achievement-qztc

课程目标达成情况分析表生成工具（QZTC版）

根据Excel学生数据替换Word模板中的课程目标达成情况，生成新的分析表。

适用场景

• 根据Excel学生名单生成课程目标达成情况分析表
• 自动计算各课程目标的达成值（随机生成成绩，百分比表示）

---

文件路径

• 模板文件: /Volumes/qztcm09/Desktop/temp/课程目标达成情况分析表-数据可视化-模版.docx
• Excel数据: /Volumes/qztcm09/Desktop/temp/数据可视化技术23级计算机.xls

---

使用步骤

步骤1：读取Excel数据

import pandas as pd
import shutil
import random
from docx import Document
from datetime import datetime

# 读取Excel
df = pd.read_excel('/Users/qztcm09/Desktop/temp/数据可视化技术23级计算机.xls')

# 排除旷考学生
df = df[df['备注'] != '旷考'].reset_index(drop=True)

# 自动判断当前学年和学期
now = datetime.now()
year = now.year
month = now.month
day= now.day

if 1 <= month <= 6:
    # 1-6月：第一学期（上学年）
    academic_year = f"{year-1} - {year}"
    semester = "一"
else:
    # 7-12月：第二学期（上学年）
    academic_year = f"{year-1} - {year}"
    semester = "二"

print(f"当前学年: {academic_year}, 学期: {semester}学期")

# 从"班级"字段提取年级、班级、专业信息
# 专业名称提取支持两种情况：
#   情况1: "23级计算机" → 年级=23, 专业=计算机
#   情况2: "23级软工2班" → 年级=23, 专业=软工
import re
class_name = df['班级'].iloc[0] if '班级' in df.columns else ''
match = re.search(r'(\d+)级', str(class_name))
grade = match.group(1) if match else ''  # 如 "23"
# 提取专业：匹配 "XX级" 后面到 "XX班" 或结尾的部分
match = re.search(r'\d+级(.+?)(?:\d+班)?$', str(class_name))
major = match.group(1).strip() if match else ''  # 如 "计算机" 或 "软工"


# 获取学生信息
students = df[['学号', '姓名']].copy()
print(f"学生人数: {len(students)}")

步骤2：复制模板并打开

template_path = '/Users/qztcm09/Desktop/temp/课程目标达成情况分析表-数据可视化-模版.docx'
output_path = '/Users/qztcm09/Desktop/temp/课程目标达成情况分析表-数据可视化-23级计算机.docx'

shutil.copy(template_path, output_path)
doc = Document(output_path)

步骤3：通用文本替换

⚠️ 重要：Word占位符可能被拆分成多个run，且表格单元格中可能有换行，需要特殊处理，保留原格式

def replace_text_preserve_format(para, replacements):
    """替换段落文本但保留格式"""
    # 先收集所有run的文本
    full_text = ''.join(run.text for run in para.runs if run.text)
    
    # 检查是否有占位符
    has_placeholder = any(old in full_text for old, _ in replacements)
    if not has_placeholder:
        return
    
    # 执行替换
    for old, new in replacements:
        full_text = full_text.replace(old, new)
    
    # 获取第一个run的格式作为基准
    if para.runs:
        first_run = para.runs[0]
        font_name = first_run.font.name
        font_size = first_run.font.size
        font_bold = first_run.font.bold
        font_italic = first_run.font.italic
    else:
        font_name, font_size, font_bold, font_italic = None, None, None, None
    
    # 清空并用新文本创建单一run，保留格式
    para.clear()
    run = para.add_run(full_text)
    if font_name:
        run.font.name = font_name
    if font_size:
        run.font.size = font_size
    if font_bold is not None:
        run.font.bold = font_bold
    if font_italic is not None:
        run.font.italic = font_italic
    
    return para

def replace_text_in_table_cell(cell, replacements):
    """替换表格单元格中的文本（处理单元格内换行的情况）"""
    # 遍历单元格中的所有段落
    for para in cell.paragraphs:
        full_text = ''.join(run.text for run in para.runs if run.text)
        has_placeholder = any(old in full_text for old, _ in replacements)
        
        if has_placeholder:
            # 获取格式
            if para.runs:
                first_run = para.runs[0]
                font_name = first_run.font.name
                font_size = first_run.font.size
                font_bold = first_run.font.bold
                font_italic = first_run.font.italic
            else:
                font_name, font_size, font_bold, font_italic = None, None, None, None
            
            # 执行替换
            for old, new in replacements:
                full_text = full_text.replace(old, new)
            
            # 清空并重新设置
            para.clear()
            run = para.add_run(full_text)
            if font_name:
                run.font.name = font_name
            if font_size:
                run.font.size = font_size
            if font_bold is not None:
                run.font.bold = font_bold
            if font_italic is not None:
                run.font.italic = font_italic
    
    return cell

# 替换配置
replacements = [
    ('$acyear$', academic_year),
    ('$semester$', semester),
    ('$g$', grade),
    ('$major$', major),
    ('$total$', f'{len(students)}人'),
    ('$year$', str(year)),
    ('$month$', str(month)),
    ('$day$', str(day)),
]

# 替换表格中的文本
for table in doc.tables:
    for row in table.rows:
        for cell in row.cells:
            replace_text_in_cell(cell, replacements)

# 替换段落中的文本（处理被拆分的情况，保留格式）
for para in doc.paragraphs:
    replace_text_preserve_format(para, replacements)