cd2e307402
主要内容： - 包含12个产业的完整教务系统前端代码 - 智能启动脚本 (start-industry.sh) - 可视化产业导航页面 (index.html) - 项目文档 (README.md) 优化内容： - 删除所有node_modules和.yoyo文件夹，从7.5GB减少到2.7GB - 添加.gitignore文件避免上传不必要的文件 - 自动依赖管理和智能启动系统 产业列表： 1. 文旅产业 (5150) 2. 智能制造 (5151) 3. 智能开发 (5152) 4. 财经商贸 (5153) 5. 视觉设计 (5154) 6. 交通物流 (5155) 7. 大健康 (5156) 8. 土木水利 (5157) 9. 食品产业 (5158) 10. 化工产业 (5159) 11. 能源产业 (5160) 12. 环保产业 (5161) 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
171 lines
6.2 KiB
Python
171 lines
6.2 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
重新组织面试题数据 - 只修改数据，不修改代码结构
|
|
将各个position的questions合并到对应industry的questions字段
|
|
"""
|
|
|
|
import json
|
|
import re
|
|
from datetime import datetime
|
|
|
|
def load_health_resume_data():
|
|
"""加载大健康岗位简历数据"""
|
|
try:
|
|
with open('网页未导入数据/大健康产业/大健康岗位简历.json', 'r', encoding='utf-8') as f:
|
|
return json.load(f)
|
|
except Exception as e:
|
|
print(f"Error loading health resume data: {e}")
|
|
return None
|
|
|
|
def parse_interview_content_to_flat_array(content):
|
|
"""解析面试题内容，转换为扁平的问答数组"""
|
|
if not content:
|
|
return []
|
|
|
|
questions = []
|
|
|
|
# 按大标题分割（# 一、二、三等）
|
|
if content.startswith('# '):
|
|
content = '\n' + content
|
|
sections = re.split(r'\n# ([一二三四五六七八九十]+、[^#\n]+)', content)
|
|
|
|
if len(sections) < 2:
|
|
return []
|
|
|
|
question_counter = 1
|
|
for i in range(1, len(sections), 2):
|
|
if i + 1 < len(sections):
|
|
section_title = sections[i].strip()
|
|
section_content = sections[i + 1].strip()
|
|
|
|
# 按问题编号分割 (1. 2. 3. 等)
|
|
question_parts = re.split(r'\n\s*(\d+\.)?\s*', section_content)
|
|
|
|
for j in range(1, len(question_parts)):
|
|
if j >= len(question_parts) or question_parts[j] is None:
|
|
continue
|
|
question_block = str(question_parts[j]).strip()
|
|
if not question_block or question_block.endswith('.'):
|
|
continue
|
|
|
|
# 提取问题和答案
|
|
lines = question_block.split('\n')
|
|
question_text = ""
|
|
answer_text = ""
|
|
in_answer = False
|
|
|
|
for line in lines:
|
|
line = line.strip()
|
|
if line.startswith('示例答案：'):
|
|
in_answer = True
|
|
continue
|
|
|
|
if not in_answer and line and not line.startswith('示例答案：'):
|
|
if question_text:
|
|
question_text += " "
|
|
question_text += line
|
|
elif in_answer and line:
|
|
if answer_text:
|
|
answer_text += " "
|
|
answer_text += line
|
|
|
|
if question_text:
|
|
questions.append({
|
|
"id": f"q{question_counter}",
|
|
"question": question_text,
|
|
"answer": answer_text
|
|
})
|
|
question_counter += 1
|
|
|
|
return questions
|
|
|
|
def reorganize_questions_by_industry():
|
|
"""重新组织面试题数据"""
|
|
try:
|
|
# 加载大健康数据
|
|
health_data = load_health_resume_data()
|
|
if not health_data:
|
|
print("Failed to load health resume data")
|
|
return False
|
|
|
|
# 按面试题类别分组
|
|
category_questions = {}
|
|
for item in health_data:
|
|
category = item.get('面试题', '')
|
|
interview_content = item.get('面试题内容', '')
|
|
|
|
if category and interview_content and category not in category_questions:
|
|
questions = parse_interview_content_to_flat_array(interview_content)
|
|
if questions:
|
|
category_questions[category] = questions
|
|
|
|
print(f"解析了 {len(category_questions)} 个面试题类别")
|
|
|
|
# 读取现有文件
|
|
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
|
|
content = f.read()
|
|
|
|
# 创建备份
|
|
backup_filename = f'src/mocks/resumeInterviewMock.js.backup_{datetime.now().strftime("%Y%m%d_%H%M%S")}'
|
|
with open(backup_filename, 'w', encoding='utf-8') as f:
|
|
f.write(content)
|
|
print(f"已创建备份文件: {backup_filename}")
|
|
|
|
updated_content = content
|
|
|
|
# 首先移除所有position级别的questions字段
|
|
updated_content = re.sub(
|
|
r',?\s*"questions": \[[^\]]*?\](?:\s*,\s*)?',
|
|
'',
|
|
updated_content,
|
|
flags=re.DOTALL
|
|
)
|
|
|
|
# 映射关系：行业名称 -> 面试题类别
|
|
industry_category_mapping = {
|
|
"健康管理": "健康管理类岗位面试题",
|
|
"健康检查": "健康检查类岗位面试题",
|
|
"康复治疗": "康复治疗类岗位面试题",
|
|
"医疗美容": "医疗美容类岗位面试题",
|
|
"运营管理": "运营类岗位面试题",
|
|
"心理健康": "心理健康类岗位面试题",
|
|
"供应链管理": "供应链类岗位面试题",
|
|
"药品制造": "药品制造类岗位面试题",
|
|
"检测分析": "检测分析类岗位面试题",
|
|
"临床研究": "临床研究类岗位面试题"
|
|
}
|
|
|
|
# 为每个行业添加对应的面试题
|
|
for industry_name, category in industry_category_mapping.items():
|
|
if category in category_questions:
|
|
questions_data = category_questions[category]
|
|
questions_json = json.dumps(questions_data, ensure_ascii=False, indent=6)
|
|
|
|
# 查找对应行业并添加questions字段
|
|
pattern = rf'("name": "{re.escape(industry_name)}"[^}}]*?"positions": \[[^\]]*?\]\s*)'
|
|
replacement = r'\1,\n "questions": ' + questions_json
|
|
|
|
updated_content = re.sub(
|
|
pattern,
|
|
replacement,
|
|
updated_content,
|
|
flags=re.DOTALL
|
|
)
|
|
print(f"✅ 为 {industry_name} 行业添加了面试题 ({len(questions_data)} 个问题)")
|
|
|
|
# 写回文件
|
|
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
|
|
f.write(updated_content)
|
|
|
|
print("面试题数据重组完成！")
|
|
return True
|
|
|
|
except Exception as e:
|
|
print(f"重组失败: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
return False
|
|
|
|
if __name__ == "__main__":
|
|
reorganize_questions_by_industry() |