import sys
import os
from PyQt5.QtWidgets import QApplication, QWidget, QVBoxLayout, QHBoxLayout, QGridLayout, QPushButton, QLabel, QLineEdit, QFileDialog, QListWidget, QTableWidget, QTableWidgetItem, QHeaderView, QAbstractItemView, QGroupBox, QMessageBox, QSpacerItem, QSizePolicy
from PyQt5.QtCore import Qt
from PyQt5.QtGui import QDragEnterEvent, QDropEvent
from docx import Document
from PIL import Image
from io import BytesIO
from openpyxl import load_workbook
from pptx import Presentation
import win32com.client  # 用于處理 .doc 和 .ppt 文件（Windows特定）


class OptimizedUI(QWidget):
    def __init__(self):
        super().__init__()

        self.setWindowTitle("Office文檔圖片提取器")
        self.setGeometry(100, 100, 800, 600)

        self.init_ui()

    def init_ui(self):
        layout = QVBoxLayout(self)

        # 文件選擇框
        file_frame = QGroupBox("選擇的文件")
        file_layout = QVBoxLayout()
        self.file_list = QListWidget()
        self.file_list.setSelectionMode(QAbstractItemView.MultiSelection)
        file_layout.addWidget(self.file_list)

        # ScrollBar
        self.file_list.setVerticalScrollBarPolicy(Qt.ScrollBarAlwaysOn)
        file_frame.setLayout(file_layout)

        # 按鈕
        button_layout = QHBoxLayout()
        add_button = QPushButton("添加文件")
        add_button.clicked.connect(self.browse_files)
        remove_button = QPushButton("移除選中")
        remove_button.clicked.connect(self.remove_files)

        button_layout.addWidget(add_button)
        button_layout.addWidget(remove_button)

        # 輸出目錄
        output_frame = QGroupBox("輸出目錄")
        output_layout = QHBoxLayout()
        self.output_folder = QLineEdit()
        browse_button = QPushButton("瀏覽")
        browse_button.clicked.connect(self.browse_output_folder)
        output_layout.addWidget(self.output_folder)
        output_layout.addWidget(browse_button)
        output_frame.setLayout(output_layout)

        # 提取日志框
        log_frame = QGroupBox("提取日志")
        log_layout = QVBoxLayout()
        self.log_table = QTableWidget(0, 3)
        self.log_table.setHorizontalHeaderLabels(["文件名", "圖片名稱", "保存路徑"])
        self.log_table.horizontalHeader().setSectionResizeMode(0, QHeaderView.Stretch)
        self.log_table.horizontalHeader().setSectionResizeMode(1, QHeaderView.Stretch)
        self.log_table.horizontalHeader().setSectionResizeMode(2, QHeaderView.Stretch)
        log_layout.addWidget(self.log_table)
        log_frame.setLayout(log_layout)

        # 提取按鈕
        extract_button = QPushButton("提取圖片")
        extract_button.clicked.connect(self.extract_and_log)

        # 布局
        layout.addWidget(file_frame)
        layout.addLayout(button_layout)
        layout.addWidget(output_frame)
        layout.addWidget(log_frame)
        layout.addWidget(extract_button)

        self.setLayout(layout)

        # 啟用拖放文件功能
        self.setAcceptDrops(True)

    def browse_files(self):
        files, _ = QFileDialog.getOpenFileNames(self, "選擇文件", "", "Office Files (*.doc *.docx *.xls *.xlsx *.ppt *.pptx)")
        if files:
            self.file_list.addItems(files)

    def remove_files(self):
        selected_items = self.file_list.selectedItems()
        for item in selected_items:
            self.file_list.takeItem(self.file_list.row(item))

    def browse_output_folder(self):
        folder = QFileDialog.getExistingDirectory(self, "選擇輸出目錄")
        if folder:
            self.output_folder.setText(folder)

    def extract_and_log(self):
        files = [self.file_list.item(i).text() for i in range(self.file_list.count())]
        output_dir = self.output_folder.text()

        if not files:
            QMessageBox.warning(self, "警告", "請至少添加一個(gè)文件。")
            return

        if not output_dir:
            QMessageBox.warning(self, "警告", "請選擇輸出目錄。")
            return

        log_data = []  # 用于保存日志信息

        for file_path in files:
            try:
                for image_name, image_path in self.extract_images(file_path, output_dir):
                    if image_name:
                        log_data.append((file_path, image_name, image_path))
                    else:
                        log_data.append((file_path, "N/A", image_path))
            except ValueError as e:
                log_data.append((file_path, "N/A", f"錯誤：{str(e)}"))

        self.update_log_table(log_data)

    def update_log_table(self, log_data):
        self.log_table.setRowCount(0)  # 清空表格
        for row, log_entry in enumerate(log_data):
            self.log_table.insertRow(row)
            for col, value in enumerate(log_entry):
                self.log_table.setItem(row, col, QTableWidgetItem(value))

    def extract_images(self, file_path, output_dir):
        """根據(jù)文件類型調(diào)用不同的提取圖片函數(shù)。"""
        if file_path.endswith(".docx"):
            return self.extract_images_from_docx(file_path, output_dir)
        elif file_path.endswith(".xlsx"):
            return self.extract_images_from_xlsx(file_path, output_dir)
        elif file_path.endswith(".pptx"):
            return self.extract_images_from_pptx(file_path, output_dir)
        elif file_path.endswith(".doc"):
            return self.extract_images_from_doc(file_path, output_dir)
        elif file_path.endswith(".xls"):
            return self.extract_images_from_xls(file_path, output_dir)
        elif file_path.endswith(".ppt"):
            return self.extract_images_from_ppt(file_path, output_dir)
        else:
            raise ValueError("不支持的文件類型")

