Python处理Office文件模版代码（自己参考用）-PDF-python-pypdf2包

一、安装

pip install pypdf2

二、样例模版

# pip install pypdf2
def read_pdf1(path):
    from PyPDF2 import PdfReader
    reader = PdfReader(path)
    print(reader.metadata)
    for page in reader.pages:
        print(page.extract_text())

def read_pdf2(path):
    # pip install pdfplumber
    import pdfplumber
    with pdfplumber.open(path) as pdf:
        for page in pdf.pages:
            print(page.extract_text())

def merge_pdf(path1, path2):
    from PyPDF2 import PdfReader, PdfWriter
    writer = PdfWriter()
    for path in [path1, path2]:
        reader = PdfReader(path)
        for page in reader.pages:
            writer.add_page(page)
    with open('merge.pdf', 'wb') as target:
        writer.write(target)

def split_pdf(path):
    from PyPDF2 import PdfReader, PdfWriter
    reader = PdfReader(path)
    for i,page in enumerate(reader.pages):
        writer = PdfWriter()
        writer.add_page(page)
        with open(f'page_{i}.pdf', 'wb') as target:
            writer.write(target)

def encrypt_pdf(path):
    from PyPDF2 import PdfReader, PdfWriter
    reader = PdfReader(path)
    writer = PdfWriter()
    for page in reader.pages:
        writer.add_page(page)
    writer.encrypt('password')                                  # 加密PDF，密码为password
    with open('encrypted.pdf', 'wb') as target:
        writer.write(target)

def decrypt_pdf(path):
    from PyPDF2 import PdfReader
    reader = PdfReader(path)
    reader.decrypt('password')                                  # 读取PDF解密，密码为password
    for page in reader.pages:
        print(page.extract_text())

if __name__ == '__main__':
    read_pdf1('./file_path/test.pdf')
    read_pdf2('./file_path/test.pdf')
    merge_pdf('./file_path/test-part1.pdf', './file_path/test-part2.pdf')
    split_pdf('./file_path/test.pdf')
    encrypt_pdf('./file_path/test.pdf')
    decrypt_pdf('./file_path/encrypted.pdf')

三、特殊说明

使用的是PYPDF2 3.0.1的版本，3 以前的版本使用PdfFileReader,PdfFileWriter。

如需使用其他功能，参看官方文档，有好多方法不可用。