使用Python将Word文档导出为PDF格式并从Word文档中提取数据

pip install pywin32

import os
from win32com import client as wc

def convert_word_to_pdf(word_path: str) -> str:
    """
    将单个Word文档(doc/docx)转换为PDF格式，并返回转换后的文件路径
    
    Args:
        word_path (str): Word文件路径
        
    Returns:
        str: 转换后的PDF文件路径
        
    Raises:
        FileNotFoundError: 如果文件不存在
        ValueError: 如果文件不是Word格式或路径无效
        Exception: 转换过程中的其他错误
    """
    # 参数验证
    if not word_path or not isinstance(word_path, str):
        raise ValueError("文件路径不能为空且必须是字符串")
    
    # 检查文件是否存在
    if not os.path.exists(word_path):
        raise FileNotFoundError(f"文件不存在: {word_path}")
    
    # 检查文件扩展名
    valid_extensions = ('.doc', '.docx')
    if not word_path.lower().endswith(valid_extensions):
        raise ValueError(f"文件不是Word格式(.doc/.docx): {word_path}")
    
    # 检查文件是否被占用（临时文件）
    if os.path.basename(word_path).startswith('~'):
        raise ValueError(f"文件可能是临时文件: {word_path}")
    
    # 检查文件大小（避免处理空文件或损坏文件）
    file_size = os.path.getsize(word_path)
    if file_size == 0:
        raise ValueError(f"文件为空: {word_path}")
    
    word = None
    doc = None
    
    try:
        # 创建Word应用实例
        word = wc.Dispatch("Word.Application")
        word.Visible = False
        
        # 打开文档
        doc = word.Documents.Open(word_path)
        
        # 生成新的PDF文件路径
        base_path = os.path.splitext(word_path)[0]
        new_path = base_path + ".pdf"
        
        # 处理文件名冲突
        count = 0
        while os.path.exists(new_path):
            count += 1
            new_path = f"{base_path}({count}).pdf"
        
        # 保存为PDF格式（17代表PDF格式）
        doc.SaveAs(new_path, 17)
        
        # 验证转换后的文件
        if not os.path.exists(new_path):
            raise Exception("转换后的PDF文件未创建成功")
        
        # 检查转换后的文件大小
        if os.path.getsize(new_path) == 0:
            raise Exception("转换后的PDF文件为空")
        
        return new_path
        
    except Exception as e:
        # 清理可能创建的部分文件
        if 'new_path' in locals() and os.path.exists(new_path):
            try:
                os.remove(new_path)
            except:
                pass
        raise e
        
    finally:
        # 确保资源被正确释放
        try:
            if doc:
                doc.Close()
        except:
            pass
            
        try:
            if word:
                word.Quit()
        except:
            pass


def main():
    """主函数：转换单个文件并显示结果"""
    # 直接在代码中设置要转换的文件路径
    word_file_path = r"D:\word_files\example.docx"  # 修改为您要转换的Word文件路径
    
    try:
        print(f"开始转换文件: {word_file_path}")
        
        # 转换文件
        pdf_path = convert_word_to_pdf(word_file_path)
        
        # 输出成功信息
        print("\n" + "="*50)
        print("✓ 文件转换成功！")
        print(f"原始文件: {word_file_path}")
        print(f"转换后文件: {pdf_path}")
        print(f"文件大小: {os.path.getsize(pdf_path)} 字节")
        print("="*50)
        
    except FileNotFoundError as e:
        print(f"✗ 错误: {e}")
        print("请检查文件路径是否正确")
    except ValueError as e:
        print(f"✗ 错误: {e}")
        print("请确保文件是有效的Word文档(.doc/.docx)")
    except Exception as e:
        print(f"✗ 转换失败: {e}")
        print("可能是Word应用问题或文件损坏")


if __name__ == "__main__":
    main()

import os
from win32com import client as wc

word = wc.Dispatch("Word.Application")
word.Visible = False

doc = word.Documents.Open(word_path)
doc.SaveAs(new_path, 17)
doc.Close()

word.Quit()

pip install python-docx

pip install faker

import os
import random
from docx import Document
from docx.shared import Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.oxml.ns import qn

from faker import Faker

def set_document_font(doc):
    """
    设置文档的默认字体为宋体和Times New Roman
    """
    # 设置全局样式
    style = doc.styles['Normal']
    font = style.font
    font.name = 'Times New Roman'
    font._element.rPr.rFonts.set(qn('w:eastAsia'), u'宋体')
    font.size = Pt(12)

def set_paragraph_font(paragraph, bold=False, size=12):
    """
    设置段落的字体
    """
    for run in paragraph.runs:
        run.font.name = 'Times New Roman'
        run._element.rPr.rFonts.set(qn('w:eastAsia'), u'宋体')
        run.font.size = Pt(size)
        run.font.bold = bold

def generate_resume_docx(filename, resume_data):
    """
    生成单个简历Word文档
    
    Args:
        filename (str): 保存的文件名
        resume_data (dict): 简历数据
    """
    doc = Document()
    
