1

pip install PyMuPDF

1

2

import fitz

doc = fitz.open("example.pdf")

1

2

page_count = doc.page_count 

print("Number of pages:", page_count)

1

2

text = page.get_text() 

print("Extracted text:", text)

1

doc.save("modified_example.pdf")

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

import fitz

import os

def split_pdf(pdf_path):

    # 检查输入的PDF文件是否存在

    if not os.path.exists(pdf_path):

        print("您输入的路径无pdf文件！")

        return

        # 打开pdf文件

    doc = fitz.open(pdf_path)

    page_count = len(doc)

    print(f"该pdf文件页数为：{page_count}")

    while True:

        # 获取起始页码（0基索引）

        page_num1 = None

        while True:

            try:

                user_input = input("请输入您拆分的起始页码（输入q/Q退出）：")

                if user_input.lower() == 'q':

                    doc.close()

                    return

                page_num1 = int(user_input) - 1

                if page_num1 < 0 or page_num1 >= page_count:

                    print("起始页码无效，请重新输入。")

                else:

                    break

            except ValueError:

                print("请输入有效的起始页码或q/Q退出。")

        # 获取结束页码（0基索引）

        page_num2 = None

        while True:

            try:

                user_input = input("请输入您拆分的截止页码（输入q/Q退出）：")

                if user_input.lower() == 'q':

                    doc.close()

                    return

                page_num2 = int(user_input) - 1

                if page_num2 < 0 or page_num2 >= page_count:

                    print("截止页码无效，请重新输入。")

                else:

                    break

            except ValueError:

                print("请输入有效的截止页码或q/Q退出。")

        # 创建一个新的PDF文档并插入指定的页面范围

        new_doc = fitz.open()

        new_doc.insert_pdf(doc, from_page=page_num1, to_page=page_num2)

        # 获取用户输入的PDF基础名字和保存目录

        pdf_base_name = input("请输入您的PDF基础名字：")

        if not pdf_base_name.lower().endswith('.pdf'):

            pdf_name = f"{pdf_base_name}_{page_num1 + 1}-{page_num2 + 1}.pdf"

        else:

            pdf_name = f"{pdf_base_name[:-4]}_{page_num1 + 1}-{page_num2 + 1}.pdf"

        save_dir = input("请输入您想要保存PDF的目录（例如：C:/Users/YourName/Documents/）：")

        # 确保目录末尾有斜杠，并检查目录是否存在

        if not save_dir.endswith(os.sep) and save_dir != "":

            save_dir += os.sep

        os.makedirs(save_dir, exist_ok=True)

        output_path = os.path.join(save_dir, pdf_name)

        new_doc.save(output_path)

        new_doc.close()

        print(f"Saved: {output_path}")

        # 检查是否继续拆分或退出

        is_continue = input("是否继续拆分其他页面范围（q/Q退出）？").strip().lower()

        if is_continue == 'q':

            doc.close()

            break

# 调用函数进行PDF拆分

pdf_path = input("请输入您需要拆分的PDF路径：")

split_pdf(pdf_path)