Files
online_sys/frontend_大健康/add_questions_safely.py

150 lines
5.8 KiB
Python
Raw Normal View History

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import json
import re
def parse_interview_questions(content):
"""解析面试题内容为结构化数据"""
questions = []
# 分割成不同的问题类别
sections = re.split(r'\n# ([一二三四五六七八九十]+、[^#\n]+)', content)
question_id = 1
for i in range(1, len(sections), 2):
if i >= len(sections):
break
section_title = sections[i].strip()
section_content = sections[i + 1] if i + 1 < len(sections) else ""
# 提取每个问题
question_blocks = re.split(r'\n\d+\.\s+', section_content)
for j, block in enumerate(question_blocks[1:], 1): # 跳过第一个空块
lines = block.strip().split('\n')
if not lines:
continue
question_text = lines[0].strip()
# 查找答案
answer_text = ""
for k, line in enumerate(lines):
if '示例答案' in line or '答案' in line:
# 获取答案内容
answer_lines = []
for answer_line in lines[k+1:]:
answer_line = answer_line.strip()
if answer_line and not answer_line.startswith('示例答案'):
if re.match(r'^\d+\.', answer_line):
break
answer_lines.append(answer_line)
answer_text = ' '.join(answer_lines)
break
if question_text and answer_text:
questions.append({
"id": f"q{question_id}",
"question": question_text,
"answer": answer_text
})
question_id += 1
return questions
def main():
# 读取大健康岗位简历数据
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/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:
health_data = json.load(f)
# 读取Mock文件
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
content = f.read()
# 创建岗位群到面试题的映射
industry_questions = {}
for item in health_data:
industry = item.get('简历岗位群', '')
interview_content = item.get('面试题内容', '')
if industry and interview_content and industry not in industry_questions:
questions = parse_interview_questions(interview_content)
if questions:
# 按类别分组
category_questions = {}
current_category = "综合面试题"
for q in questions:
if '岗位理解' in q['question']:
current_category = "岗位理解类问题"
elif '实践经验' in q['question'] or '案例' in q['question']:
current_category = "实践经验类问题"
elif '客户服务' in q['question'] or '客户' in q['question']:
current_category = "客户服务类问题"
elif '市场' in q['question'] or '趋势' in q['question']:
current_category = "市场与未来趋势类问题"
if current_category not in category_questions:
category_questions[current_category] = []
category_questions[current_category].append(q)
# 构建questions数组
questions_array = []
cat_id = 1
for category, cat_questions in category_questions.items():
questions_array.append({
"id": f"group_q{cat_id}",
"question": category,
"subQuestions": cat_questions
})
cat_id += 1
industry_questions[industry] = questions_array
# 映射岗位群名称到ID
industry_mapping = {
'健康管理': 'health_1',
'健康检查': 'health_2',
'康复治疗': 'health_3',
'慢性病管理': 'health_4',
'轻医美': 'health_5',
'心理健康': 'health_6',
'社群运营': 'health_7',
'药品供应链管理': 'health_8',
'药品生产': 'health_9',
'药品质量检测': 'health_10',
'药物研发': 'health_11'
}
# 为每个岗位群添加questions字段
updates = 0
for orig_name, industry_id in industry_mapping.items():
if orig_name in industry_questions:
questions = industry_questions[orig_name]
# 生成questions的JSON字符串
questions_json = json.dumps(questions, ensure_ascii=False, indent=2)
# 查找对应的岗位群并添加questions字段
# 使用更精确的模式在positions数组结束后添加questions
pattern = rf'("id":\s*"{industry_id}"[^{{]*?"positions":\s*\[[^\]]*?\])\s*(\}})'
# 添加questions字段
replacement = rf'\1,\n "questions": {questions_json}\n \2'
new_content, count = re.subn(pattern, replacement, content, flags=re.DOTALL)
if count > 0:
content = new_content
updates += 1
print(f"✓ 为 {orig_name} ({industry_id}) 添加了 {len(questions)} 个问题分类")
# 写回文件
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
f.write(content)
print(f"\n完成!更新了 {updates} 个岗位群的面试题")
if __name__ == "__main__":
main()