    # 设置文档字体
    set_document_font(doc)
    
    # 添加标题
    title = doc.add_heading('个人简历', 0)
    title.alignment = WD_ALIGN_PARAGRAPH.CENTER
    set_paragraph_font(title, bold=True, size=16)
    
    # 添加个人信息表格
    doc.add_heading('基本信息', level=1)
    table = doc.add_table(rows=6, cols=4)
    table.style = 'Table Grid'
    
    # 填充基本信息表格
    info_cells = [
        ("姓名", resume_data['name']),
        ("性别", resume_data['gender']),
        ("年龄", str(resume_data['age'])),
        ("联系电话", resume_data['phone']),
        ("邮箱", resume_data['email']),
        ("现居地", resume_data['address'])
    ]
    
    for i, (label, value) in enumerate(info_cells):
        table.cell(i, 0).text = label
        table.cell(i, 1).text = value
        table.cell(i, 2).text = "求职意向" if i == 0 else ""
        table.cell(i, 3).text = resume_data['job_intention'] if i == 0 else ""
        
        # 设置表格单元格字体
        for j in range(4):
            for paragraph in table.cell(i, j).paragraphs:
                set_paragraph_font(paragraph, bold=(j == 0 or j == 2))
    
    # 教育背景
    doc.add_heading('教育背景', level=1)
    edu_table = doc.add_table(rows=2, cols=4)
    edu_table.style = 'Table Grid'
    
    # 表头
    headers = ["时间", "学校", "专业", "学历"]
    for i, header in enumerate(headers):
        edu_table.cell(0, i).text = header
        for paragraph in edu_table.cell(0, i).paragraphs:
            set_paragraph_font(paragraph, bold=True)
    
    # 教育信息
    edu_table.cell(1, 0).text = resume_data['education']['period']
    edu_table.cell(1, 1).text = resume_data['education']['school']
    edu_table.cell(1, 2).text = resume_data['education']['major']
    edu_table.cell(1, 3).text = resume_data['education']['degree']
    
    # 设置教育信息行的字体
    for i in range(4):
        for paragraph in edu_table.cell(1, i).paragraphs:
            set_paragraph_font(paragraph)
    
    # 工作经历
    doc.add_heading('工作经历', level=1)
    for exp in resume_data['work_experience']:
        p = doc.add_paragraph()
        company_run = p.add_run(f"{exp['company']} | ")
        company_run.bold = True
        position_run = p.add_run(f"{exp['position']} | ")
        position_run.bold = True
        period_run = p.add_run(exp['period'])
        period_run.bold = True
        
        set_paragraph_font(p, bold=True)
        
        desc_para = doc.add_paragraph(exp['description'])
        set_paragraph_font(desc_para)
    
    # 技能特长
    doc.add_heading('技能特长', level=1)
    skills_para = doc.add_paragraph()
    for skill in resume_data['skills']:
        skills_para.add_run(f"• {skill}\n")
    set_paragraph_font(skills_para)
    
    # 自我评价
    doc.add_heading('自我评价', level=1)
    self_eval_para = doc.add_paragraph(resume_data['self_evaluation'])
    set_paragraph_font(self_eval_para)
    
    # 保存文档
    doc.save(filename)
    print(f"已生成简历: {filename}")

def generate_sample_resumes(num=10):
    """
    生成指定数量的模拟简历
    
    Args:
        num (int): 简历数量，默认为10
    """
    fake = Faker('zh_CN')
    
