ALL-teach_sys/frontend_化工/extract_all_questions_complete.py

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

# 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_all_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_all_questions:
        job_group_all_questions[job_group] = []

    # 解析面试题内容 - 分别处理模拟问答题和选择题
    sections = interview_content.split('#')

    for section in sections:
        if not section.strip():
            continue

        section_lines = section.strip().split('\n')
        section_title = section_lines[0] if section_lines else ''

        if '模拟问答题' in section_title or '问答题' in section_title:
            # 处理问答题
            current_q = None
            current_a = []

            for line in section_lines[1:]:
                line = line.strip()

                # 检查是否是新问题（以数字开头）
                if re.match(r'^\d+\.', line):
                    # 保存之前的问答对
                    if current_q and current_a:
                        answer_text = '\n'.join(current_a)
                        job_group_all_questions[job_group].append({
                            'question': current_q,
                            'answer': answer_text
                        })
                        total_questions += 1

                    current_q = line
                    current_a = []
                elif '示例答案' in line or '答案：' in line:
                    # 开始收集答案
                    continue
                elif current_q and (line.startswith('-') or line.startswith('•') or line):
                    # 收集答案内容
                    if line and not line.startswith('![]'):  # 排除图片链接
                        current_a.append(line)

            # 保存最后一个问答对
            if current_q and current_a:
                answer_text = '\n'.join(current_a)
                job_group_all_questions[job_group].append({
                    'question': current_q,
                    'answer': answer_text
                })
                total_questions += 1

        elif '选择题' in section_title:
            # 处理选择题
            current_q = None
            options = []
            current_answer = None

            for line in section_lines[1:]:
                line = line.strip()

                # 检查是否是新问题（以数字开头）
                if re.match(r'^\d+\.', line):
                    # 保存之前的选择题
                    if current_q and options and current_answer:
                        full_question = current_q + '\n' + '\n'.join(options)
                        job_group_all_questions[job_group].append({
                            'question': full_question,
                            'answer': current_answer
                        })
                        total_questions += 1

                    current_q = line
                    options = []
                    current_answer = None
                elif re.match(r'^[A-D]\.', line):
                    # 收集选项
                    options.append(line)
                elif '正确答案' in line or '正确选项' in line or '答案：' in line:
                    # 提取答案
                    current_answer = line

            # 保存最后一个选择题
            if current_q and options and current_answer:
                full_question = current_q + '\n' + '\n'.join(options)
                job_group_all_questions[job_group].append({
                    'question': full_question,
                    'answer': current_answer
                })
                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_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)} 题")

# 显示部分题目示例
print(f"\n===== 面试题示例 =====")
for job_group in list(job_group_all_questions.keys())[:2]:
    questions = job_group_all_questions[job_group]
    if questions:
        print(f"\n【{job_group}】共{len(questions)}题，前2题示例：")
        for i, q in enumerate(questions[:2], 1):
            print(f"  题{i}:")
            print(f"    问题: {q['question'][:60]}...")
            print(f"    答案: {q['answer'][:60]}...")

# 保存面试题数据
with open('all_questions_complete.json', 'w', encoding='utf-8') as f:
    json.dump(job_group_all_questions, f, ensure_ascii=False, indent=2)

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

# 生成最终的更新脚本
print(f"\n正在生成最终更新脚本...")

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

# 读取完整的面试题数据
with open('all_questions_complete.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_final_{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):
        # 对问题和答案进行JSON转义
        escaped_q = json.dumps(q['question'], ensure_ascii=False)
        escaped_a = json.dumps(q['answer'], ensure_ascii=False)

        question_str = '{'
        question_str += f'"id": "q{i+1}", '
        question_str += f'"question": {escaped_q}, '
        question_str += f'"answer": {escaped_a}'
        question_str += '}'
        sub_questions_items.append(question_str)

    # 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_all_questions_final.py")
print(f"\n请运行以下命令来更新所有面试题：")
print(f"python3 update_all_questions_final.py")