208 lines
7.5 KiB
Python
208 lines
7.5 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
# -*- coding: utf-8 -*-
|
|||
|
|
"""
|
|||
|
|
更新简历与面试题页面的面试题数据
|
|||
|
|
使用大健康岗位简历.json中的个性化面试题内容
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import json
|
|||
|
|
import re
|
|||
|
|
import sys
|
|||
|
|
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_js(content):
|
|||
|
|
"""解析面试题内容，转换为JavaScript格式的问答结构"""
|
|||
|
|
if not content:
|
|||
|
|
return '[]'
|
|||
|
|
|
|||
|
|
questions_js = []
|
|||
|
|
|
|||
|
|
# 按大标题分割（# 一、二、三等）
|
|||
|
|
# 先处理开头可能没有\n的情况
|
|||
|
|
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_id = 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()
|
|||
|
|
|
|||
|
|
# 解析每个section中的问题
|
|||
|
|
sub_questions_js = []
|
|||
|
|
|
|||
|
|
# 按问题编号分割 (1. 2. 3. 等)
|
|||
|
|
question_parts = re.split(r'\n\s*(\d+\.)\s+', section_content)
|
|||
|
|
|
|||
|
|
sub_question_id = 1
|
|||
|
|
for j in range(1, len(question_parts), 2):
|
|||
|
|
if j + 1 < len(question_parts):
|
|||
|
|
question_block = question_parts[j + 1].strip()
|
|||
|
|
|
|||
|
|
# 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 += " " # 用空格连接，而不是换行
|
|||
|
|
answer_text += line
|
|||
|
|
|
|||
|
|
if question_text:
|
|||
|
|
# 转义引号和换行符
|
|||
|
|
question_text = question_text.replace('"', '\\"').replace('\n', '\\n')
|
|||
|
|
answer_text = answer_text.replace('"', '\\"').replace('\n', '\\n')
|
|||
|
|
|
|||
|
|
sub_question_template = ''' {{
|
|||
|
|
"id": "q{}_{}",
|
|||
|
|
"question": "{}",
|
|||
|
|
"answer": "{}"
|
|||
|
|
}}'''.format(question_id, sub_question_id, question_text, answer_text)
|
|||
|
|
sub_questions_js.append(sub_question_template)
|
|||
|
|
sub_question_id += 1
|
|||
|
|
|
|||
|
|
if sub_questions_js:
|
|||
|
|
section_title_escaped = section_title.replace('"', '\\"')
|
|||
|
|
question_template = ''' {{
|
|||
|
|
"id": "group_q{}",
|
|||
|
|
"question": "# {}",
|
|||
|
|
"subQuestions": [
|
|||
|
|
{}
|
|||
|
|
]
|
|||
|
|
}}'''.format(question_id, section_title_escaped, ',\n'.join(sub_questions_js))
|
|||
|
|
questions_js.append(question_template)
|
|||
|
|
question_id += 1
|
|||
|
|
|
|||
|
|
if questions_js:
|
|||
|
|
return '''[
|
|||
|
|
{}
|
|||
|
|
]'''.format(',\n'.join(questions_js))
|
|||
|
|
else:
|
|||
|
|
return '[]'
|
|||
|
|
|
|||
|
|
def update_interview_questions(health_data):
|
|||
|
|
"""更新面试题数据"""
|
|||
|
|
try:
|
|||
|
|
# 读取现有文件
|
|||
|
|
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
|
|||
|
|
content = f.read()
|
|||
|
|
|
|||
|
|
# 创建岗位到面试题的映射，按类别分组
|
|||
|
|
position_questions_map = {}
|
|||
|
|
category_questions_map = {}
|
|||
|
|
|
|||
|
|
# 首先按面试题类别分组
|
|||
|
|
for item in health_data:
|
|||
|
|
position_name = item.get('岗位名称', '')
|
|||
|
|
interview_category = item.get('面试题', '')
|
|||
|
|
interview_content = item.get('面试题内容', '')
|
|||
|
|
|
|||
|
|
if position_name and interview_content:
|
|||
|
|
# 为每个岗位生成个性化的面试题
|
|||
|
|
questions_js = parse_interview_content_to_js(interview_content)
|
|||
