Python案例怎么解析Word文档？

wen python案例 2026-06-09 9

本文目录导读：

Python案例怎么解析Word文档？

安装所需库
基础用法：读取Word文档
完整解析案例
高级应用场景
注意事项
替代方案

我来详细介绍如何使用Python解析Word文档,主要使用 python-docx 库，它支持 .docx 格式。

安装所需库

pip install python-docx

基础用法：读取Word文档

1 读取段落文本

from docx import Document
# 打开Word文档
doc = Document('example.docx')
# 读取所有段落
for i, paragraph in enumerate(doc.paragraphs):
    print(f"段落 {i+1}: {paragraph.text}")

2 读取表格数据

from docx import Document
doc = Document('example.docx')
# 遍历所有表格
for table_idx, table in enumerate(doc.tables):
    print(f"\n=== 表格 {table_idx+1} ===")
    # 遍历行
    for row_idx, row in enumerate(table.rows):
        cells = [cell.text for cell in row.cells]
        print(f"行 {row_idx+1}: {cells}")

完整解析案例

1 综合解析Word文档

from docx import Document
from docx.shared import Pt, Inches
from docx.enum.text import WD_ALIGN_PARAGRAPH
import json
class WordParser:
    def __init__(self, file_path):
        self.doc = Document(file_path)
        self.result = {
            'metadata': {},
            'paragraphs': [],
            'tables': [],
            'images': []
        }
    def parse_metadata(self):
        """解析文档属性"""
        props = self.doc.core_properties
        self.result['metadata'] = {
            'title': props.title,
            'author': props.author,
            'created': str(props.created),
            'modified': str(props.modified),
            'last_modified_by': props.last_modified_by
        }
    def parse_paragraphs(self):
        """解析段落"""
        for para in self.doc.paragraphs:
            if para.text.strip():  # 忽略空段落
                # 获取段落格式
                format_info = {
                    'alignment': str(para.alignment),
                    'style': para.style.name if para.style else None
                }
                # 获取文本和格式
                runs_info = []
                for run in para.runs:
                    run_data = {
                        'text': run.text,
                        'bold': run.bold,
                        'italic': run.italic,
                        'font_size': str(run.font.size) if run.font.size else None,
                        'font_name': run.font.name,
                        'color': str(run.font.color.rgb) if run.font.color and run.font.color.rgb else None
                    }
                    runs_info.append(run_data)
                self.result['paragraphs'].append({
                    'text': para.text,
                    'format': format_info,
                    'runs': runs_info
                })
    def parse_tables(self):
        """解析表格"""
        for table in self.doc.tables:
            table_data = {
                'rows': len(table.rows),
                'columns': len(table.columns),
                'data': []
            }
            for row in table.rows:
                row_data = []
                for cell in row.cells:
                    cell_data = {
                        'text': cell.text,
                        'paragraphs': [p.text for p in cell.paragraphs if p.text.strip()]
                    }
                    row_data.append(cell_data)
                table_data['data'].append(row_data)
            self.result['tables'].append(table_data)
    def parse_images(self):
        """解析图片（内联图片）"""
        for rel in self.doc.part.rels.values():
            if "image" in rel.reltype:
                image = rel.target_part
                image_data = {
                    'file_name': image.partname,
                    'content_type': image.content_type,
                    'blob': image.blob
                }
                self.result['images'].append(image_data)
    def parse_all(self):
        """执行全面解析"""
        self.parse_metadata()
        self.parse_paragraphs()
        self.parse_tables()
        self.parse_images()
        return self.result
    def export_to_json(self, output_path='output.json'):
        """导出为JSON"""
        with open(output_path, 'w', encoding='utf-8') as f:
            json.dump(self.result, f, ensure_ascii=False, indent=2)
# 使用示例
parser = WordParser('document.docx')
result = parser.parse_all()
print(f"文档标题: {result['metadata'].get('title')}")
print(f"段落数量: {len(result['paragraphs'])}")
print(f"表格数量: {len(result['tables'])}")
print(f"图片数量: {len(result['images'])}")
# 导出为JSON
parser.export_to_json('document_parsed.json')