    # 创建保存目录 - 使用os.path.join处理路径
    resume_dir = os.path.join('resumes')
    os.makedirs(resume_dir, exist_ok=True)
    
    # 职位列表
    jobs = ['软件工程师', '数据分析师', '产品经理', 'UI设计师', '市场营销', '人力资源', '财务专员', '运营专员']
    
    # 技能列表
    skill_sets = {
        '软件工程师': ['Python', 'Java', 'SQL', 'Linux', 'Git', 'Docker'],
        '数据分析师': ['Python', 'SQL', 'Excel', 'Tableau', '统计学', '机器学习'],
        '产品经理': ['Axure', 'Visio', '项目管理', '需求分析', '用户研究', 'PRD编写'],
        'UI设计师': ['Photoshop', 'Sketch', 'Figma', 'Illustrator', '用户体验设计', '交互设计'],
        '市场营销': ['市场分析', '营销策划', '社交媒体运营', '内容创作', '数据分析', '品牌管理'],
        '人力资源': ['招聘', '培训', '绩效管理', '员工关系', 'HR系统', '劳动法'],
        '财务专员': ['会计', '财务报表', '税务', '成本控制', '财务分析', 'ERP系统'],
        '运营专员': ['内容运营', '用户运营', '活动策划', '数据分析', '社交媒体', 'SEO/SEM']
    }
    
    # 生成简历
    for i in range(num):
        # 随机选择一个职位
        job = random.choice(jobs)
        
        # 生成简历数据
        resume_data = {
            'name': fake.name(),
            'gender': random.choice(['男', '女']),
            'age': random.randint(22, 35),
            'phone': fake.phone_number(),
            'email': fake.email(),
            'address': fake.city(),
            'job_intention': job,
            'education': {
                'period': f"{fake.year()}-{fake.year()}",
                'school': fake.company() + "大学",
                'major': fake.job() + "专业",
                'degree': random.choice(['本科', '硕士', '博士'])
            },
            'work_experience': [],
            'skills': random.sample(skill_sets[job], random.randint(4, 6)),
            'self_evaluation': fake.paragraph(nb_sentences=3)
        }
        
        # 生成工作经历
        num_experiences = random.randint(1, 3)
        for j in range(num_experiences):
            start_year = 2020 - j * 2
            resume_data['work_experience'].append({
                'company': fake.company(),
                'position': job,
                'period': f"{start_year}-{start_year+2}",
                'description': fake.paragraph(nb_sentences=2)
            })
        
        # 生成文档 - 使用os.path.join处理路径
        safe_name = resume_data['name'].replace(' ', '_')
        filename = os.path.join(resume_dir, f"简历_{safe_name}_{job}.docx")
        generate_resume_docx(filename, resume_data)

if __name__ == "__main__":
    print("开始生成模拟简历...")
    generate_sample_resumes(10)
    print("简历生成完成！")

import os
import re
import csv
from docx import Document

def extract_resume_info(filepath):
    """
    从Word简历中提取信息
    
    Args:
        filepath (str): Word文档路径
        
    Returns:
        dict: 提取的简历信息
    """
    try:
        doc = Document(filepath)
        resume_data = {
            'filename': os.path.basename(filepath),
            'name': '',
            'gender': '',
            'age': '',
            'phone': '',
            'email': '',
            'address': '',
            'job_intention': '',
            'education_period': '',
            'education_school': '',
            'education_major': '',
            'education_degree': '',
            'work_experience': '',
            'skills': '',
            'self_evaluation': ''
        }
        
        # 提取基本信息
        basic_info_extracted = False
        education_extracted = False
        in_work_experience = False
        in_skills = False
        in_self_evaluation = False
        
        work_experiences = []
        skills_list = []
        
        for i, paragraph in enumerate(doc.paragraphs):
            text = paragraph.text.strip()
            
            # 跳过空段落
            if not text:
                continue
                
            # 提取基本信息表格
            if text == '基本信息' and not basic_info_extracted:
                # 查找所有表格
                for table in doc.tables:
                    # 检查表格是否包含基本信息
                    try:
                        if table.cell(0, 0).text == '姓名':
                            resume_data['name'] = table.cell(0, 1).text
                            resume_data['gender'] = table.cell(1, 1).text
                            resume_data['age'] = table.cell(2, 1).text
                            resume_data['phone'] = table.cell(3, 1).text
                            resume_data['email'] = table.cell(4, 1).text
                            resume_data['address'] = table.cell(5, 1).text
                            resume_data['job_intention'] = table.cell(0, 3).text
                            basic_info_extracted = True
                            break
                    except:
                        continue
                
                if not basic_info_extracted:
                    # 如果没有找到表格，尝试从段落中提取
                    extract_basic_info_from_text(doc, resume_data)
                    basic_info_extracted = True
            