|
|
position_questions_map[position_name] = questions_js
|
|||
|
|
|
|||
|
|
# 同时按类别存储（用于相同类别的岗位）
|
|||
|
|
if interview_category and interview_category not in category_questions_map:
|
|||
|
|
category_questions_map[interview_category] = questions_js
|
|||
|
|
|
|||
|
|
# 更新每个岗位的面试题
|
|||
|
|
updated_content = content
|
|||
|
|
update_count = 0
|
|||
|
|
|
|||
|
|
for position_name, questions_js in position_questions_map.items():
|
|||
|
|
# 查找该岗位的questions字段并替换
|
|||
|
|
# 先尝试查找已存在questions字段的岗位
|
|||
|
|
pattern = rf'"title": "{re.escape(position_name)}",[^}}]+?"questions": \[[^\]]*?\]'
|
|||
|
|
|
|||
|
|
def replace_questions(match):
|
|||
|
|
matched_text = match.group(0)
|
|||
|
|
# 替换questions数组
|
|||
|
|
return re.sub(r'"questions": \[[^\]]*?\]', f'"questions": {questions_js}', matched_text, flags=re.DOTALL)
|
|||
|
|
|
|||
|
|
new_content = re.sub(pattern, replace_questions, updated_content, flags=re.DOTALL)
|
|||
|
|
|
|||
|
|
if new_content != updated_content:
|
|||
|
|
updated_content = new_content
|
|||
|
|
update_count += 1
|
|||
|
|
print(f"Updated interview questions for position: {position_name}")
|
|||
|
|
else:
|
|||
|
|
# 如果岗位没有questions字段，则添加
|
|||
|
|
pattern2 = rf'"title": "{re.escape(position_name)}",[^}}]+?"requirements": \[[^\]]*?\]'
|
|||
|
|
|
|||
|
|
def add_questions(match):
|
|||
|
|
matched_text = match.group(0)
|
|||
|
|
# 在requirements后添加questions字段
|
|||
|
|
return matched_text + ',\n "questions": ' + questions_js
|
|||
|
|
|
|||
|
|
new_content2 = re.sub(pattern2, add_questions, updated_content, flags=re.DOTALL)
|
|||
|
|
|
|||
|
|
if new_content2 != updated_content:
|
|||
|
|
updated_content = new_content2
|
|||
|
|
update_count += 1
|
|||
|
|
print(f"Added interview questions for position: {position_name}")
|
|||
|
|
|
|||
|
|
# 写回文件
|
|||
|
|
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(updated_content)
|
|||
|
|
|
|||
|
|
print(f"Interview questions updated successfully! Updated {update_count} positions.")
|
|||
|
|
print("Summary of question categories:")
|
|||
|
|
for category in category_questions_map.keys():
|
|||
|
|
print(f" - {category}")
|
|||
|
|
|
|||
|
|
return True
|
|||
|
|
|
|||
|
|
except Exception as e:
|
|||
|
|
print(f"Error updating interview questions: {e}")
|
|||
|
|
import traceback
|
|||
|
|
traceback.print_exc()
|
|||
|
|
return False
|
|||
|
|
|
|||
|
|
def main():
|
|||
|
|
"""主函数"""
|
|||
|
|
print("Starting to update personalized interview questions...")
|
|||
|
|
|
|||
|
|
# 加载数据
|
|||
|
|
health_data = load_health_resume_data()
|
|||
|
|
if not health_data:
|
|||
|
|
print("Failed to load health resume data")
|
|||
|
|
return False
|
|||
|
|
|
|||
|
|
# 更新面试题数据
|
|||
|
|
success = update_interview_questions(health_data)
|
|||
|
|
|
|||
|
|
if success:
|
|||
|
|
print("Personalized interview questions update completed!")
|
|||
|
|
else:
|
|||
|
|
print("Interview questions update failed!")
|
|||
|
|
|
|||
|
|
return success
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
main()
|