def newdir(self,path):
            self.new = os.path.splitext(path)[0]
            if not os.path.isdir(self.new): #使用os.path.isdir判断文件夹是否存在，
                os.mkdir(self.new)

 1 def pdfsplt(self,path):
 2                     if os.path.isfile(path):
 3                             file_1 = open(path,"rb")
 4                             file_reader = PyPDF2.PdfFileReader(file_1, strict=False)  #使用strict关闭错误提示
 5                             #使用for循环读取每一页并将其写入新pdf文件，文件以页码命名
 6                             for page in range(0,file_reader.getNumPages()):
 7                                 file_write = PyPDF2.PdfFileWriter()
 8                                 pageobj = file_reader.getPage(page)
 9                                 file_write.addPage(pageobj)
10                                 output = str(self.new) + "\\" + str(int(page+1)) + ".pdf"
11                                 with open(output,"wb") as output_pdf:
12                                         file_write.write(output_pdf)
13                             file_1.close()
14                     else:
15                             print("文件不存在！")
16                            time.sleep(3)
17                             exit()

1 def pdfremove(self,number):
2     for pag in number:
3         filename = str(self.new) + "\\" + str(pag) + ".pdf"
4         if os.path.isfile(filename):
5             os.unlink(filename)
6         else:
7             print("请确认要删除的页码%s是否正确！！"%pag)

 1 def pdfmerge(self):
 2     file_list = [int(os.path.splitext(x)[0]) for x in os.listdir(self.new)]  #读取新建文件夹下的所有文件并提取文件名转为数字
 3     file_write = PyPDF2.PdfFileWriter() #先创建一个新的pdf对象
 4     for page in sorted(file_list):
 5         pathstr = str(self.new) + "\\" + str(page) + ".pdf"
 6         file_1 = open(pathstr,"rb")
 7         file_reader = PyPDF2.PdfFileReader(file_1, strict=False)  # 使用strict关闭错误提示
 8         pageobj = file_reader.getPage(0)
 9         file_write.addPage(pageobj)
10         output = str(self.new) + "_new.pdf"
11         with open(output, "wb") as output_pdf:
12             file_write.write(output_pdf)
13             print("第%s页完成"%page)
14         file_1.close()

1 def rmdir(self):
2     if os.path.isdir(self.new):
3         shutil.rmtree(self.new)

 1 import PyPDF2
 2 import os,time,shutil,sys
 3 import threading
 4 
 5 class mypdf(object):
 6     def __init__(self,path,number):
 7         self.newdir(path)
 8         self.pdfsplt(path)
 9         self.pdfremove(number)
10         self.pdfmerge()
11         self.rmdir()
12         pass
13 
14     #用于创建一个独立的文件夹，存放缓存数据
15     def newdir(self,path):
16         self.new = os.path.splitext(path)[0]
17         if not os.path.isdir(self.new): #使用os.path.isdir判断文件夹是否存在，
18             os.mkdir(self.new)
19 
20     #将每一页生成独立文件，存放到缓存文件夹
21     def pdfsplt(self,path):
22         if os.path.isfile(path):
23             file_1 = open(path,"rb")
24             file_reader = PyPDF2.PdfFileReader(file_1, strict=False)  #使用strict关闭错误提示
25             #使用for循环读取每一页并将其写入新pdf文件，文件以页码命名
26             for page in range(0,file_reader.getNumPages()):
27                 file_write = PyPDF2.PdfFileWriter()
28                 pageobj = file_reader.getPage(page)
29                 file_write.addPage(pageobj)
30                 output = str(self.new) + "\\" + str(int(page+1)) + ".pdf"
31                 with open(output,"wb") as output_pdf:
32                     file_write.write(output_pdf)
33             file_1.close()
34         else:
35             print("文件不存在！")
36             time.sleep(3)
37             exit()
38 
39     #删除缓存文件夹中的不要的页
40     def pdfremove(self,number):
41         for pag in number:
42             filename = str(self.new) + "\\" + str(pag) + ".pdf"
43             if os.path.isfile(filename):
44                 os.unlink(filename)
45             else:
46                 print("请确认要删除的页码%s是否正确！！"%pag)
47 
48     #将缓存文件夹中的剩余文件合进行合并
49     def pdfmerge(self):
50         file_list = [int(os.path.splitext(x)[0]) for x in os.listdir(self.new)]  #读取新建文件夹下的所有文件并提取文件名转为数字
51         file_write = PyPDF2.PdfFileWriter() #先创建一个新的pdf对象
52         for page in sorted(file_list):
53             pathstr = str(self.new) + "\\" + str(page) + ".pdf"
54             file_1 = open(pathstr,"rb")
55             file_reader = PyPDF2.PdfFileReader(file_1, strict=False)  # 使用strict关闭错误提示
56             pageobj = file_reader.getPage(0)
57             file_write.addPage(pageobj)
58             output = str(self.new) + "_new.pdf"
59             with open(output, "wb") as output_pdf:
60                 file_write.write(output_pdf)
61                 print("第%s页完成"%page)
62             file_1.close()
63 
64     def rmdir(self):
65         if os.path.isdir(self.new):
66             shutil.rmtree(self.new)
67 
68 if __name__ == "__main__":
69     #通过第一个参数获取待处理的文件，第二个参数到以后为删除的页码
70     path = sys.argv[1]
71     number = sys.argv[2:]
72     mypdf = mypdf(path,number)
73     def f(path,number):
74         mypdf(path,number)
75     threading.Thread(target=f,args=[path,number])

