pdfmake
/
PDFmake.py

# -*- mode: python3.8.5 ; coding: utf-8 -*-
# Software: Windows 11 ; PyCharm 2022.1 ; python:3.8.5
# date：2022.10.19
# update time: 2022.11.16
# name：PDF工具合集2.6
# make：黄朝勋
# 安装依赖库
# pip install PyMuPDf==1.19.0 -i https://mirrors.aliyun.com/pypi/simple
# pip install PyWin32 -i https://mirrors.aliyun.com/pypi/simple
# pip install pyinstaller -i https://mirrors.aliyun.com/pypi/simple
# pip install pdf2docx -i https://mirrors.aliyun.com/pypi/simple
# pip install ttkbootstrap -i https://mirrors.aliyun.com/pypi/simple
# pip install PyPDF2 -i https://mirrors.aliyun.com/pypi/simple
# pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple
# pip install paddlepaddle==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple
# pip install "paddleocr>=2.6.0.3" -i https://pypi.tuna.tsinghua.edu.cn/simple
# 生成可执行文件命令：pyinstaller -D -w -i favicon.ico PDFmake.py
# pyinstaller PDFmake.spec

import base64
import os
import tkinter
from tkinter import filedialog
from tkinter import messagebox
from tkinter import ttk

import cv2
import fitz
from PIL import Image
from PIL import ImageEnhance
from PyPDF2 import PdfReader, PdfWriter
from paddleocr import PPStructure
from paddleocr import PaddleOCR
from recovery_to_doc import sorted_layout_boxes, convert_info_docx
from pdf2docx import Converter
from ttkbootstrap import Style
from win32com.client import constants, gencache

from icon import img  # 引用 icon.py 的图片

# 读取base64转码后的数据，并设置压缩图标
picture = open("picture.ico", "wb+")
picture.write(base64.b64decode(img))
picture.close()

style = Style(theme='minty')


class desk:
    def __init__(self):
        self.init_window = style.master
        self.init_window.title('PDF工具合集2.6(黄朝勋)')
        self.init_window.geometry('450x350+450+200')
        self.init_window["background"] = "#fafbf0"
        self.init_window.attributes("-topmost", True)
        self.init_window.iconbitmap('picture.ico')
        self.init_window.attributes("-toolwindow", False)

    def Button(self, row, column, text, func):
        button = ttk.Button(self.init_window, text=text, command=func, style='success.Outline.TButton')
        button.grid(row=row, column=column, padx=53, pady=18)

    def run(self):
        self.Button(1, 1, 'PDF转图片工具', lambda: self.conver('PdfToImg'))
        self.Button(1, 2, 'Word转PDF工具', lambda: self.conver('WordToPdf'))
        self.Button(2, 1, 'PDF转Word工具', lambda: self.conver('PdfToWord'))
        self.Button(2, 2, 'PDF文件压缩工具', lambda: self.conver('PdfToLow'))
        self.Button(3, 1, 'PDF文件拆分工具', lambda: self.conver('PdfToMore'))
        self.Button(3, 2, '照片磨皮修复工具', lambda: self.conver('PhotoToImg'))
        self.Button(4, 1, '图片文字转word', lambda: self.conver('PhotoToWord'))
        self.Button(4, 2, 'PDF转可编辑word', lambda: self.conver('PdfToRWord'))
        self.lab = tkinter.Label()
        self.lab.place(rely=1.0, relx=1.0, x=0, y=0)
        self.init_window.mainloop()

    def conver(self, type):
        selectFile = filedialog.askopenfilename()
        obj = Change(selectFile)
        res = getattr(obj, type)

        self.message(res())

    def message(self, text):
        messagebox.showinfo('结果', text)


class Change:
    def __init__(self, filename):
        self.filename = filename

    # pdf转图片模块
    def PdfToImg(self):
        try:
            self.pdf = fitz.open(self.filename)
            self.pageCount = self.pdf.pageCount
            for pg in range(self.pageCount):
                page = self.pdf[pg]
                trans = fitz.Matrix(2.0, 2.0).prerotate(0)
                pm = page.get_pixmap(matrix=trans, alpha=False)
                pm.save(self.filename + '%s.png' % pg)
            return '转换图片完成'
        except Exception as e:
            return e

    # word转pdf模块
    def WordToPdf(self):
        pdfname = self.filename + '.pdf'
        word = gencache.EnsureDispatch('Word.Application')
        doc = word.Documents.Open(self.filename, ReadOnly=1)
        doc.ExportAsFixedFormat(pdfname,
                                constants.wdExportFormatPDF,
                                Item=constants.wdExportDocumentWithMarkup,
                                CreateBookmarks=constants.wdExportCreateHeadingBookmarks)
        word.Quit(constants.wdDoNotSaveChanges)
        return '转换DPF完成'

    # PDF转word模块
    def PdfToWord(self):
        Wordname = (self.filename + '.docx')
        cv = Converter(self.filename)
        cv.convert(Wordname, start=0, end=None)
        cv.close()
        return '转换word完成'

    # PDF文件压缩模块
    def PdfToLow(self):
        reader = PdfReader(self.filename)
        writer = PdfWriter()
        for page in reader.pages:
            page.compress_content_streams()
            writer.add_page(page)
        with open(self.filename + '.pdf', 'wb') as f:
            writer.write(f)
        return 'PDF文件压缩完成'

    # PDF拆分模块
    def PdfToMore(self):
        reader = PdfReader(self.filename)
        writer = self.filename
        for i in range(0, reader.getNumPages()):
            pdf_writer = PdfWriter()
            pdf_writer.addPage(reader.getPage(i))
            with open(writer + '-{}.pdf'.format(str(i)), 'wb') as fh:
                pdf_writer.write(fh)
        return '将PDF文件中的每页生成单独一个PDF文件完成'

    # 照片磨皮修复模块
    def PhotoToImg(self):
        path = self.filename
        img = cv2.imread(path)
        work_img = cv2.bilateralFilter(img, 31, 100, 150)
        # 图像融合
        result_img = cv2.addWeighted(img, 0.3, work_img, 0.7, 0)
        cv2.imwrite("img_1.jpg", result_img)
        image = Image.open("img_1.jpg")
        # 锐度调节
        enh_img = ImageEnhance.Sharpness(image)
        image_sharped = enh_img.enhance(1.5)
        # 对比度调节
        con_img = ImageEnhance.Contrast(image_sharped)
        image_con = con_img.enhance(1.15)
        image_con.save(self.filename + '.jpg')
        return '照片修复完成'

    # 图片内容转word
    def PhotoToWord(self):
        table_engine = PPStructure(layout=False, recovery=True)
        img_path = self.filename
        save_folder = img_path + '\Desktop'
        img = cv2.imread(img_path)
        result = table_engine(img)
        h, w, _ = img.shape
        res = sorted_layout_boxes(result, w)
        convert_info_docx(img, res, save_folder, os.path.dirname(img_path + '\Desktop').split('.')[0])
        return '图片内容转word完成'

    # PDF转可编辑word
    def PdfToRWord(self):
        log = open(self.filename + '.doc', mode="a", encoding="utf-8")
        ocr = PaddleOCR(use_angle_cls=True, lang="ch")
        img_path = self.filename
        result = ocr.ocr(img_path, cls=True)
        Result = result[0]
        txts = [line[1][0] for line in Result]
        for i in range(len(txts)):
            res = txts[i]
            for line in res:
                print(line, file=log, end='')
        log.close()
        return '转换成可编辑word完成'


if __name__ == '__main__':
    obj = desk()
    obj.run()