ALL-teach_sys/frontend_化工/extract_all_complete_questions.py

#!/usr/bin/env python3
import json
import re
from datetime import datetime

print("正在提取化工岗位简历中的所有面试题...")

# 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)

# 收集每个岗位群的所有面试题
job_group_all_questions = {}
total_questions = 0

# 遍历所有岗位，提取完整的面试题内容
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_all_questions:
        job_group_all_questions[job_group] = []

    # 解析面试题内容
    questions = []

    # 分割内容为行
    lines = interview_content.split('\n')

    current_question = None
    current_answer = []
    in_answer = False

    for i, line in enumerate(lines):
        line = line.strip()

        # 跳过空行和标题行
        if not line or line.startswith('#'):
            continue

        # 检测新的问题（以数字开头）
        if re.match(r'^[0-9]+[\.、]', line):
            # 保存之前的问答
            if current_question and current_answer:
                answer_text = '\n'.join(current_answer).strip()
                if answer_text and not any(skip in answer_text for skip in ['![', 'image']):
                    questions.append({
                        'question': current_question,
                        'answer': answer_text
                    })

            # 开始新问题
            current_question = line
            current_answer = []
            in_answer = False

        # 检测答案标记
        elif any(marker in line for marker in ['示例答案', '答案：', '正确答案', '正确选项', '答案是']):
            in_answer = True
            # 如果答案在同一行
            if '：' in line or ':' in line:
                answer_part = line.split('：', 1)[-1].split(':', 1)[-1].strip()
                if answer_part:
                    current_answer.append(answer_part)

        # 收集选项（选择题）
        elif current_question and re.match(r'^[A-D][\.、]', line):
            current_question += '\n' + line

        # 收集答案内容
        elif in_answer and line:
            if not line.startswith('#'):
                current_answer.append(line)

        # 如果还没有明确的答案标记，但这可能是答案内容
        elif current_question and not re.match(r'^[0-9]+[\.、]', line):
            # 检查是否可能是答案（在问题后面的非问题行）
            if i > 0 and not in_answer:
                # 如果上一行是问题，这行可能是答案
                prev_line = lines[i-1].strip() if i > 0 else ''
                if re.match(r'^[0-9]+[\.、]', prev_line) or prev_line == current_question:
                    in_answer = True
                    current_answer.append(line)

    # 保存最后一个问答
    if current_question and current_answer:
        answer_text = '\n'.join(current_answer).strip()
        if answer_text and not any(skip in answer_text for skip in ['![', 'image']):
            questions.append({
                'question': current_question,
                'answer': answer_text
            })

    # 将问题添加到岗位群（避免重复）
    for q in questions:
        # 清理问题和答案文本
        q['question'] = q['question'].strip()
        q['answer'] = q['answer'].strip()

        # 检查是否重复
        is_duplicate = False
        for existing in job_group_all_questions[job_group]:
            # 比较问题的前50个字符来判断是否重复
            if existing['question'][:50] == q['question'][:50]:
                is_duplicate = True
                break

        if not is_duplicate and len(q['question']) > 5 and len(q['answer']) > 5:
            job_group_all_questions[job_group].append(q)
            total_questions += 1

# 输出统计信息
print(f"\n===== 提取完成 =====")
print(f"总岗位群数: {len(job_group_all_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_all_questions.items()):
    print(f"  {job_group}: {len(questions)} 道题")

# 显示一些示例
print(f"\n===== 面试题示例 =====")
for job_group in ['化工安全', '化工检验检测', '化工生产']:
    if job_group in job_group_all_questions:
        questions = job_group_all_questions[job_group]
        print(f"\n【{job_group}】共 {len(questions)} 道题，前2题：")
        for i, q in enumerate(questions[:2], 1):
            print(f"  {i}. {q['question'][:60]}...")
            print(f"     答: {q['answer'][:60]}...")

# 保存提取的所有面试题
with open('all_interview_questions_complete.json', 'w', encoding='utf-8') as f:
    json.dump(job_group_all_questions, f, ensure_ascii=False, indent=2)

print(f"\n✅ 已保存到 all_interview_questions_complete.json")

# 读取现有mock文件并更新
print(f"\n正在更新 resumeInterviewMock.js...")

with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    content = f.read()

# 备份
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
updated_count = 0
for job_group, questions in job_group_all_questions.items():
    if not questions:
        continue

    # 为每个问题创建正确的格式
    formatted_questions = []
    for i, q in enumerate(questions, 1):
        formatted_questions.append({
            "id": f"q{i}",
            "question": q['question'],
            "answer": q['answer']
        })

    # 转换为JSON字符串
    sub_questions_str = json.dumps(formatted_questions, ensure_ascii=False, indent=8)

    # 替换对应岗位群的subQuestions
    pattern = rf'("question"\s*:\s*"{re.escape(job_group)}岗位群面试题"\s*,\s*"subQuestions"\s*:\s*)\[[^\]]*\]'
    replacement = rf'\1{sub_questions_str}'

    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}: {len(questions)} 道题")

# 保存更新后的文件
if updated_count > 0:
    with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
        f.write(content)
    print(f"\n✅ 成功更新了 {updated_count} 个岗位群，共 {total_questions} 道面试题")

# 验证语法
import subprocess
try:
    result = subprocess.run(['node', '-c', 'src/mocks/resumeInterviewMock.js'],
                          capture_output=True, text=True, encoding='utf-8')
    if result.returncode == 0:
        print("✓ 语法检查通过")
    else:
        print(f"✗ 语法检查失败: {result.stderr}")
        # 恢复备份
        with open(backup_file, 'r', encoding='utf-8') as f:
            backup_content = f.read()
        with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
            f.write(backup_content)
        print("已从备份恢复")
except Exception as e:
    print(f"错误: {e}")