大小 center_window(win, 600, 450) def setFileAndPage(fname, pdf, ps): pdf.set(fname) input = PdfFileReader(open(fname, "rb")) # 获得源PDF文件中页面总数 pageCount = input.getNumPages() ps.set("1-{}".format(pageCount)) def openPdfFile1(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf1, ps1) def openPdfFile2(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf2, ps2) def openPdfFile3(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf3, ps3) def openPdfFile4(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf4, ps4) def openPdfFile5(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf5, ps5) def openPdfFile6(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf6, ps6) def openPdfFile7(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf7, ps7) def openPdfFile8(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf8, ps8) def openPdfFile9(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf9, ps9) def openPdfFile10(): fname = filedialog.askopenfilename(title='打开Pdf文件', filetypes=[('Pdf file', '*.pdf'), ('All Files', '*')]) setFileAndPage(fname, pdf10, ps10) def openPdfFolder(): folderName = filedialog.askdirectory(title="选择pdf文件夹") print(folderName) foundPdf = False for path, dirnames, filenames in os.walk(folderName): for filename in filenames: if filename.lower().endswith(".pdf"): foundPdf = True break if foundPdf: folder.set(folderName) else: messagebox.showerror(folderName,'未找到pdf文件！！！') #判断当前页码是否在选择的页码范围之内 #pageScope 1-5,10-20,15-30,3,5,- def inPageScope(curPage, pageScope): if pageScope == "": return False else: scopes = pageScope.split(",") for scope in scopes: if scope == "-": return True elif '-' not in scope: return curPage+1 == scope else: limits = scope.split("-") if (limits[0] == "" or curPage+1 >= int( limits[0]) ) and \ (limits[1] == "" or curPage+1 <= int( limits[1]) ): return True else: continue return False def mergeExtractedPdf(pdfFiles, outfile): try: print(outfile) output = PdfFileWriter() outputPages = 0 for pdf_file,ps in pdfFiles: print(pdf_file) print(ps) print("路径：%s"%pdf_file) if pdf_file == "" or ps == "": continue try: # 读取源PDF文件 input = PdfFileReader(open(pdf_file, "rb"), strict = False) # 获得源PDF文件中页面总数 pageCount = input.getNumPages() print("页数：%d"%pageCount) # 分别将page添加到输出output中 for iPage in range(pageCount): if inPageScope(iPage, ps): output.addPage(input.getPage(iPage)) outputPages += 1 except: continue print("合并后的总页数:%d."%outputPages) # 写入到目标PDF文件 #outputStream = open(os.path.join(filepath, outfile), "wb") outputStream = open(outfile, "wb") output.write(outputStream) outputStream.close() messagebox.showinfo("合并后的总页数:%d."%outputPages, "PDF文件合并完成！") except Exception as e: messagebox.showerror("合并pdf出错", str(e)) # 使用os模块的walk函数，搜索出指定目录下的全部PDF文件 # 获取同一目录下的所有PDF文件的绝对路径 def getPdfFiles(filedir): file_list = [os.path.join(root, filespath) \ for root, dirs, files in os.walk(filedir) \ for filespath in files \ if str(filespath).endswith('pdf') ] return file_list if file_list else [] # 合并同一目录下的所有PDF文件 def mergePDF(filepath, outfile): output = PdfFileWriter() outputPages = 0 pdfFiles= getPdfFiles(filepath) if pdfFiles: for pdf_file in pdfFiles: print("路径：%s"%pdf_file) # 读取源PDF文件 input = PdfFileReader(open(pdf_file, "rb")) # 获得源PDF文件中页面总数 pageCount = input.getNumPages() outputPages += pageCount print("页数：%d"%pageCount) # 分别将page添加到输出output中 for iPage in range(pageCount): output.addPage(input.getPage(iPage)) print("合并后的总页数:%d."%outputPages) # 写入到目标PDF文件 #outputStream = open(os.path.join(filepath, outfile), "wb") outputStream = open(outfile, "wb") output.write(outputStream) outputStream.close() messagebox.showinfo("提示", "PDF文件合并完成！") else: messagebox.showinfo("提示", "没有可以合并的PDF文件！") # 选择文件 selFiles = ttk.LabelFrame(win, text="选择文件或文件夹，页码范围：1-3,5-8,3(单页),4,-(全部页码)",width=560) selFiles.grid(column=0, row=0, padx=4, pady=10) #可以选择十个pdf文件 #pdfFile1 curRow = 0 lblF1 = ttk.Label(selFiles, text="文件1：") lblF1.grid(column=0, row=curRow, sticky='W', pady=4) pdf1 = tk.StringVar() pdfFile1 = ttk.Entry(selFiles, textvariable=pdf1, width=48) pdfFile1.grid(column=1, row=curRow, sticky='W', padx=4, pady=4) btn1 = ttk.Button(selFiles, text='...', width=5, command=openPdfFile1) btn1.grid(column=2, row=curRow, sticky='W', pady=4) label1 = ttk.Label(selFiles, text="页码范围：") label1.grid(column=3, row=curRow, sticky='W', pady=4) ps1 = tk.StringV