python PyPDF2处理PDF文件

python PyPDF2处理PDF文件

• 安装PyPDF2

pip install PyPDF2

• 官方文档：
  • https://pypdf2.readthedocs.io/en/latest/
• 导入模块

import PyPDF2

1. 读取PDF中的内容

# author:mlnt
# createdate:2022/8/16
import PyPDF2    # 导入PyPDF2模块

# 官方文档：https://pypi.org/project/PyPDF2/
# 1.打开PDF文件
pdf = open(file='test.pdf', mode='rb')  # 以二进制方式打开

# 2.获取PDF文件的页数
# 打开PDF文件成功后，可使用PdfFileReader()方法读取PDF内容
pdf_reader = PyPDF2.PdfFileReader(pdf)  # 读取PDF内容
print(f'PDF页数为：{pdf_reader.numPages}')
print(f'PDF页数为：{len(pdf_reader.pages)}')

# 3.读取PDF页面内容
"""
- 使用PdfFileReader()方法读取PDF文件后，可使用getPage(n)（或pages[n]）获取第n页的PDF内容
- PDF页面从第0页开始计算
- 页面内容被读入后，可使用extractText()取得该页的字符串内容
"""
for i in range(pdf_reader.numPages):
    pageObj = pdf_reader.getPage(i)  # 读取第i页内容
    # pageObj = pdf_reader.pages[i]  # 读取第i页内容
    page_content = pageObj.extractText()  # 提取页面内容
    print(page_content)

test.pdf：

读取效果：

2. PDF简单加密与解密

# author:mlnt
# createdate:2022/8/16

import PyPDF2
from PyPDF2 import PdfReader, PdfWriter


def checkEncrypted(filename):
    """检查文件是否加密"""
    pdfObj = open(file=filename, mode='rb')  # 以二进制方式打开
    pdfRd = PyPDF2.PdfFileReader(pdfObj)  # 读取PDF内容
    # 判断文件是否加密
    if pdfRd.isEncrypted:
        print(f'{filename}属于加密文件')
    else:
        print(f'{filename}未加密')


def pdfEncrypt(filename):
    """pdf加密"""
    reader = PdfReader(filename)  # 创建RdfReader对象
    writer = PdfWriter()  # 创建PdfWriter对象

    # 将所有页面添加到writer
    for page in reader.pages:
        # PDF页面旋转
        page.rotate_clockwise(90)  # 旋转90度
        page.rotate_clockwise(-180)  # 逆时针旋转180度
        writer.add_page(page)

    # 添加密码
    writer.encrypt('123456')

    new_name = filename[:filename.rfind('.pdf')] + '-encrypted.pdf'
    # 保存pdf
    with open(new_name, 'wb') as f:
        writer.write(f)


def pdfDecrypt(filename):
    """pdf解密"""
    reader = PdfReader(filename)
    writer = PdfWriter()

    # 判断是否加密
    if reader.isEncrypted:
        reader.decrypt('123456')

    for page in reader.pages:
        writer.add_page(page)

    new_name = filename[:filename.rfind('.pdf')] + '-decrypted.pdf'
    # 保存pdf
    with open(new_name, 'wb') as f:
        writer.write(f)


checkEncrypted('test.pdf')
pdfEncrypt('test.pdf')
pdfDecrypt('test-encrypted.pdf')

3. 合并PDF文件

# author:mlnt
# createdate:2022/8/16
from PyPDF2 import PdfMerger

merger = PdfMerger()  # 创建PdfMerger对象

pdf1 = open('test.pdf', 'rb')

pdf2 = open('watermark.pdf', 'rb')

# 将整个文档添加到merger
merger.append(fileobj=pdf1)

# 将pdf2插入到merger，从第0页开始
merger.merge(position=0, fileobj=pdf2)

with open('merger-test.pdf', 'wb') as f:
    merger.write(f)

merger.close()

watermark.pdf：

合并效果：

4.处理PDF页面重叠

# author:mlnt
# createdate:2022/8/16
import PyPDF2
from PyPDF2 import PdfReader, PdfWriter

reader1 = PdfReader('test.pdf')  # 创建RdfReader对象
reader2 = PdfReader('watermark.pdf')  # 创建RdfReader对象

writer = PdfWriter()  # 创建PdfWriter对象

# 将所有页面添加到writer
for page in reader1.pages:
    # 执行重叠合并
    page.merge_page(reader2.pages[0])
    # 添加到新的PDF对象
    writer.add_page(page)

# 保存pdf
with open('test-watermark.pdf', 'wb') as f:
    writer.write(f)

效果：

5. 添加水印到pdf

from pathlib import Path
from typing import Union, List

from PyPDF2 import PdfWriter, PdfReader
from typing_extensions import Literal


def watermark(
    content_pdf: Path,
    watermark_pdf: Path,
    pdf_result: Path,
    page_indices: Union[Literal["ALL"], List[int]] = "ALL",
):
    """
    添加水印
    :param content_pdf: 要添加水印的pdf文件
    :param watermark_pdf: 水印pdf
    :param pdf_result:  处理后保存的文件名
    :param page_indices: 页面目录
    :return:
    """
    reader = PdfReader(content_pdf)
    if page_indices == "ALL":
        page_indices = list(range(0, len(reader.pages)))

    writer = PdfWriter()
    for index in page_indices:
        content_page = reader.pages[index]
        mediabox = content_page.mediabox

        # 读取水印pdf文件
        reader_watermark = PdfReader(watermark_pdf)
        # 获取水印pdf文件第1页的内容
        image_page = reader_watermark.pages[0]
        # 将两个页面的内容流合并为一个
        image_page.merge_page(content_page)
        image_page.mediabox = mediabox
        writer.add_page(image_page)
    # 保存处理后的内容
    with open(pdf_result, "wb") as fp:
        writer.write(fp)


watermark(content_pdf='test.pdf', watermark_pdf='watermark.pdf', pdf_result='result.pdf')

效果：

---

参考：

• 官方文档：https://pypdf2.readthedocs.io/en/latest/
• https://www.cnblogs.com/yuminhu/p/15984340.html