import json import re import os # 读取环保岗位简历数据 with open('网页未导入数据/环保产业/环保岗位简历.json', 'r', encoding='utf-8') as f: env_data = json.load(f) # 读取面试题数据 with open('网页未导入数据/岗位群面试题（全产业）.json', 'r', encoding='utf-8') as f: interview_data = json.load(f) # 读取修改版简历 modified_resumes = {} modified_resume_dir = '网页未导入数据/环保产业/环保修改版简历' if os.path.exists(modified_resume_dir): for filename in os.listdir(modified_resume_dir): if filename.endswith('.md'): # 获取文件名（不含扩展名） file_position_name = filename.replace('.md', '') # 处理特殊的岗位名称映射 if file_position_name == '环评工程师（环境影响评价工程师）': # 同时存储两种形式，以确保能匹配 with open(os.path.join(modified_resume_dir, filename), 'r', encoding='utf-8') as f: content = f.read() modified_resumes['环评工程师'] = content modified_resumes['环评工程师（环境影响评价工程师）'] = content else: with open(os.path.join(modified_resume_dir, filename), 'r', encoding='utf-8') as f: modified_resumes[file_position_name] = f.read() print(f"已加载{len(modified_resumes)}个修改版简历：{list(modified_resumes.keys())}") # 按岗位群组织数据 position_groups = { "环境规划": [], "节能与碳管理": [], "设备运维与支持": [], "生态修复": [], "污染治理": [], "资源回收与再生": [], "报告输出与管理": [], "环境监测": [], "环境体系咨询": [], "实验室检测": [] } # 组织简历数据 for item in env_data: group = item.get("简历岗位群", "") if group in position_groups: position_groups[group].append(item) # 获取环保产业的面试题 env_interview_questions = {} for item in interview_data: if item.get("所属就业管家") == "环保": group = item.get("简历岗位群", "") if group not in env_interview_questions: env_interview_questions[group] = item.get("面试题内容", "") # 生成JavaScript格式的数据结构 js_output = """// 岗位群列表 const industries = [ """ # 生成所有岗位群的数据 industry_configs = [ ("environment_planning", "环境规划"), ("energy_carbon", "节能与碳管理"), ("equipment_maintenance", "设备运维与支持"), ("ecological_restoration", "生态修复"), ("pollution_control", "污染治理"), ("resource_recycling", "资源回收与再生"), ("report_management", "报告输出与管理"), ("environment_monitoring", "环境监测"), ("environment_consulting", "环境体系咨询"), ("laboratory_testing", "实验室检测") ] for idx, (industry_id, industry_name) in enumerate(industry_configs): js_output += f""" {{ id: "{industry_id}", name: "{industry_name}", positions: [ """ # 获取该岗位群的岗位列表 positions = position_groups.get(industry_name, []) for pos_idx, pos in enumerate(positions): position_name = pos.get("岗位名称", "") level = pos.get("岗位等级标签", "普通岗") avatar = pos.get("简历头像url", "") js_output += f""" {{ id: "{industry_id}_{pos_idx + 1}", title: "{position_name}", level: "{level}", avatar: "{avatar}", department: "{industry_name}", type: "全职", experience: "1-3年", education: "大专", salary: "6-10K", location: "苏州", updateTime: "2024-01-20", description: "{position_name}职位描述", requirements: [ "熟悉{industry_name}相关工作", "具有良好的沟通能力", "有相关工作经验优先" ] }}""" if pos_idx < len(positions) - 1: js_output += "," js_output += "\n" js_output += """ ], questions: [ { """ # 添加面试题内容 interview_content = env_interview_questions.get(industry_name, "") if interview_content: # 解析面试题内容，提取问答对 questions = [] lines = interview_content.split('\n') current_q = "" current_a = "" in_answer = False for i, line in enumerate(lines): # 匹配题目行：数字开头，可能包含"问题：" if line.strip() and line.strip()[0].isdigit() and '.' in line: if current_q and current_a: questions.append((current_q, current_a)) # 移除题号和"问题："前缀 current_q = re.sub(r'^\d+\.\s*', '', line.strip()) current_q = re.sub(r'^问题：\s*', '', current_q) current_a = "" in_answer = False # 匹配答案标记行 elif '答案' in line or '参考' in line or '回答' in line or '回复' in line: in_answer = True # 如果答案在同一行（冒号后） if '：' in line or ':' in line: parts = re.split('[：:]', line, 1) if len(parts) > 1 and parts[1].strip(): current_a = parts[1].strip() # 收集答案内容 elif in_answer and line.strip(): if not current_a: current_a = line.strip() else: current_a += " " + line.strip() # 空行可能表示答案结束 elif in_answer and not line.strip() and current_a: in_answer = False if current_q and current_a: questions.append((current_q, current_a)) # 不限制问题数量，显示所有题目 # questions = questions[:6] js_output += f""" id: "{industry_id}_q1", question: "{industry_name}岗位群面试题", subQuestions: [ """ for q_idx, (question, answer) in enumerate(questions): # 清理问题和答案文本 question = question.replace('"', '\\"').replace('\n', ' ') answer = answer.replace('"', '\\"').replace('\n', ' ') js_output += f""" {{ id: "q{q_idx + 1}", question: "{question}", answer: `{answer}` }}""" if q_idx < len(questions) - 1: js_output += "," js_output += "\n" js_output += """ ] } ] """ js_output += " }" if idx < len(industry_configs) - 1: js_output += "," js_output += "\n" js_output += """]; // 简历模板数据 const resumeTemplates = { """ # 生成简历模板数据 for idx, (industry_id, industry_name) in enumerate(industry_configs): js_output += f' "{industry_name}": [\n' positions = position_groups.get(industry_name, []) for pos_idx, pos in enumerate(positions): position_name = pos.get("岗位名称", "") level = pos.get("岗位等级标签", "普通岗") resume_content = pos.get("简历内容", "") project_name = pos.get("对应项目案例名称", "") avatar = pos.get("简历头像url", "") # 解析简历内容 project_desc = "" core_skills = [] compound_skills = [] personal_summary = "" if resume_content: # 提取项目职责 match = re.search(r'###\s*\(五\)\s*岗位职责[：:](.*?)(?=\n#|$)', resume_content, re.DOTALL) if match: project_desc = match.group(1).strip() # 提取垂直能力 match = re.search(r'###\s*\(一\)\s*垂直能力(.*?)(?=###|\n#|$)', resume_content, re.DOTALL) if match: skills_text = match.group(1) core_skills = [s.strip() for s in re.findall(r'\d+\.\s*(.*?)(?=\n\d+\.|$)', skills_text, re.DOTALL)][:5] # 提取复合能力 match = re.search(r'###\s*\(二\)\s*复合能力(.*?)(?=\n#|$)', resume_content, re.DOTALL) if match: skills_text = match.group(1) compound_skills = [s.strip() for s in re.findall(r'\d+\.\s*(.*?)(?=\n\d+\.|$)', skills_text, re.DOTALL)][:5] # 提取个人评价 match = re.search(r'#\s*三、\s*个人评价(.*?)$', resume_content, re.DOTALL) if match: personal_summary = match.group(1).strip() # 清理文本 def clean_text(text): return text.replace('\\n', '\\\\n').replace('"', '\\"').replace('\n', '\\n') # 获取修改版简历（如果存在） modified_content = modified_resumes.get(position_name) if not modified_content: # 尝试不同的岗位名称格式 if '（' in position_name: # 尝试去掉括号部分 short_name = position_name.split('（')[0] modified_content = modified_resumes.get(short_name) elif position_name == '环评工程师': # 特殊处理环评工程师 modified_content = modified_resumes.get('环评工程师（环境影响评价工程师）') # 如果没有修改版，使用原始版本 if not modified_content: modified_content = resume_content js_output += f""" {{ position: "{position_name}", level: "{level}", avatar: "{avatar}", content: {{ original: `{clean_text(resume_content)}`, modified: `{clean_text(modified_content)}` }}, studentInfo: {{ project_experience: {{ project_name: "{project_name}", position: "{position_name}", time_period: "XXXXXX", company: "XXXXXX", description: `{clean_text(project_desc)}` }}, core_skills: [ """ for skill_idx, skill in enumerate(core_skills): js_output += f' "{clean_text(skill)}"' if skill_idx < len(core_skills) - 1: js_output += "," js_output += "\n" js_output += """ ], compound_skills: [ """ for skill_idx, skill in enumerate(compound_skills): js_output += f' "{clean_text(skill)}"' if skill_idx < len(compound_skills) - 1: js_output += "," js_output += "\n" js_output += f""" ], personal_summary: "{clean_text(personal_summary)}" }} }}""" if pos_idx < len(positions) - 1: js_output += "," js_output += "\n" js_output += " ]" if idx < len(industry_configs) - 1: js_output += "," js_output += "\n" js_output += """}; // 我的简历数据 const myResume = { personalInfo: { name: "邓沐", phone: "138****8888", email: "dengmu@example.com", age: 22, education: "苏州农业职业技术学院 生态环境修复技术 2021.9-2024.6", experience: "1年", location: "苏州" }, workExperience: [ { company: "某环保科技公司", position: "环境监测实习生", duration: "2023.06-2024.01", description: "负责环境监测数据采集、分析和报告编制工作" } ], skills: ["环境监测", "数据分析", "报告编制", "AutoCAD", "GIS"], projects: [ { name: "某工业园区环境影响评价项目", role: "环评助理", duration: "2023.09-2024.01", description: "协助完成环境影响评价报告的编制和现场踏勘工作" } ] }; // 获取页面mock数据的函数 export function getMockPageData() { return resumeInterviewMockData; } // 导出合并的数据 export const resumeInterviewMockData = { industries, resumeTemplates, myResume }; """ # 写入文件 with open('src/mocks/resumeInterviewMock_env.js', 'w', encoding='utf-8') as f: f.write(js_output) print("转换完成！已生成 src/mocks/resumeInterviewMock_env.js")