2 按样式提取内容

from docx import Document
def extract_by_style(doc_path, style_name):
    """提取指定样式的段落"""
    doc = Document(doc_path)
    result = []
    for para in doc.paragraphs:
        if para.style and para.style.name == style_name:
            result.append(para.text)
    return result
def extract_headings(doc_path):
    """提取所有标题"""
    doc = Document(doc_path)
    headings = []
    for para in doc.paragraphs:
        if para.style and para.style.name.startswith('Heading'):
            headings.append({
                'level': para.style.name,
                'text': para.text
            })
    return headings
# 使用示例
doc_path = 'document.docx'
headings = extract_headings(doc_path)
for h in headings:
    print(f"{h['level']}: {h['text']}")
# 提取特定样式
normal_texts = extract_by_style(doc_path, 'Normal')

3 处理带格式的文本

from docx import Document
def extract_formatted_text(doc_path):
    """提取文本及格式信息"""
    doc = Document(doc_path)
    formatted_content = []
    for para in doc.paragraphs:
        if not para.text.strip():
            continue
        para_data = {
            'text': para.text,
            'formatted_parts': []
        }
        for run in para.runs:
            if run.text.strip():
                format_info = {
                    'text': run.text,
                    'bold': run.bold,
                    'italic': run.italic,
                    'underline': run.underline,
                    'font_size': run.font.size,
                    'font_name': run.font.name
                }
                para_data['formatted_parts'].append(format_info)
        formatted_content.append(para_data)
    return formatted_content
# 使用示例
content = extract_formatted_text('document.docx')
for para in content[:5]:  # 只显示前5个段落
    print(f"段落文本: {para['text'][:50]}...")
    for part in para['formatted_parts'][:2]:
        if part['bold']:
            print(f"  加粗文本: {part['text']}")

高级应用场景

1 合并多个Word文档

from docx import Document
from docx.oxml import parse_xml
import os
def merge_word_documents(file_paths, output_path):
    """合并多个Word文档"""
    if not file_paths:
        return
    # 使用第一个文档作为基础
    merged_doc = Document(file_paths[0])
    for file_path in file_paths[1:]:
        doc = Document(file_path)
        # 合并段落
        for para in doc.paragraphs:
            merged_doc.add_paragraph(para.text, style=para.style)
        # 合并表格
        for table in doc.tables:
            # 添加新表格
            new_table = merged_doc.add_table(
                rows=len(table.rows),
                cols=len(table.columns)
            )
            for i, row in enumerate(table.rows):
                for j, cell in enumerate(row.cells):
                    new_table.rows[i].cells[j].text = cell.text
    merged_doc.save(output_path)
    print(f"合并完成，保存到: {output_path}")
# 使用示例
files = ['doc1.docx', 'doc2.docx', 'doc3.docx']
merge_word_documents(files, 'merged.docx')

2 查找替换功能

from docx import Document
def find_and_replace(doc_path, search_text, replace_text, output_path=None):
    """查找替换功能"""
    doc = Document(doc_path)
    # 在段落中替换
    for para in doc.paragraphs:
        for run in para.runs:
            if search_text in run.text:
                run.text = run.text.replace(search_text, replace_text)
    # 在表格中替换
    for table in doc.tables:
        for row in table.rows:
            for cell in row.cells:
                for para in cell.paragraphs:
                    for run in para.runs:
                        if search_text in run.text:
                            run.text = run.text.replace(search_text, replace_text)
    # 保存
    output_path = output_path or doc_path
    doc.save(output_path)
    print(f"替换完成，保存到: {output_path}")
# 使用示例
find_and_replace('document.docx', '旧文本', '新文本', 'document_updated.docx')