From 35993e2270bccc39d49bb07507206e3b66f30644 Mon Sep 17 00:00:00 2001
From: Dawn_Ocean <1785590531@qq.com>
Date: Wed, 18 Oct 2023 16:39:47 +0800
Subject: [PATCH] first commit

---
 README.md | Bin 0 -> 624 bytes
 main.py   |  84 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+)
 create mode 100644 README.md
 create mode 100644 main.py

diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..647063ac9d2f7227f72e8d3deae300cc26c6d274
GIT binary patch
literal 624
zcmY#pP+*8+@L~vMaAgQ%a0K#{dc`7_CNWHvYSc+z8RVVB%fQ6|!pcCXz%W1PZv#w(
zEhaeLH>f@Jo1bN*uHRF?1cr;j8I`&WH~j3fH*|-_>oVx}7Wjc!2@F<#41P!ITFN;6
z6ypDdxfj``YJ?{+=rN=)<TE5QR4^nkfXrzr;|XE#E1i)voyh=Zi<CcG3`k`GP;DAe
z9ist=mj&dfqwrF}e2^)x8dn76^d}`-0bK;rmj{>W4ZM_`8i+6(;-`9ljnbW|S94%C
z8Ul4GFu-iBgu0E-uQi?}lC1>hdXP)C{2;zZm}msn3kws6B+hh@dd}qZLbjkIb+sY9
zAyWSZ3{?Dl{R>jVqXi8F4619o!$EXeV5EO*;7*_z!ZZb-I}{ks`57=6GBCuSj^s?P
zn$aHzGNnK6doa&`o)A!&f@}lve*i;|=Re3issEsuNMzvo4~vT=AR87N$qW!1Af|Ww
zH$_VQH()SgNMgtdyy6Ga0Sh$+23-a_pbK=Wd%&>=GY#Y?ge#4~e!kG}(*X%@Scvib
Wx6H^(zL0EHc^fEqHYLWN$p8R7%CR8;

literal 0
HcmV?d00001

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..7f17772
--- /dev/null
+++ b/main.py
@@ -0,0 +1,84 @@
+from docx import Document
+from docx.shared import Inches, Pt
+
+from PIL import Image
+
+import fitz
+import os
+
+types = "abc"
+
+def convert(path = os.path.abspath('.')):
+    while True:
+        for _, _, files in os.walk(path):
+            for filename in files:
+                if ".pdf" in filename:
+                    result = pdf2img(path, filename)
+                    if result:                  # 1 -> Error
+                        continue
+                if ".jpg" in filename or ".jpeg" in filename:
+                    img = Image.open(filename)
+                    img.save(filename.split('.')[0] + ".png", "PNG")
+        break
+
+def gen_filelist(pages, path = os.path.abspath('.')):
+    types = "abc"
+    file_list = []
+    for _, _, files in os.walk(path):
+            for filename in files:
+                if ".png" in filename:
+                    file_list.append(filename)
+    file_list.sort()
+    page_curr = 1
+    type_curr = 0
+    for filename in file_list:
+        if int(filename[0:1]) != page_curr or filename[2] != types[type_curr % 3]:
+            return []
+        else:
+            type_curr += 1
+            if type_curr % 3 == 0:
+                page_curr += 1
+    return file_list
+
+def gen_docx():
+    while True:
+        doc = Document()
+        print()
+        pages = input("输入你要生成的材料页数（对应的 3 份图片为 1 页）：")
+        if pages.isdigit():
+            pages = int(pages)
+        else:
+            print("请输入一个数字！")
+            continue
+        file_list = gen_filelist(pages)
+        print(file_list)
+        if len(file_list) != 0:
+            pic_count = 0
+            for filename in file_list:
+                doc.add_picture(filename, height = Inches(2.5))
+                pic_count += 1
+                if pic_count % 3 == 0 and 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")
+        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")
+    convert()
+    gen_docx()
+    
\ No newline at end of file