#!/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")