pdfGenerator/main/create_pdf.py

152 lines
5.5 KiB
Python
Raw Normal View History

2024-06-30 10:57:44 +08:00
import shutil
import sys
import zipfile
import os
from PIL import Image
from fpdf import FPDF
def read_config(config_path):
# 默认配置
default_config = {
'imagesPerRow': 3,
'rowsPerPage': 2,
'imageWidth': 60,
'imageHeight': 130,
'xStart': 10,
'yStart': 20
}
# 如果配置文件不存在,返回默认配置
if not os.path.exists(config_path):
return default_config
# 读取配置文件
config = default_config.copy()
with open(config_path, 'r') as file:
for line in file:
name, value = line.split('=')
config[name.strip()] = int(value.strip())
return config
def collect_images(src_dir, tmp_dir):
os.makedirs(tmp_dir, exist_ok=True)
# 支持更多图像格式
supported_formats = ('.jpg', '.jpeg', '.png', '.tiff', '.bmp', '.gif')
for root, _, files in os.walk(src_dir):
for file_name in files:
if file_name.endswith(supported_formats):
src_file_path = os.path.join(root, file_name)
dst_file_path = os.path.join(tmp_dir, file_name)
shutil.copy(src_file_path, dst_file_path)
elif file_name.endswith('.zip'):
zip_file_path = os.path.join(root, file_name)
extract_path = os.path.join(tmp_dir, os.path.splitext(file_name)[0])
os.makedirs(extract_path, exist_ok=True)
with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
zip_ref.extractall(extract_path)
for extracted_file in os.listdir(extract_path):
extracted_file_path = os.path.join(extract_path, extracted_file)
if extracted_file.endswith(supported_formats):
dst_file_path = os.path.join(tmp_dir, extracted_file)
shutil.move(extracted_file_path, dst_file_path)
shutil.rmtree(extract_path, ignore_errors=True)
def process_images_to_pdf(tmp_dir, output_pdf_path, config):
try:
# 支持更多图像格式
supported_formats = ('.jpg', '.jpeg', '.png', '.tiff', '.bmp', '.gif')
# 收集所有支持格式的图像文件
extracted_files = [f for f in os.listdir(tmp_dir) if f.endswith(supported_formats)]
# Sort the files in descending order based on the timestamp in the filename
sorted_files_descending = sorted(extracted_files, key=lambda x: int(x.split('.')[0]), reverse=True)
# Create a PDF document with images arranged in rows, three images per row, six images per page,
# proportionally scaled
pdf = FPDF()
# 读取布局参数
images_per_row = config['imagesPerRow']
rows_per_page = config['rowsPerPage']
max_images_per_page = images_per_row * rows_per_page
image_width = config['imageWidth'] # 每张图片的宽度比例
image_height = config['imageHeight'] # 每张图片的最大高度以适应两行
# 在 PDF 中按比例缩放添加图片
x_start = config['xStart']
y_start = config['yStart']
current_x = x_start
current_y = y_start
# Function to convert images to supported format
def convert_image_to_jpeg(image_path):
img = Image.open(image_path)
if img.mode in ("RGBA", "P"):
img = img.convert("RGB")
jpeg_path = image_path + ".jpg"
img.save(jpeg_path, "JPEG")
return jpeg_path
# Function to get scaled dimensions
def get_scaled_dimensions(image_path, max_width, max_height):
img = Image.open(image_path)
width, height = img.size
ratio = min(max_width / width, max_height / height)
return width * ratio, height * ratio
for idx, image_file in enumerate(sorted_files_descending):
if idx % max_images_per_page == 0:
pdf.add_page()
current_x = x_start
current_y = y_start
image_path = os.path.join(tmp_dir, image_file)
jpeg_path = convert_image_to_jpeg(image_path)
width, height = get_scaled_dimensions(jpeg_path, image_width, image_height)
pdf.image(jpeg_path, x=current_x, y=current_y, w=width, h=height)
# Update x position for next image
current_x += image_width + 5 # Add some margin between images
# If we have placed three images in the current row, move to the next row
if (idx + 1) % images_per_row == 0:
current_x = x_start
current_y += image_height + 10 # Add some margin between rows
# Save the PDF to a file
pdf.output(output_pdf_path)
print(f'PDF saved to: {output_pdf_path}')
finally:
# Clean up tmp directory if needed
shutil.rmtree(tmp_dir, ignore_errors=True)
def main():
current_dir = os.getcwd()
config_path = os.path.join(current_dir, 'config.txt')
tmp_dir = os.path.join(current_dir, 'tmp')
output_dir_path = os.path.join(current_dir, 'out')
origin_dir_path = os.path.join(current_dir, 'orgin')
# 读取配置文件
config = read_config(config_path)
# Ensure output directory exists
os.makedirs(output_dir_path, exist_ok=True)
# Collect images from 'orgin' directory
collect_images(origin_dir_path, tmp_dir)
# Generate PDF from collected images
output_pdf_path = os.path.join(output_dir_path, 'output.pdf')
process_images_to_pdf(tmp_dir, output_pdf_path, config)
if __name__ == "__main__":
main()