# -*- coding:utf-8*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import os
import os.path
from pyPdf import PdfFileReader,PdfFileWriter
import time
time1=time.time()
# 使用os模塊walk函數(shù)，搜索出某目錄下的全部pdf文件
######################獲取同一個(gè)文件夾下的所有PDF文件名#######################
def getFileName(filepath):
  file_list = []
  for root,dirs,files in os.walk(filepath):
    for filespath in files:
      # print(os.path.join(root,filespath))
      file_list.append(os.path.join(root,filespath))
  return file_list
##########################合并同一個(gè)文件夾下所有PDF文件########################
def MergePDF(filepath,outfile):
  output=PdfFileWriter()
  outputPages=0
  pdf_fileName=getFileName(filepath)
  for each in pdf_fileName:
    print each
    # 讀取源pdf文件
    input = PdfFileReader(file(each, "rb"))
    # 如果pdf文件已經(jīng)加密，必須首先解密才能使用pyPdf
    if input.isEncrypted == True:
      input.decrypt("map")
    # 獲得源pdf文件中頁面總數(shù)
    pageCount = input.getNumPages()
    outputPages += pageCount
    print pageCount
    # 分別將page添加到輸出output中
    for iPage in range(0, pageCount):
      output.addPage(input.getPage(iPage))
  print "All Pages Number:"+str(outputPages)
  # 最后寫pdf文件
  outputStream=file(filepath+outfile,"wb")
  output.write(outputStream)
  outputStream.close()
  print "finished"
if __name__ == '__main__':
  file_dir = r'D:/course/'
  out=u"第一周.pdf"
  MergePDF(file_dir,out)
  time2 = time.time()
  print u'總共耗時(shí)：' + str(time2 - time1) + 's'

"D:\Program Files\Python27\python.exe" D:/PycharmProjects/learn2017/合并多個(gè)PDF文件.py
D:/course/C1W1L01 Welcome.pdf
3
D:/course/C1W1L02 WhatIsNN.pdf
4
D:/course/C1W1L03 SupLearnWithNN.pdf
4
D:/course/C1W1L04 WhyIsDLTakingOff.pdf
3
D:/course/C1W1L05 AboutThisCourse.pdf
3
D:/course/C1W1L06 CourseResources.pdf
3
All Pages Number:20
finished
總共耗時(shí)：0.128000020981s
Process finished with exit code 0