161 lines
5.3 KiB
Python
161 lines
5.3 KiB
Python
import os
|
||
from reportlab.lib.pagesizes import A3
|
||
from reportlab.platypus import SimpleDocTemplate, Image
|
||
from PyPDF2 import PdfReader, PdfWriter
|
||
from PIL import Image as PILImage
|
||
import io
|
||
|
||
|
||
def compress_image(image_path, target_size_kb=300):
|
||
"""快速压缩图片到目标大小（单位：KB）"""
|
||
with PILImage.open(image_path) as img:
|
||
# 调整图片尺寸，保持宽高比
|
||
# 如果图片有透明度，转换为RGB
|
||
if img.mode in ('RGBA', 'P'):
|
||
img = img.convert('RGB')
|
||
|
||
# 获取原始文件大小（KB）
|
||
original_size_kb = os.path.getsize(image_path) / 1024
|
||
|
||
# 如果原始大小已小于目标大小，直接返回原始数据
|
||
if original_size_kb <= target_size_kb:
|
||
output = io.BytesIO()
|
||
img.save(output, format='JPEG', quality=85)
|
||
return output.getvalue()
|
||
|
||
# 根据原始大小和目标大小预估初始质量
|
||
# 假设质量与文件大小近似线性关系，设置一个初始值
|
||
estimated_quality = min(95, max(10, int(85 * (target_size_kb / original_size_kb))))
|
||
|
||
output = io.BytesIO()
|
||
img.save(output, format='JPEG', quality=estimated_quality)
|
||
size_kb = len(output.getvalue()) / 1024
|
||
|
||
# 如果预估结果偏差较大，使用二分法调整（最多尝试3次）
|
||
low, high = 10, 95
|
||
for _ in range(3):
|
||
if size_kb <= target_size_kb * 0.9 or size_kb >= target_size_kb * 1.1: # 允许±10%偏差
|
||
quality = (low + high) // 2
|
||
output.seek(0)
|
||
output.truncate(0)
|
||
img.save(output, format='JPEG', quality=quality)
|
||
size_kb = len(output.getvalue()) / 1024
|
||
|
||
if size_kb > target_size_kb:
|
||
high = quality - 1
|
||
else:
|
||
low = quality + 1
|
||
else:
|
||
break
|
||
|
||
return output.getvalue()
|
||
|
||
|
||
def create_pdf_from_images(directory, output_pdf):
|
||
"""从目录中的图片创建PDF"""
|
||
image_extensions = {'.jpg', '.jpeg', '.png', '.gif', '.bmp', '.tiff', '.webp'}
|
||
image_files = []
|
||
|
||
# 遍历目录，筛选图片文件
|
||
for root, dirs, files in os.walk(directory):
|
||
for file in files:
|
||
_, ext = os.path.splitext(file)
|
||
if ext.lower() in image_extensions:
|
||
image_files.append(os.path.join(root, file))
|
||
|
||
# 如果没有找到图片，返回
|
||
if not image_files:
|
||
print(f"未在 {directory} 中找到图片文件。")
|
||
return
|
||
|
||
# 按文件名排序
|
||
image_files.sort()
|
||
|
||
# 设置PDF文档，使用A3页面大小
|
||
doc = SimpleDocTemplate(output_pdf, pagesize=A3)
|
||
|
||
# 创建图片列表
|
||
image_list = []
|
||
for image_file in image_files:
|
||
|
||
# 压缩图片到~300KB
|
||
compressed_image_data = compress_image(image_file)
|
||
|
||
# 从压缩字节数据中读取图片以获取新尺寸
|
||
with PILImage.open(io.BytesIO(compressed_image_data)) as compressed_img:
|
||
img_width, img_height = compressed_img.size
|
||
|
||
# 设置目标宽度（适应A3页面宽度，最大800点）
|
||
target_width = 800
|
||
|
||
# 计算新高度，保持宽高比
|
||
target_height = int(img_height * (target_width / img_width))
|
||
|
||
# 限制最大高度，避免超出页面
|
||
max_page_height = 1091 - 100 # A3页面高度1191点，留出空间
|
||
if target_height > max_page_height:
|
||
target_height = max_page_height
|
||
target_width = int(target_height * (img_width / img_height))
|
||
|
||
# 创建图片对象并添加到列表
|
||
img = Image(io.BytesIO(compressed_image_data), width=target_width, height=target_height)
|
||
image_list.append(img)
|
||
|
||
# 生成PDF
|
||
doc.build(image_list)
|
||
print(f"PDF {output_pdf} 创建成功。")
|
||
|
||
|
||
def encrypt_pdf(input_pdf, output_pdf, password):
|
||
"""加密PDF文件"""
|
||
writer = PdfWriter()
|
||
with open(input_pdf, "rb") as file:
|
||
reader = PdfReader(file)
|
||
for page in reader.pages:
|
||
writer.add_page(page)
|
||
|
||
with open(output_pdf, "wb") as file:
|
||
writer.encrypt(password)
|
||
writer.write(file)
|
||
print(f"PDF {output_pdf} 加密成功。")
|
||
|
||
|
||
def generate_pdf_from_images(directory):
|
||
"""从数字命名的文件夹生成PDF"""
|
||
# 获取目录下所有数字命名的文件夹
|
||
folder_names = [folder for folder in os.listdir(directory)
|
||
if os.path.isdir(os.path.join(directory, folder)) and folder.isdigit()]
|
||
|
||
# 如果没有数字命名的文件夹，返回
|
||
if not folder_names:
|
||
print("未找到数字命名的文件夹。")
|
||
return
|
||
|
||
# 循环处理每个文件夹
|
||
for folder_name in folder_names:
|
||
folder_path = os.path.join(directory, folder_name)
|
||
|
||
# 设置PDF输出路径
|
||
output_pdf = f"./PDF/{folder_name}.pdf"
|
||
|
||
# 如果PDF已存在，跳过
|
||
if os.path.exists(output_pdf):
|
||
print(f"PDF {output_pdf} 已存在，跳过...")
|
||
continue
|
||
|
||
# 创建PDF目录
|
||
os.makedirs("../../xiuren/PDF", exist_ok=True)
|
||
|
||
# 创建PDF
|
||
create_pdf_from_images(folder_path, output_pdf)
|
||
|
||
# 加密PDF
|
||
encrypt_pdf(output_pdf, output_pdf, "4000") # 密码为4000
|
||
|
||
# 返回PDF绝对路径
|
||
return os.path.abspath(output_pdf)
|
||
|
||
|
||
# 示例用法
|
||
if __name__ == "__main__":
|
||
generate_pdf_from_images("./") |