Python实现精准提取Word文档中的文本与表格

pip install spire.doc

from spire.doc import *
from spire.doc.common import *

# 创建 Document 对象并加载 Word 文件
doc = Document()
doc.LoadFromFile("input.docx")

# 获取整个文档的纯文本内容
full_text = doc.GetText()

# 将文本写入 txt 文件
with open("output.txt", "w", encoding="utf-8") as file:
    file.write(full_text)

doc.Close()
print("文本提取完成，已保存至 output.txt")

from spire.doc import *
from spire.doc.common import *
import os
# 创建输出文件夹
output_dir = "output/Tables"
os.makedirs(output_dir, exist_ok=True)
# 加载 Word 文档
doc = Document()
doc.LoadFromFile("Sample.docx")
# 遍历所有节
for section_idx in range(doc.Sections.Count):
    section = doc.Sections.get_Item(section_idx)
    tables = section.Tables
    for table_idx in range(tables.Count):
        table = tables.get_Item(table_idx)
        table_data = ""
        # 遍历表格所有行和单元格
        for row_idx in range(table.Rows.Count):
            row = table.Rows.get_Item(row_idx)
            for col_idx in range(row.Cells.Count):
                cell = row.Cells.get_Item(col_idx)
                # 收集单元格内所有段落文本
                cell_text = ""
                for para_idx in range(cell.Paragraphs.Count):
                    cell_text += cell.Paragraphs.get_Item(para_idx).Text + " "
                table_data += cell_text.strip()
                # 列之间用制表符分隔
                if col_idx < row.Cells.Count - 1:
                    table_data += "\t"
            table_data += "\n"   # 行结束
        # 保存当前表格数据
        output_path = f"{output_dir}/WordTable_{section_idx+1}_{table_idx+1}.txt"
        with open(output_path, "w", encoding="utf-8") as f:
            f.write(table_data)
        print(f"已保存：{output_path}")
doc.Close()