 1 def pdfsplt(self,path,number):
 2         print(number,type(number))
 3         if os.path.isfile(path):
 4             file_1 = open(path,"rb")
 5             file_reader = PyPDF2.PdfFileReader(file_1, strict=False)  #使用strict关闭错误提示
 6             file_write = PyPDF2.PdfFileWriter()
 7             #使用for循环读取每一页并将其写入新pdf文件，文件以页码命名
 8             for page in range(0,file_reader.getNumPages()):
 9                 if page not in number:
10                     pageobj = file_reader.getPage(page)
11                     file_write.addPage(pageobj)
12                     output = str(self.new) + "_new.pdf"
13                     with open(output,"wb") as output_pdf: 
14                         file_write.write(output_pdf)
15             file_1.close()
16         else:
17             print("文件不存在！")
18             time.sleep(3)
19             exit()

 1 def pdfsplt(self,path,number):
 2         print(number,type(number))
 3         if os.path.isfile(path):
 4             file_1 = open(path,"rb")
 5             file_reader = PyPDF2.PdfFileReader(file_1, strict=False)  #使用strict关闭错误提示
 6             file_write = PyPDF2.PdfFileWriter()
 7             #使用for循环读取每一页并将其写入新pdf文件，文件以页码命名
 8             for page in range(0,file_reader.getNumPages()):
 9                 if page not in number:
10                     pageobj = file_reader.getPage(page)
11                     file_write.addPage(pageobj)
12             output = str(self.new) + "_new.pdf"
13             with open(output,"wb") as output_pdf: #将内容全部放入内存，最后写入，提高处理速度
14                 file_write.write(output_pdf)
15             file_1.close()
16         else:
17             print("文件不存在！")
18             time.sleep(3)
19             exit()

 1 import PyPDF2
 2 import os,time,shutil,sys
 3 import threading
 4 
 5 class mypdf(object):
 6     def __init__(self,path,number):
 7         self.new = os.path.splitext(path)[0] #获取文件的路径
 8         self.pdfsplt(path,number)
 9         pass
10 
11  #循环每一页读入内存，最后写入文件
12     def pdfsplt(self,path,number):
13         print(number,type(number))
14         if os.path.isfile(path):
15             file_1 = open(path,"rb")
16             file_reader = PyPDF2.PdfFileReader(file_1, strict=False)  #使用strict关闭错误提示
17             file_write = PyPDF2.PdfFileWriter()
18             #使用for循环读取每一页并将其写入新pdf文件，文件以页码命名
19             for page in range(0,file_reader.getNumPages()):
20                 if page not in number:
21                     pageobj = file_reader.getPage(page)
22                     file_write.addPage(pageobj)
23             output = str(self.new) + "_new.pdf"
24             with open(output,"wb") as output_pdf: #将内容全部放入内存，最后写入，提高处理速度
25                 file_write.write(output_pdf)
26             file_1.close()
27         else:
28             print("文件不存在！")
29             time.sleep(3)
30             exit()
31 
32 if __name__ == "__main__":
33     #通过第一个参数获取待处理的文件，第二个参数到以后为删除的页码
34     path = sys.argv[1]
35     number = sys.argv[2:]
36     number = list(map(int, number))
37     mypdf = mypdf(path,number)
38     def f(path,number):
39         mypdf(path,number)
40     threading.Thread(target=f,args=[path,number])