基于python实现PDF分页和管理工具开发详解

class PDFSplitterFrame(wx.Frame):
    def __init__(self):
        super().__init__(None, title="PDF分离和管理工具", size=(1200, 800))

# 首先初始化所有必要的变量
self.pdf_path = ""
self.target_folder = ""
self.folder_name = ""
self.created_folder_path = ""
self.split_files = []
self.xml_file = "pdf_aliases.xml"
self.zoom_factor = 1.0
self.current_pdf_path = None

# 主分割器 - 垂直分割
main_splitter = wx.SplitterWindow(panel, style=wx.SP_LIVE_UPDATE)

# 创建水平分割器用于分离文件列表和预览
h_splitter = wx.SplitterWindow(upper_panel, style=wx.SP_LIVE_UPDATE)

def on_split_pdf(self, event):
    doc = fitz.open(self.pdf_path)
    total_pages = len(doc)
    
    for page_num in range(total_pages):
        # 创建新的PDF文档，只包含当前页
        new_doc = fitz.open()
        new_doc.insert_pdf(doc, from_page=page_num, to_page=page_num)
        
        # 保存单页PDF
        output_filename = f"page_{page_num + 1:03d}.pdf"
        output_path = os.path.join(self.created_folder_path, output_filename)
        new_doc.save(output_path)
        new_doc.close()

def preview_pdf(self, pdf_path):
    doc = fitz.open(pdf_path)
    page = doc[0]  # 获取第一页
    
    # 使用当前缩放因子渲染页面
    base_matrix = fitz.Matrix(1.5, 1.5)  # 基础缩放因子
    zoom_matrix = fitz.Matrix(self.zoom_factor, self.zoom_factor)
    final_matrix = base_matrix * zoom_matrix
    
    pix = page.get_pixmap(matrix=final_matrix)
    img_data = pix.tobytes("png")

# PyMuPDF → PIL → wxPython 转换链
stream = io.BytesIO(img_data)
pil_image = Image.open(stream)
width, height = pil_image.size
wx_image = wx.Image(width, height, pil_image.tobytes())
bitmap = wx.Bitmap(wx_image)

# 创建带滚动条的预览面板
self.preview_scroll = wx.ScrolledWindow(parent)
self.preview_scroll.SetScrollRate(20, 20)

# 设置虚拟大小支持大图像
self.preview_scroll.SetVirtualSize(width, height)

def on_zoom_in(self, event):
    self.zoom_factor = min(self.zoom_factor * 1.2, 5.0)
    
def on_zoom_out(self, event):
    self.zoom_factor = max(self.zoom_factor / 1.2, 0.2)
    
def on_zoom_reset(self, event):
    self.zoom_factor = 1.0

# 更新缩放比例显示
self.zoom_label.SetLabel(f"{int(self.zoom_factor * 100)}%")

<?xml version='1.0' encoding='utf-8'?>
<aliases>
    <item>
        <alias>别名1</alias>
        <path>/path/to/file1.pdf</path>
    </item>
    <item>
        <alias>别名2</alias>
        <path>/path/to/file2.pdf</path>
    </item>
</aliases>

def on_save_alias(self, event):
    tree = ET.parse(self.xml_file)
    root = tree.getroot()
    
    # 检查别名重复
    for item in root.findall('item'):
        if item.find('alias').text == alias:
            wx.MessageBox("别名已存在", "错误", wx.OK | wx.ICON_ERROR)
            return
    
    # 添加新记录
    item = ET.SubElement(root, 'item')
    alias_elem = ET.SubElement(item, 'alias')
    alias_elem.text = alias

try:
    # 主要逻辑
    pass
except ImportError as e:
    wx.MessageBox(f"缺少必要的库: {str(e)}")
except fitz.FileDataError as e:
    wx.MessageBox(f"PDF文件格式错误: {str(e)}")
except Exception as e:
    wx.MessageBox(f"预览PDF失败: {str(e)}")

self.statusbar.SetStatusText(f"正在加载PDF: {os.path.basename(pdf_path)}")
# ... 处理逻辑
self.statusbar.SetStatusText(f"PDF预览加载完成: {os.path.basename(pdf_path)}")

# 及时关闭文档
doc.close()
new_doc.close()

# 清理UI资源
self.preview_scroll.DestroyChildren()

# 按需渲染，只渲染第一页
page = doc[0]  # 获取第一页

# 合理的基础分辨率
base_matrix = fitz.Matrix(1.5, 1.5)

# 按钮绑定
pdf_btn.Bind(wx.EVT_BUTTON, self.on_select_pdf)

# 列表选择绑定
self.file_listbox.Bind(wx.EVT_LISTBOX, self.on_select_split_file)