Python - PyPDF2模块的基本操作

1. 安装

命令：pip install pypdf2

2. 应用

2.1 获取PDF文件的基本信息

​x
1
from PyPDF2 import PdfReader
2

3
# PDF文件
4
path = 'demo.pdf'
5

6
with open(path,'rb') as rbf:
7
    pdf_read = PdfReader(rbf)
8
    # 获取PDF文件的基本信息对象
9
    info = pdf_read.metadata
10
    dic = {
11
        '页数':len(pdf_read.pages),
12
        '标题':info.get('/Title'),
13
        '作者':info.get('/Author'),
14
        '创建时间':info.get('/CreationDate'),
15
        '修改时间':info.get('/ModDate'),
16
        'PDF版本':pdf_read.pdf_header
17
            }
18
    print(dic)
19
    
20
# 输出结果
21
{'页数': 145, '标题': 'Python手册-0620', '作者': 'Liu Qianqian', '创建时间': 'D:20160620028668Z', '修改时间': "D:20160620130185+08'00'", 'PDF版本': '%PDF-1.3'}

2.2 将PDF文件拆分成多个PDF文件

2.2.1 将PDF文件每一页拆分成一个PDF文件

xxxxxxxxxx
17
1
from PyPDF2 import PdfReader,PdfWriter
2

3
# PDF文件
4
path = 'demo.pdf'
5

6
pdf_read = PdfReader(path)
7

8
# 获取PDF文件页数
9
pages = len(pdf_read.pages)
10

11
for i in range(0,pages):
12
    page = pdf_read.pages[i]
13
    pdf_write = PdfWriter()
14
    pdf_write.add_page(page)
15
    save_name = str(i+1).zfill(3) + '.pdf'  # str(i+1)因为i是从0开始
16
    with open(save_name,'wb') as wbf:
17
        pdf_write.write(wbf)

2.2.2 将PDF文件每十页拆分成一个PDF文件

xxxxxxxxxx
18
1
from PyPDF2 import PdfReader,PdfWriter
2

3
# PDF文件
4
path = 'demo.pdf'
5

6
pdf_read = PdfReader(path)
7

8
# 获取PDF文件页数
9
pages = len(pdf_read.pages)
10

11
for i in range(0,pages,10):
12
    pdf_write = PdfWriter()
13
    for j in range(i,min(i+10,pages)):
14
        page = pdf_read.pages[j]
15
        pdf_write.add_page(page)
16
    save_name = str(i+1).zfill(3) + '.pdf'  # str(i+1)因为i是从0开始
17
    with open(save_name,'wb') as wbf:
18
        pdf_write.write(wbf)

2.3 将多个PDF文件合并为一个PDF文件

xxxxxxxxxx
14
1
from PyPDF2 import PdfReader,PdfMerger
2

3
# 需要合并的PDF文件名列表
4
files = ['demo.pdf','demo1.pdf','demo2.pdf','demo3.pdf']
5

6
# 合并以后的PDF文件
7
new_path = 'demo4.pdf'
8

9
pdf_joint = PdfMerger()
10

11
for file in files:
12
    pdf_joint.append(PdfReader(file))
13

14
pdf_joint.write(new_path)

2.4 将PDF文件加密

xxxxxxxxxx
20
1
from PyPDF2 import PdfReader,PdfWriter
2

3
# PDF文件
4
path = 'demo.pdf'
5

6
# 加密后的PDF文件
7
new_path = 'demo_encryption.pdf'
8

9
pdf_read = PdfReader(path)
10

11
pdf_write = PdfWriter()
12

13
pages = len(pdf_read.pages)
14

15
for i in range(pages):
16
    pdf_write.add_page(pdf_read.pages[i])
17
# 加密
18
pdf_write.encrypt(user_password='123456',use_128bit=True)
19
with open(new_path,'wb') as wbf:
20
    pdf_write.write(wbf)

2.5 将PDF文件解密

xxxxxxxxxx
25
1
from PyPDF2 import PdfReader,PdfWriter
2

3
# 需解密的PDF文件
4
path = 'demo_encryption.pdf'
5

6
# 解密后的PDF文件
7
new_path = 'demo.pdf'
8

9
# 密码
10
pwd = '123456'
11

12
pdf_read = PdfReader(path)
13

14
pdf_write = PdfWriter()
15

16
# 解密
17
pdf_read.decrypt(pwd)
18

19
pages = len(pdf_read.pages)
20

21
for i in range(pages):
22
    page = pdf_read.pages[i]
23
    pdf_write.add_page(page)
24
    with open(new_path,'wb') as wbf:
25
        pdf_write.write(wbf)

2.6 将PDF文件添加水印

xxxxxxxxxx
26
1
from PyPDF2 import PdfReader,PdfWriter
2

3
# PDF文件
4
path = 'demo.pdf'
5

6
# 水印文件
7
water_path = 'water.pdf'
8

9
# 加完水印后的PDF文件
10
new_path = 'demo_water.pdf'
11

12
# 创建水印页对象
13
water_page = PdfReader(water_path).pages[0]
14

15
pdf_read = PdfReader(path)
16

17
pdf_write = PdfWriter()
18

19
page_num = len(pdf_read.pages)
20

21
for i in range(page_num):
22
    page = pdf_read.pages[i]
23
    page.merge_page(water_page)
24
    pdf_write.add_page(page)
25
    with open(new_path,'wb') as wbf:
26
        pdf_write.write(wbf)