qc_ns_web/format_manual_v2.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
格式化系统操作手册 - 改进版本，支持图片复制
"""

from docx import Document
from docx.shared import Pt, Inches
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.oxml.ns import qn
import re
from io import BytesIO

def set_font(run, font_name='宋体', font_size=12, bold=False):
    """设置字体"""
    run.font.name = font_name
    run.font.size = Pt(font_size)
    run.font.bold = bold
    run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)

def is_heading_level_1(text):
    """判断是否为一级标题"""
    if not text:
        return False
    # 匹配: 1、系统登录, 2、数据管理 等
    return bool(re.match(r'^\d+、', text)) or text == '系统登录'

def is_heading_level_2(text):
    """判断是否为二级标题"""
    if not text or len(text) < 3:
        return False
    # 匹配: 1.1, 1.2, 2.1 等
    match = re.match(r'^\d+\.\d+\s', text)
    return bool(match)

def is_heading_level_3(text):
    """判断是否为三级标题"""
    if not text or len(text) < 5:
        return False
    # 匹配: 2.1.1, 2.1.2 等
    match = re.match(r'^\d+\.\d+\.\d+\s', text)
    return bool(match)

def copy_paragraph_with_images(source_para, target_doc):
    """复制段落，包括文本和图片"""
    text = source_para.text.strip()

    # 创建新段落
    new_para = target_doc.add_paragraph()

    # 根据文本类型设置格式
    if is_heading_level_1(text):
        run = new_para.add_run(text)
        set_font(run, font_name='黑体', font_size=16, bold=True)
        new_para.paragraph_format.space_before = Pt(12)
        new_para.paragraph_format.space_after = Pt(6)

    elif is_heading_level_2(text):
        run = new_para.add_run(text)
        set_font(run, font_name='黑体', font_size=14, bold=True)
        new_para.paragraph_format.space_before = Pt(10)
        new_para.paragraph_format.space_after = Pt(5)

    elif is_heading_level_3(text):
        run = new_para.add_run(text)
        set_font(run, font_name='黑体', font_size=13, bold=True)
        new_para.paragraph_format.space_before = Pt(8)
        new_para.paragraph_format.space_after = Pt(4)

    else:
        # 普通段落
        if text:
            run = new_para.add_run(text)
            set_font(run, font_name='宋体', font_size=11)
            new_para.paragraph_format.space_after = Pt(3)
            new_para.paragraph_format.line_spacing = 1.15

    # 检查并复制图片
    if source_para._element.xpath('.//w:drawing'):
        img_para = target_doc.add_paragraph()
        img_para.alignment = WD_ALIGN_PARAGRAPH.CENTER

        for run in source_para.runs:
            if hasattr(run, '_element') and run._element.xpath('.//a:blip'):
                # 获取图片的 rId
                blip = run._element.xpath('.//a:blip')[0]
                rId = blip.get(qn('r:embed'))

                # 从源文档获取图片
                image_part = source_para.part.related_parts[rId]
                image_bytes = image_part.blob

                # 添加到新文档
                try:
                    # 获取原始图片尺寸
                    inline = run._element.xpath('.//wp:inline')[0]
                    extent = inline.xpath('.//wp:extent')[0]
                    cx = int(extent.get('cx'))
                    cy = int(extent.get('cy'))

                    # 转换为英寸
                    width = Inches(cx / 914400)
                    height = Inches(cy / 914400)

                    # 添加图片 - 使用 BytesIO 包装字节数据
                    img_run = img_para.add_run()
                    image_stream = BytesIO(image_bytes)
                    img_run.add_picture(image_stream, width=width, height=height)
                except Exception as e:
                    print(f"复制图片时出错: {e}")
                    # 如果失败，尝试不指定尺寸
                    try:
                        img_run = img_para.add_run()
                        image_stream = BytesIO(image_bytes)
                        img_run.add_picture(image_stream)
                    except:
                        pass

def format_document(input_path, output_path):
    """格式化文档"""
    print("正在读取文档...")
    doc = Document(input_path)

    print("创建新文档...")
    new_doc = Document()

    # 设置页边距
    for section in new_doc.sections:
        section.top_margin = Inches(1)
        section.bottom_margin = Inches(1)
        section.left_margin = Inches(1.25)
        section.right_margin = Inches(1.25)

    # ===== 第一页：标题页 =====
    print("创建标题页...")
    # 添加空行使标题居中
    for _ in range(8):
        new_doc.add_paragraph()

    title_para = new_doc.add_paragraph()
    title_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
    title_run = title_para.add_run('系统操作手册')
    set_font(title_run, font_name='黑体', font_size=28, bold=True)

    # 添加分页符
    new_doc.add_page_break()

    # ===== 第二页：目录 =====
    print("创建目录...")
    toc_title = new_doc.add_paragraph()
    toc_title.alignment = WD_ALIGN_PARAGRAPH.CENTER
    toc_run = toc_title.add_run('目  录')
    set_font(toc_run, font_name='黑体', font_size=18, bold=True)
    new_doc.add_paragraph()

    # 目录内容
    toc_items = [
        ('1、系统登录', 0),
        ('    1.1 系统登录', 1),
        ('    1.2 系统首页', 1),
        ('2、数据管理', 0),
        ('    2.1 检查列表', 1),
        ('        2.1.1 影像上传', 2),
        ('        2.1.2 查看影像数据详情', 2),
        ('    2.2 部位列表', 1),
        ('    2.3 患者信息', 1),
        ('3、质控管理', 0),
        ('    3.1 全量质控', 1),
        ('    3.2 质控任务', 1),
        ('    3.3 质控结果', 1),
        ('    3.4 部位结果', 1),
        ('4、字典管理', 0),
        ('    4.1 质控标准', 1),
        ('    4.2 质控因子', 1),
        ('    4.3 检查项目', 1),
        ('5、系统管理', 0),
        ('    5.1 用户管理', 1),
        ('    5.2 对接设置', 1),
    ]

    for item_text, level in toc_items:
        toc_para = new_doc.add_paragraph()
        toc_run = toc_para.add_run(item_text)
        set_font(toc_run, font_name='宋体', font_size=12)
        toc_para.paragraph_format.space_after = Pt(2)

    # 添加分页符
    new_doc.add_page_break()

    # ===== 第三页开始：正文内容 =====
    print("复制正文内容...")
    content_started = False
    para_count = 0

    for para in doc.paragraphs:
        text = para.text.strip()

        # 跳过前面的空段落
        if not content_started and not text:
            continue

        if text:
            content_started = True

        if content_started:
            copy_paragraph_with_images(para, new_doc)
            para_count += 1

            if para_count % 10 == 0:
                print(f"已处理 {para_count} 个段落...")

    # 保存新文档
    print("保存文档...")
    new_doc.save(output_path)
    print(f"\n✓ 文档格式化完成！")
    print(f"✓ 已保存到: {output_path}")
    print(f"✓ 共处理 {para_count} 个段落")


if __name__ == '__main__':
    input_file = '/Users/geng/Desktop/系统操作手册.docx'
    output_file = '/Users/geng/Desktop/系统操作手册_格式化.docx'

    try:
        format_document(input_file, output_file)
    except Exception as e:
        print(f"\n✗ 错误: {e}")
        import traceback
        traceback.print_exc()