forked from Dawn_Ocean/ZJUEVA-Reimburse
102 lines
3.6 KiB
Python
102 lines
3.6 KiB
Python
from docx import Document
|
||
from docx.shared import Inches
|
||
|
||
from copy import copy
|
||
|
||
from PIL import Image
|
||
|
||
import fitz
|
||
|
||
from docx2pdf import convert
|
||
|
||
import os
|
||
|
||
def convert_img(path = os.path.abspath('.')):
|
||
while True:
|
||
print("正在扫描并处理文件中...")
|
||
files = os.listdir('.')
|
||
for file in files:
|
||
if file.endswith('.pdf') and "output" not in file:
|
||
result = pdf2img(path, file)
|
||
if result: # 1 -> Error
|
||
print("PDF 转换失败！")
|
||
continue
|
||
elif file.endswith('.jpg') or file.endswith('.jpeg'):
|
||
img = Image.open(file)
|
||
img.save(file.split('.')[0] + ".png", "PNG")
|
||
print("JPG/JPEG 转换失败！")
|
||
print("转换完毕！")
|
||
break
|
||
|
||
def gen_filelist(path = os.path.abspath('.')):
|
||
types = "abc"
|
||
print("创建文件列表中...")
|
||
file_list = os.listdir('.')
|
||
file_list_cp = copy(file_list) # 创建浅拷贝
|
||
for filename in file_list_cp:
|
||
if ".png" not in filename:
|
||
file_list.remove(filename)
|
||
file_list.sort()
|
||
page_curr = 1
|
||
type_curr = 0
|
||
for filename in file_list:
|
||
if int(filename[0:2]) != page_curr or filename[2] != types[type_curr % 3]:
|
||
return []
|
||
else:
|
||
type_curr += 1
|
||
if type_curr % 3 == 0:
|
||
page_curr += 1
|
||
print("创建完毕！将要加入文档的文件如下：")
|
||
for file in file_list:
|
||
print(file)
|
||
return file_list
|
||
|
||
def gen_docx():
|
||
while True:
|
||
doc = Document()
|
||
file_list = gen_filelist()
|
||
input("按回车键确认...")
|
||
print("生成 .docx 文档中...")
|
||
if len(file_list) != 0:
|
||
pic_count = 0
|
||
for filename in file_list:
|
||
pic_count += 1
|
||
if pic_count % 3 == 1:
|
||
doc.add_picture(filename, height = Inches(2.5))
|
||
table = doc.add_table(rows = 1, cols = 2)
|
||
elif pic_count % 3 == 2:
|
||
cell1 = table.cell(0, 0)
|
||
cell1.paragraphs[0].add_run().add_picture(filename, height = Inches(5.0))
|
||
elif pic_count % 3 == 0:
|
||
cell2 = table.cell(0, 1)
|
||
cell2.paragraphs[0].add_run().add_picture(filename, height = Inches(5.0))
|
||
if pic_count != len(file_list):
|
||
doc.add_page_break()
|
||
else:
|
||
print("请检查文件命名是否正确！")
|
||
doc.save("output.docx")
|
||
print("生成完毕！")
|
||
break
|
||
|
||
def pdf2img(pdf_path, pdf_name, zoom_x = 3, zoom_y = 3):
|
||
doc = fitz.open(pdf_path + "\\" + pdf_name) # 打开文档
|
||
if len(doc) != 1:
|
||
print("PDF 文件只能包含一页！")
|
||
return 1
|
||
for page in doc: # 遍历页面
|
||
pix = page.get_pixmap(matrix=fitz.Matrix(zoom_x, zoom_y)) # 将页面渲染为图片
|
||
pix.save(pdf_name[:-4] + '.png') # 将图像存储为PNG格式
|
||
doc.close() # 关闭文档
|
||
|
||
if __name__ == "__main__":
|
||
print("在使用该脚本前，请将发票、付款记录、购买记录按以下规则命名：")
|
||
print("在文件名前添加[两位数字][类型]")
|
||
print("数字代表的是第几份材料，类型：发票a，付款记录b，购买记录c")
|
||
print("如：02b小公仔付款.png 代表第二份材料中的付款记录")
|
||
input("按回车键开始...")
|
||
convert_img()
|
||
gen_docx()
|
||
print("生成 .pdf 文件中...")
|
||
convert("output.docx", "output.pdf")
|
||
print("生成完毕！")
|
||
|