222 lines
9.0 KiB
Python
222 lines
9.0 KiB
Python
|
#!/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，移除重复的岗位群
|
|||
|
|
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()
|
|||
|
|
|
|||
|
|
# 找到industries数组
|
|||
|
|
match = re.search(r'const industries = \[(.*?)\];', content, re.DOTALL)
|
|||
|
|
if not match:
|
|||
|
|
print("未找到industries数组")
|
|||
|
|
return
|
|||
|
|
|
|||
|
|
industries_content = match.group(1)
|
|||
|
|
|
|||
|
|
# 解析每个岗位群
|
|||
|
|
industry_blocks = re.findall(r'\{[^}]*?"id":\s*"health_\d+"[^}]*?"positions":\s*\[[^\]]*?\][^}]*?\}', industries_content, re.DOTALL)
|
|||
|
|
|
|||
|
|
# 去重并保留第一个出现的
|
|||
|
|
seen_ids = set()
|
|||
|
|
unique_blocks = []
|
|||
|
|
for block in industry_blocks:
|
|||
|
|
id_match = re.search(r'"id":\s*"(health_\d+)"', block)
|
|||
|
|
if id_match:
|
|||
|
|
industry_id = id_match.group(1)
|
|||
|
|
if industry_id not in seen_ids:
|
|||
|
|
seen_ids.add(industry_id)
|
|||
|
|
unique_blocks.append(block)
|
|||
|
|
|
|||
|
|
print(f"找到 {len(industry_blocks)} 个岗位群块，去重后剩余 {len(unique_blocks)} 个")
|
|||
|
|
|
|||
|
|
# 为每个岗位群添加面试题
|
|||
|
|
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"
|
|||
|
|
elif '技术' in q['question'] or '专业' in q['question']:
|
|||
|
|
current_category = "专业技术类问题"
|
|||
|
|
elif '团队' in q['question'] or '协作' in q['question']:
|
|||
|
|
current_category = "团队协作类问题"
|
|||
|
|
|
|||
|
|
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'
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# 更新每个岗位群块，添加questions字段
|
|||
|
|
updated_blocks = []
|
|||
|
|
for block in unique_blocks:
|
|||
|
|
# 获取岗位群名称
|
|||
|
|
name_match = re.search(r'"name":\s*"([^"]+)"', block)
|
|||
|
|
id_match = re.search(r'"id":\s*"(health_\d+)"', block)
|
|||
|
|
|
|||
|
|
if name_match and id_match:
|
|||
|
|
industry_name = name_match.group(1)
|
|||
|
|
industry_id = id_match.group(1)
|
|||
|
|
|
|||
|
|
# 查找对应的面试题
|
|||
|
|
questions = None
|
|||
|
|
for orig_name, mapped_id in industry_mapping.items():
|
|||
|
|
if mapped_id == industry_id and orig_name in industry_questions:
|
|||
|
|
questions = industry_questions[orig_name]
|
|||
|
|
break
|
|||
|
|
|
|||
|
|
# 如果没找到，使用默认面试题
|
|||
|
|
if not questions:
|
|||
|
|
questions = [{
|
|||
|
|
"id": "group_q1",
|
|||
|
|
"question": f"{industry_name}专业认知",
|
|||
|
|
"subQuestions": [
|
|||
|
|
{
|
|||
|
|
"id": "q1",
|
|||
|
|
"question": f"你如何理解{industry_name}的核心价值？",
|
|||
|
|
"answer": f"{industry_name}的核心价值在于通过专业技能和知识，为企业和客户创造价值，推动行业发展。"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"id": "q2",
|
|||
|
|
"question": f"{industry_name}中最重要的能力是什么？",
|
|||
|
|
"answer": "专业技能、沟通能力、团队协作和持续学习能力都是非常重要的。"
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"id": "q3",
|
|||
|
|
"question": f"你为什么选择{industry_name}这个方向？",
|
|||
|
|
"answer": "我对这个领域充满热情，相信能够在这里发挥我的专业优势，为行业发展做出贡献。"
|
|||
|
|
}
|
|||
|
|
]
|
|||
|
|
}]
|
|||
|
|
|
|||
|
|
# 在positions数组后添加questions字段
|
|||
|
|
if '"questions"' not in block:
|
|||
|
|
# 找到positions数组的结束位置
|
|||
|
|
pos_end = block.rfind(']')
|
|||
|
|
if pos_end > 0:
|
|||
|
|
questions_json = json.dumps(questions, ensure_ascii=False, indent=4)
|
|||
|
|
# 调整缩进
|
|||
|
|
questions_json = questions_json.replace('\n', '\n ')
|
|||
|
|
new_block = block[:pos_end+1] + ',\n "questions": ' + questions_json + block[pos_end+1:]
|
|||
|
|
updated_blocks.append(new_block)
|
|||
|
|
print(f" ✓ 为 {industry_name} ({industry_id}) 添加了面试题")
|
|||
|
|
else:
|
|||
|
|
updated_blocks.append(block)
|
|||
|
|
else:
|
|||
|
|
updated_blocks.append(block)
|
|||
|
|
else:
|
|||
|
|
updated_blocks.append(block)
|
|||
|
|
|
|||
|
|
# 重新构建industries数组
|
|||
|
|
new_industries = 'const industries = [\n ' + ',\n '.join(updated_blocks) + '\n];'
|
|||
|
|
|
|||
|
|
# 替换原内容
|
|||
|
|
new_content = content[:content.index('const industries')] + new_industries + content[content.index('];', content.index('const industries')) + 2:]
|
|||
|
|
|
|||
|
|
# 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(new_content)
|
|||
|
|
|
|||
|
|
print(f"\n完成！处理了 {len(updated_blocks)} 个岗位群")
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
main()
|