    def extract_images_from_docx(self, file_path, output_dir):
        """從 .docx 文件中提取圖片并保存到輸出目錄。"""
        try:
            doc = Document(file_path)
            image_count = 0
            for rel in doc.part.rels.values():
                if "image" in rel.target_ref:
                    image_count += 1
                    image_data = rel.target_part.blob
                    image = Image.open(BytesIO(image_data))

                    ext = image.format.lower()
                    image_name = f"{os.path.splitext(os.path.basename(file_path))[0]}_image{image_count}.{ext}"
                    image_path = os.path.join(output_dir, image_name)
                    image.save(image_path)

                    yield image_name, image_path

            if image_count == 0:
                yield None, "未找到圖片。"

        except Exception as e:
            yield None, f"錯誤：{str(e)}"

    def extract_images_from_xlsx(self, file_path, output_dir):
        """從 .xlsx 文件中提取圖片并保存到輸出目錄。"""
        try:
            workbook = load_workbook(file_path)
            image_count = 0
            for sheet in workbook.sheetnames:
                sheet_obj = workbook[sheet]
                for image in sheet_obj._images:
                    image_count += 1
                    image_data = image.ref
                    img = Image.open(BytesIO(image_data))

                    ext = img.format.lower()
                    image_name = f"{os.path.splitext(os.path.basename(file_path))[0]}_image{image_count}.{ext}"
                    image_path = os.path.join(output_dir, image_name)
                    img.save(image_path)

                    yield image_name, image_path

            if image_count == 0:
                yield None, "未找到圖片。"

        except Exception as e:
            yield None, f"錯誤：{str(e)}"

    def extract_images_from_pptx(self, file_path, output_dir):
        """從 .pptx 文件中提取圖片并保存到輸出目錄。"""
        try:
            prs = Presentation(file_path)
            image_count = 0

            for slide in prs.slides:
                for shape in slide.shapes:
                    if shape.shape_type == 13:  # 圖片類型
                        image_stream = shape.image.blob  # 獲取圖像流

                        ext = shape.image.ext.lower()  # 使用圖片的擴(kuò)展名（如jpg, png）
                        image_name = f"{os.path.splitext(os.path.basename(file_path))[0]}_image{image_count + 1}.{ext}"
                        image_path = os.path.join(output_dir, image_name)

                        image = Image.open(BytesIO(image_stream))
                        image.save(image_path)

                        image_count += 1  # 圖片計(jì)數(shù)
                        yield image_name, image_path

            if image_count == 0:
                yield None, "未找到圖片。"

        except Exception as e:
            yield None, f"錯誤：{str(e)}"

    def extract_images_from_doc(self, file_path, output_dir):
        """從 .doc 文件中提取圖片（Windows特定，使用win32com）。"""
        try:
            word = win32com.client.Dispatch("Word.Application")
            doc = word.Documents.Open(file_path)
            image_count = 0

            for shape in doc.Shapes:
                if shape.Type == 13:  # 圖片類型
                    image_count += 1
                    image_stream = shape.PictureFormat.Picture
                    image = Image.open(BytesIO(image_stream))

                    ext = image.format.lower()
                    image_name = f"{os.path.splitext(os.path.basename(file_path))[0]}_image{image_count}.{ext}"
                    image_path = os.path.join(output_dir, image_name)
                    image.save(image_path)

                    yield image_name, image_path

            if image_count == 0:
                yield None, "未找到圖片。"

        except Exception as e:
            yield None, f"錯誤：{str(e)}"
        finally:
            word.Quit()

    def extract_images_from_xls(self, file_path, output_dir):
        """從 .xls 文件中提取圖片（Windows特定，使用xlrd或openpyxl）。"""
        try:
            import xlrd
            workbook = xlrd.open_workbook(file_path)
            image_count = 0
            yield None, "暫不支持的圖片提取。"

        except Exception as e:
            yield None, f"錯誤：{str(e)}"

    def extract_images_from_ppt(self, file_path, output_dir):
        """從 .ppt 文件中提取圖片（Windows特定，使用win32com）。"""
        try:
            ppt = win32com.client.Dispatch("PowerPoint.Application")
            presentation = ppt.Presentations.Open(file_path)
            image_count = 0

            for slide in presentation.Slides:
                for shape in slide.Shapes:
                    if shape.Type == 13:  # 圖片類型
                        image_count += 1
                        image_stream = shape.PictureFormat.Picture
                        image = Image.open(BytesIO(image_stream))

                        ext = image.format.lower()
                        image_name = f"{os.path.splitext(os.path.basename(file_path))[0]}_image{image_count}.{ext}"
                        image_path = os.path.join(output_dir, image_name)
                        image.save(image_path)

                        yield image_name, image_path

            if image_count == 0:
                yield None, "未找到圖片。"

        except Exception as e:
            yield None, f"錯誤：{str(e)}"
        finally:
            ppt.Quit()

    def dragEnterEvent(self, event):
        """處理拖拽進(jìn)入事件"""
        if event.mimeData().hasUrls():
            event.acceptProposedAction()

    def dropEvent(self, event):
        """處理拖拽釋放事件"""
        for url in event.mimeData().urls():
            file_path = url.toLocalFile()
            if os.path.isfile(file_path):
                self.file_list.addItem(file_path)

# 運(yùn)行應(yīng)用
if __name__ == "__main__":
    app = QApplication(sys.argv)
    window = OptimizedUI()
    window.show()
    sys.exit(app.exec_())