python实现带图形界面的图片和文字类型的pdf转word

可以使用Python的三方库PyQt和pdfminer来实现带图形界面的图片和文字类型的PDF转Word。具体步骤如下：

1. 安装PyQt和pdfminer库

pip install PyQt5
pip install pdfminer

2. 构建图形界面

可以使用Qt Designer来构建简单的图形界面，然后将其转换成Python代码。这里给出一个简单的示例代码：

from PyQt5.QtWidgets import QApplication, QWidget, QPushButton, QFileDialog, QLabel
from PyQt5.QtGui import QPixmap
import sys

class App(QWidget):
    def __init__(self):
        super().__init__()
        self.title = 'PDF转Word'
        self.left = 100
        self.top = 100
        self.width = 640
        self.height = 480
        self.initUI()

    def initUI(self):
        self.setWindowTitle(self.title)
        self.setGeometry(self.left, self.top, self.width, self.height)

        self.button = QPushButton('选择PDF文件', self)
        self.button.move(50, 50)
        self.button.clicked.connect(self.openFileDialog)

        self.label = QLabel(self)
        self.label.move(50, 100)
        self.label.resize(200, 200)

        self.show()

    def openFileDialog(self):
        fileName, _ = QFileDialog.getOpenFileName(self, "选择PDF文件", "", "PDF Files (*.pdf)")
        if fileName:
            self.convertPDFtoWord(fileName)

    def convertPDFtoWord(self, fileName):
        # TODO: 实现PDF转Word的功能
        pixmap = QPixmap('example.png')
        self.label.setPixmap(pixmap)

if __name__ == '__main__':
    app = QApplication(sys.argv)
    ex = App()
    sys.exit(app.exec_())

3. 实现PDF转Word的功能

使用pdfminer库来解析PDF文件，找到其中的图片和文字，并将其转换成Word中的图片和文字格式。具体代码如下：

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter, PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBoxHorizontal, LTTextBoxVertical, LTTextLine, LTImage, LTFigure
from pdfminer.pdfpage import PDFPage
from io import StringIO
import os
from PIL import Image
import docx

def convertPDFtoWord(pdfFileName):
    pdf = open(pdfFileName, 'rb')
    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    doc = docx.Document()

    # 循环遍历每一页
    for page in PDFPage.get_pages(pdf):
        interpreter.process_page(page)
        layout = device.get_result()

        # 循环遍历每一个layout对象
        for lt_obj in layout:
            if isinstance(lt_obj, LTTextBoxHorizontal):
                # 如果是水平文本框，将其转换为Word中的文字格式
                text = lt_obj.get_text().strip()
                if text:
                    doc.add_paragraph(text)

            elif isinstance(lt_obj, LTImage):
                # 如果是图片，将其转换为Word中的图片格式
                x, y, w, h = lt_obj.bbox
                img = Image.open(StringIO(lt_obj.stream.get_rawdata()))
                img.save('example.png')
                doc.add_picture('example.png')

    pdf.close()

    # 将Word文件保存为docx格式
    doc.save(pdfFileName.replace('.pdf', '.docx'))

将上述代码添加到App类中，完整代码如下：

from PyQt5.QtWidgets import QApplication, QWidget, QPushButton, QFileDialog, QLabel
from PyQt5.QtGui import QPixmap
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter, PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBoxHorizontal, LTTextBoxVertical, LTTextLine, LTImage, LTFigure
from pdfminer.pdfpage import PDFPage
from io import StringIO
import os
from PIL import Image
import docx
import sys

class App(QWidget):
    def __init__(self):
        super().__init__()
        self.title = 'PDF转Word'
        self.left = 100
        self.top = 100
        self.width = 640
        self.height = 480
        self.initUI()

    def initUI(self):
        self.setWindowTitle(self.title)
        self.setGeometry(self.left, self.top, self.width, self.height)

        self.button = QPushButton('选择PDF文件', self)
        self.button.move(50, 50)
        self.button.clicked.connect(self.openFileDialog)

        self.label = QLabel(self)
        self.label.move(50, 100)
        self.label.resize(200, 200)

        self.show()

    def openFileDialog(self):
        fileName, _ = QFileDialog.getOpenFileName(self, "选择PDF文件", "", "PDF Files (*.pdf)")
        if fileName:
            self.convertPDFtoWord(fileName)

    def convertPDFtoWord(self, pdfFileName):
        pdf = open(pdfFileName, 'rb')
        rsrcmgr = PDFResourceManager()
        laparams = LAParams()
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
        interpreter = PDFPageInterpreter(rsrcmgr, device)

        doc = docx.Document()

        # 循环遍历每一页
        for page in PDFPage.get_pages(pdf):
            interpreter.process_page(page)
            layout = device.get_result()

            # 循环遍历每一个layout对象
            for lt_obj in layout:
                if isinstance(lt_obj, LTTextBoxHorizontal):
                    # 如果是水平文本框，将其转换为Word中的文字格式
                    text = lt_obj.get_text().strip()
                    if text:
                        doc.add_paragraph(text)

                elif isinstance(lt_obj, LTImage):
                    # 如果是图片，将其转换为Word中的图片格式
                    x, y, w, h = lt_obj.bbox
                    img = Image.open(StringIO(lt_obj.stream.get_rawdata()))
                    img.save('example.png')
                    doc.add_picture('example.png')

        pdf.close()

        # 将Word文件保存为docx格式
        doc.save(pdfFileName.replace('.pdf', '.docx'))

if __name__ == '__main__':
    app = QApplication(sys.argv)
    ex = App()
    sys.exit(app.exec_())

注意：这里使用了docx库将转换后的内容保存为docx格式的Word文件。如果需要保存为其他格式的Word文件，可以使用Python-docx-template库。