ALL-teach_sys/frontend_化工/extract_complete_questions.py

#!/usr/bin/env python3
import json

# 读取化工岗位简历数据
with open('网页未导入数据/化工产业/化工岗位简历.json', 'r', encoding='utf-8') as f:
    chemical_data = json.load(f)

# 收集所有岗位群的面试题
job_group_questions = {}
total_questions = 0

# 遍历所有岗位
for position in chemical_data:
    job_group = position.get('简历岗位群', '')
    interview_content = position.get('面试题内容', '')

    if not job_group or not interview_content:
        continue

    # 初始化岗位群
    if job_group not in job_group_questions:
        job_group_questions[job_group] = []

    # 解析面试题内容
    lines = interview_content.split('\n')
    current_question = None
    current_answer = None

    for line in lines:
        line = line.strip()

        # 识别问题行
        if any(marker in line for marker in ['示例答案', '正确答案', '答案：', '正确选项']):
            # 这是答案标记行
            if current_question and not current_answer:
                current_answer = ""
        elif line and current_answer is not None:
            # 收集答案内容
            if line.startswith('-') or line.startswith('•'):
                current_answer += line + '\n'
            elif not line.startswith('#') and not line.startswith('A.') and not line.startswith('B.') and not line.startswith('C.') and not line.startswith('D.'):
                current_answer += line + ' '
        elif line and (line[0].isdigit() or line.startswith('问题')):
            # 保存之前的问答对
            if current_question and current_answer:
                # 检查是否已存在
                is_duplicate = False
                for existing in job_group_questions[job_group]:
                    if existing['question'] == current_question:
                        is_duplicate = True
                        break

                if not is_duplicate:
                    job_group_questions[job_group].append({
                        'question': current_question.strip(),
                        'answer': current_answer.strip()
                    })
                    total_questions += 1

            # 开始新问题
            current_question = line
            current_answer = None

    # 保存最后一个问答对
    if current_question and current_answer:
        is_duplicate = False
        for existing in job_group_questions[job_group]:
            if existing['question'] == current_question:
                is_duplicate = True
                break

        if not is_duplicate:
            job_group_questions[job_group].append({
                'question': current_question.strip(),
                'answer': current_answer.strip()
            })
            total_questions += 1

# 输出统计信息
print(f"\n===== 化工岗位完整面试题统计 =====")
print(f"总岗位群数: {len(job_group_questions)}")
print(f"总面试题数: {total_questions}")
print(f"\n各岗位群面试题数量：")

for job_group, questions in sorted(job_group_questions.items()):
    print(f"  {job_group}: {len(questions)} 题")

# 保存提取的面试题
with open('complete_interview_questions.json', 'w', encoding='utf-8') as f:
    json.dump(job_group_questions, f, ensure_ascii=False, indent=2)

print(f"\n✅ 已保存所有面试题到 complete_interview_questions.json")

# 生成更新脚本
print(f"\n正在生成更新脚本...")

with open('update_complete_interview_questions.py', 'w', encoding='utf-8') as f:
    f.write('''#!/usr/bin/env python3
import json
import re
import subprocess
from datetime import datetime

# 读取提取的面试题数据
with open('complete_interview_questions.json', 'r', encoding='utf-8') as f:
    job_group_questions = json.load(f)

# 读取现有mock文件
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    content = f.read()

# 备份文件
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
backup_file = f'src/mocks/resumeInterviewMock.js.backup_complete_{timestamp}'
with open(backup_file, 'w', encoding='utf-8') as f:
    f.write(content)
print(f"已创建备份: {backup_file}")

# 更新每个岗位群的面试题
updated_count = 0
for job_group, questions in job_group_questions.items():
    if not questions:
        continue

    # 构建subQuestions数组内容
    sub_questions_items = []
    for i, q in enumerate(questions):
        question_obj = {
            "id": f"q{i+1}",
            "question": q['question'],
            "answer": q['answer']
        }
        sub_questions_items.append(json.dumps(question_obj, ensure_ascii=False, indent=20))

    # 创建完整的subQuestions内容
    sub_questions_content = ',\\n'.join(sub_questions_items)

    # 查找并替换对应岗位群的subQuestions
    pattern = rf'("question"\\s*:\\s*"{re.escape(job_group)}"[^}}]*?"subQuestions"\\s*:\\s*)\\[[^\\]]*\\]'
    replacement = rf'\\1[\\n{sub_questions_content}\\n        ]'

    new_content = re.sub(pattern, replacement, content, flags=re.DOTALL)

    if new_content != content:
        content = new_content
        updated_count += 1
        print(f"✓ 已更新 {job_group} 的 {len(questions)} 道面试题")

# 保存更新后的文件
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(content)

# 验证语法
try:
    result = subprocess.run(['node', '-c', 'src/mocks/resumeInterviewMock.js'],
                          capture_output=True, text=True, encoding='utf-8')
    if result.returncode == 0:
        print(f"\\n✓ 语法检查通过")
        print(f"✓ 成功更新了 {updated_count} 个岗位群的面试题")
        print(f"\\n✅ 所有面试题更新成功完成！")
    else:
        print(f"\\n✗ 语法检查失败: {result.stderr}")
        # 恢复备份
        with open(backup_file, 'r', encoding='utf-8') as f:
            content = f.read()
        with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
            f.write(content)
        print(f"已从备份恢复")
except Exception as e:
    print(f"错误: {e}")
''')

print(f"✅ 已生成 update_complete_interview_questions.py")
print(f"\n请运行以下命令来更新所有面试题：")
print(f"python3 update_complete_interview_questions.py")