            # 提取教育背景
            elif text == '教育背景' and not education_extracted:
                # 查找教育背景表格
                for table in doc.tables:
                    try:
                        if table.cell(0, 0).text == '时间' and '学校' in table.cell(0, 1).text:
                            resume_data['education_period'] = table.cell(1, 0).text
                            resume_data['education_school'] = table.cell(1, 1).text
                            resume_data['education_major'] = table.cell(1, 2).text
                            resume_data['education_degree'] = table.cell(1, 3).text
                            education_extracted = True
                            break
                    except:
                        continue
            
            # 提取工作经历
            elif text == '工作经历':
                in_work_experience = True
                continue
            elif in_work_experience and text and not text.startswith('技能特长') and not text.startswith('自我评价'):
                # 检查是否是工作经历标题（包含公司、职位、时间，用 | 分隔）
                if ' | ' in text:
                    parts = text.split(' | ')
                    if len(parts) >= 3:
                        # 提取公司、职位和时间
                        company = parts[0].strip()
                        position = parts[1].strip()
                        period = parts[2].strip()
                        
                        work_experiences.append({
                            'company': company,
                            'position': position,
                            'period': period
                        })
                # 否则，可能是工作描述，但我们主要关注标题信息
            
            # 提取技能特长
            elif text == '技能特长':
                in_skills = True
                in_work_experience = False
                continue
            elif in_skills and text and not text.startswith('自我评价'):
                # 技能特长部分是以 • 开头的列表项
                lines = text.split('\n')
                for line in lines:
                    line = line.strip()
                    if line.startswith('•'):
                        skill = line[1:].strip()  # 移除 • 符号
                        if skill:
                            skills_list.append(skill)
            
            # 提取自我评价
            elif text == '自我评价':
                in_self_evaluation = True
                in_skills = False
                continue
            elif in_self_evaluation and text:
                resume_data['self_evaluation'] = text
                in_self_evaluation = False
        
        # 如果没有提取到基本信息，尝试其他方法
        if not basic_info_extracted:
            extract_basic_info_from_text(doc, resume_data)
        
        # 将工作经历和技能列表转换为字符串
        if work_experiences:
            work_exp_str = " | ".join([
                f"{exp['company']} ({exp['position']}, {exp['period']})" 
                for exp in work_experiences
            ])
            resume_data['work_experience'] = work_exp_str
        
        if skills_list:
            resume_data['skills'] = "; ".join(skills_list)
        
        # 清理数据
        clean_resume_data(resume_data)
        
        return resume_data
        
    except Exception as e:
        print(f"提取简历信息时出错 {filepath}: {e}")
        return None

def extract_basic_info_from_text(doc, resume_data):
    """
    从文档文本中提取基本信息
    """
    for paragraph in doc.paragraphs:
        text = paragraph.text
        
        # 提取姓名
        if not resume_data['name'] and len(text) <= 4 and not any(keyword in text for keyword in ['基本信息', '教育背景', '工作经历']):
            resume_data['name'] = text
        
        # 提取电话
        phone_match = re.search(r'1[3-9]\d{9}', text)
        if phone_match and not resume_data['phone']:
            resume_data['phone'] = phone_match.group()
        
        # 提取邮箱
        email_match = re.search(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', text)
        if email_match and not resume_data['email']:
            resume_data['email'] = email_match.group()

def clean_resume_data(resume_data):
    """
    清理提取的简历数据
    """
    # 清理年龄，只保留数字
    if resume_data['age']:
        age_match = re.search(r'\d+', resume_data['age'])
        if age_match:
            resume_data['age'] = age_match.group()

def save_to_csv(resumes, csv_filename='resumes_data.csv'):
    """
    将简历数据保存为CSV文件
    
    Args:
        resumes (list): 简历数据列表
        csv_filename (str): CSV文件名
    """
    if not resumes:
        print("没有简历数据可保存")
        return
    
    # 定义CSV列名
    fieldnames = [
        'filename', 'name', 'gender', 'age', 'phone', 'email', 'address', 
        'job_intention', 'education_period', 'education_school', 'education_major', 
        'education_degree', 'work_experience', 'skills', 'self_evaluation'
    ]
    
    with open(csv_filename, 'w', newline='', encoding='utf-8-sig') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        writer.writeheader()
        
        for resume in resumes:
            writer.writerow(resume)
    
    print(f"简历数据已保存到: {csv_filename}")

def analyze_resumes(directory='resumes'):
    """
    分析目录中的所有简历
    
    Args:
        directory (str): 简历目录路径
    """
    if not os.path.exists(directory):
        print(f"目录不存在: {directory}")
        return
    
    resumes = []
    
