PDF简历智能解析器：用 Python 一键提取结构化数据

pip install pdfplumber pandas openpyxl python-dotenv

mkdir -p resume_parser && cd resume_parser
touch parser.py .env
mkdir -p input output

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import os
import re
import pdfplumber
import pandas as pd
from datetime import datetime
from pathlib import Path
from dotenv import load_dotenv

load_dotenv()

INPUT_DIR = "input"
OUTPUT_DIR = "output"

# 常见关键字段正则模式
FIELDS = {
    "姓名": r"(?:姓名|名字|称谓)\s*[:：]?\s*(\w{2,6})",
    "电话": r"(?:电话|手机|Tel|Mobile)\s*[:：]?(\d{11}|\+\d{1,3}-?\d{3,4}-?\d{4,7})",
    "邮箱": r"\b([A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,})\b",
    "学历": r"(?:学历|学位|教育程度)[：：]?(?:本科|硕士|博士|大专|学士)",
}

def extract_text_from_pdf(pdf_path):
    """从PDF提取全文文本"""
    with pdfplumber.open(pdf_path) as pdf:
        text = ""
        for page in pdf.pages:
            page_text = page.extract_text()
            if page_text:
                text += page_text + "\n"
        return text

def extract_fields(text):
    """从文本中提取结构化字段"""
    result = {}
    for field_name, pattern in FIELDS.items():
        matches = re.search(pattern, text, re.IGNORECASE | re.UNICODE)
        if matches:
            result[field_name] = matches.group(1).strip()
        else:
            result[field_name] = ""
    
    # 尝试提取公司名和职位（更宽松的模式）
    company_match = re.search(r"(?:任职单位|公司名称|Current Employer)[:：]?([\w\s一二三四五六七八九十]+?)[:\n])", text)
    if company_match:
        result["公司"] = company_match.group(1).strip()[:50]
    else:
        result["公司"] = ""
    
    pos_match = re.search(r(?:职位名称|岗位)[:：]?([\w\s]+?)[:\n])", text)
    if pos_match:
        result["职位"] = pos_match.group(1).strip()[:50]
    else:
        result["职位"] = ""
    
    return result

def process_resume(pdf_path, output_dir):
    """处理单个PDF文件"""
    filename = pdf_path.stem
    text = extract_text_from_pdf(pdf_path)
    fields = extract_fields(text)
    fields["文件路径"] = str(pdf_path)
    fields["提取时间"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    return fields

def main():
    """主程序入口"""
    input_dir = Path(INPUT_DIR)
    output_dir = Path(OUTPUT_DIR)
    output_dir.mkdir(exist_ok=True)
    
    if not input_dir.exists():
        print(f"❌ 目录不存在: {input_dir}")
        return
    
    pdf_files = list(input_dir.glob("*.pdf")) + list(input_dir.glob("*.PDF"))
    
    if not pdf_files:
        print(f"⚠️  {input_dir} 目录下没有找到PDF文件")
        return
    
    print(f"📄 发现 {len(pdf_files)} 个PDF文件，开始处理...")
    
    results = []
    for pdf_file in pdf_files:
        try:
            result = process_resume(pdf_file, output_dir)
            results.append(result)
            print(f"✅ {pdf_file.name}: 提取成功 ({len(result)} 个字段)")
        except Exception as e:
            print(f"❌ {pdf_file.name}: 解析失败 - {str(e)}")
    
    if results:
        df = pd.DataFrame(results)
        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
        output_file = output_dir/f"resumes_{timestamp}.xlsx"
        
        df.to_excel(output_file, index_max=False, engine="openpyxl")
        print(f"\n🎉 完成！共解析 {len(results)} 份简历")
        print(f"📁 保存至: {output_file}")
        
        # 也导出CSV方便打开
        csv_path = output_dir/f"resumes_{timestamp}.csv"
        df.to_csv(csv_path, index=False, encoding="utf-8-sig")
        print(f"📁 CSV版本: {csv_path}")

if __name__ == "__main__":
    main()

python parser.py