基于Python打造一个PDF全能处理工具

pip install PyPDF2 reportlab python-docx

from PyPDF2 import PdfReader, PdfWriter
 
def split_pdf(input_path, output_prefix, page_ranges):
    reader = PdfReader(input_path)
    writer = PdfWriter()
    
    for idx, page_num in enumerate(page_ranges, 1):
        writer.add_page(reader.pages[page_num])
        output_path = f"{output_prefix}_part{idx}.pdf"
        with open(output_path, "wb") as output_pdf:
            writer.write(output_pdf)
        writer = PdfWriter()  # 重置writer
 
# 使用示例：拆分第3-5页和第8页
split_pdf("report.pdf", "split_result", [2,3,4,7])

def split_by_size(input_path, max_size_mb=5):
    reader = PdfReader(input_path)
    max_size = max_size_mb * 1024 * 1024  # 转换为字节
    writer = PdfWriter()
    part_count = 1
    
    for page in reader.pages:
        writer.add_page(page)
        # 估算当前文件大小（实际需要写入临时文件检测）
        if get_pdf_size(writer) > max_size:
            save_part(writer, part_count)
            writer = PdfWriter()
            part_count += 1
    
    if writer.pages:
        save_part(writer, part_count)

def merge_pdfs(output_path, input_paths):
    writer = PdfWriter()
    
    for path in input_paths:
        reader = PdfReader(path)
        for page in reader.pages:
            writer.add_page(page)
    
    with open(output_path, "wb") as output_pdf:
        writer.write(output_pdf)

def encrypt_pdf(input_path, output_path, password):
    reader = PdfReader(input_path)
    writer = PdfWriter()
    
    for page in reader.pages:
        writer.add_page(page)
    
    writer.encrypt(user_password=password, use_128bit=True)
    
    with open(output_path, "wb") as output_pdf:
        writer.write(output_pdf)

# 在encrypt方法中添加权限参数
writer.encrypt(
    user_password=password,
    owner_password=owner_pwd,
    use_128bit=True,
    permissions={
        "print": False,
        "modify": False,
        "copy": False
    }
)

from reportlab.pdfbase.ttfonts import TTFont
from reportlab.pdfbase import pdfmetrics
from reportlab.lib.pagesizes import A4
from reportlab.pdfgen import canvas
 
def create_watermark(text, output_path):
    pdfmetrics.registerFont(TTFont("SimHei", "SimHei.ttf"))  # 注册中文字体
    c = canvas.Canvas(output_path, pagesize=A4)
    c.setFont("SimHei", 40)
    c.setFillAlpha(0.5)  # 设置透明度
    
    # 计算水印位置
    text_width = c.stringWidth(text, "SimHei", 40)
    x = (A4[0] - text_width) / 2
    y = A4[1] / 2
    
    c.rotate(45)  # 旋转45度
    c.drawString(x, y, text)
    c.save()

def add_image_watermark(input_path, watermark_path, output_path):
    reader = PdfReader(input_path)
    writer = PdfWriter()
    watermark = PdfReader(watermark_path).pages[0]
    
    for page in reader.pages:
        # 合并水印层和内容层
        page.merge_page(watermark)
        writer.add_page(page)
    
    with open(output_path, "wb") as output_pdf:
        writer.write(output_pdf)

def process_contract(input_path):
    # 1. 拆分签名页
    split_pdf(input_path, "temp_split", [len(reader.pages)-1])
    
    # 2. 添加动态水印
    create_watermark("文件", "watermark.pdf")
    add_image_watermark("temp_split_part1.pdf", "watermark.pdf", "watermarked.pdf")
    
    # 3. 加密保护
    encrypt_pdf("watermarked.pdf", "final_contract.pdf", "Secure@123")
    
    # 4. 邮件附件准备
    convert_to_zip(["final_contract.pdf"], "secure_package.zip")