    # 遍历目录中的所有Word文档
    for filename in os.listdir(directory):
        if filename.endswith('.docx'):
            filepath = os.path.join(directory, filename)
            print(f"正在处理: {filename}")
            
            resume_data = extract_resume_info(filepath)
            if resume_data:
                resumes.append(resume_data)
    
    # 输出分析结果
    print("\n" + "="*50)
    print("简历分析结果")
    print("="*50)
    
    # 统计基本信息
    print(f"共处理简历: {len(resumes)} 份")
    
    if not resumes:
        return
    
    # 按职位意向统计
    job_counts = {}
    for resume in resumes:
        job = resume.get('job_intention', '未知')
        job_counts[job] = job_counts.get(job, 0) + 1
    
    print("\n职位意向分布:")
    for job, count in job_counts.items():
        print(f"  {job}: {count} 人")
    
    # 平均年龄
    ages = []
    for resume in resumes:
        if resume['age'] and resume['age'].isdigit():
            ages.append(int(resume['age']))
    if ages:
        avg_age = sum(ages) / len(ages)
        print(f"\n平均年龄: {avg_age:.1f} 岁")
    
    # 学历分布
    degree_counts = {}
    for resume in resumes:
        degree = resume.get('education_degree', '未知')
        degree_counts[degree] = degree_counts.get(degree, 0) + 1
    
    print("\n学历分布:")
    for degree, count in degree_counts.items():
        print(f"  {degree}: {count} 人")
    
    # 工作经历统计
    work_exp_counts = {}
    for resume in resumes:
        work_exp = resume.get('work_experience', '')
        if work_exp:
            # 计算工作经历数量（通过 | 分隔符）
            count = work_exp.count('|') + 1
            work_exp_counts[count] = work_exp_counts.get(count, 0) + 1
    
    print("\n工作经历数量分布:")
    for count, freq in sorted(work_exp_counts.items()):
        print(f"  {count} 段经历: {freq} 人")
    
    # 技能统计
    skill_counts = {}
    for resume in resumes:
        skills_str = resume.get('skills', '')
        if skills_str:
            # 按分号分隔技能
            skills = [skill.strip() for skill in skills_str.split(';') if skill.strip()]
            for skill in skills:
                skill_counts[skill] = skill_counts.get(skill, 0) + 1
    
    # 取前10个最常用技能
    top_skills = sorted(skill_counts.items(), key=lambda x: x[1], reverse=True)[:10]
    print("\n最常用技能(前10):")
    for skill, count in top_skills:
        print(f"  {skill}: {count} 次")
    
    # 保存详细数据到CSV文件
    save_to_csv(resumes, 'resumes_data.csv')
    
    print(f"\n详细数据已保存到: resumes_data.csv")

if __name__ == "__main__":
    print("开始提取简历信息...")
    analyze_resumes()
    print("简历分析完成！")

开始提取简历信息...
正在处理: 简历_刘桂花_数据分析师.docx
正在处理: 简历_吴婷_数据分析师.docx
正在处理: 简历_吴建平_UI设计师.docx
正在处理: 简历_孙婷_软件工程师.docx
正在处理: 简历_张丽丽_市场营销.docx
正在处理: 简历_李建军_运营专员.docx
正在处理: 简历_欧宁_数据分析师.docx
正在处理: 简历_王利_运营专员.docx
正在处理: 简历_罗欢_运营专员.docx
正在处理: 简历_韩岩_财务专员.docx

==================================================
简历分析结果
==================================================
共处理简历: 10 份

职位意向分布:
  数据分析师: 3 人
  UI设计师: 1 人
  软件工程师: 1 人
  市场营销: 1 人
  运营专员: 3 人
  财务专员: 1 人

平均年龄: 28.3 岁

学历分布:
  博士: 4 人
  硕士: 3 人
  本科: 3 人

工作经历数量分布:
  1 段经历: 2 人
  2 段经历: 4 人
  3 段经历: 4 人

最常用技能(前10):
  数据分析: 4 次
  Excel: 3 次
  机器学习: 3 次
  SQL: 3 次
  Python: 3 次
  用户运营: 3 次
  活动策划: 3 次
  SEO/SEM: 3 次
  Tableau: 2 次
  统计学: 2 次
简历数据已保存到: resumes_data.csv

详细数据已保存到: resumes_data.csv
简历分析完成！

writer = csv.DictWriter(csv文件流, fieldnames=列名列表)
writer.writeheader()

{
    'company': company,
    'position': position,
    'period': period
}