Python实现批量提取word文件中文本框内容

pip install python-docx

pip install lxml

from docx import Document
from lxml import etree
import zipfile
import os
 
# 加载.docx文件
source_docx = 'example.docx'
document = Document(source_docx)
 
# 解压.docx文件以访问其XML内容
with zipfile.ZipFile(source_docx, 'r') as docx_zip:
 xml_content = docx_zip.read('word/document.xml')
 
# 解析XML内容
xml_tree = etree.XML(xml_content)
 
# 定义命名空间
namespaces = {
 'w': 'http://schemas.openxmlformats.org/wordprocessingml/2006/main',
 'v': 'urn:schemas-microsoft-com:vml'
}
 
# 创建新文档
output_docx = 'output_with_textboxes.docx'
new_document = Document()
 
# 已提取段落的文本集合
extracted_texts = set()
 
# 搜索文本框中的文本
textboxes = xml_tree.findall('.//w:txbxContent', namespaces)
for textbox in textboxes:
 paragraphs = textbox.findall('.//w:p', namespaces)
 for paragraph in paragraphs:
 texts = paragraph.findall('.//w:t', namespaces)
 paragraph_text = ''.join([text.text for text in texts if text.text])
 # 检查段落文本是否已经被提取
 if paragraph_text and paragraph_text not in extracted_texts:
 new_document.add_paragraph(paragraph_text)
 # 将提取的段落文本添加到集合中，以避免重复
 extracted_texts.add(paragraph_text)
 
# 保存新文档
new_document.save(output_docx)
 
print(f'文本框内容已被提取到 {output_docx}')

Sub ExtractTextBoxContentAndSaveInCurrentDirectory()
 Dim srcDoc As Document
 Dim destDoc As Document
 Dim shape As shape
 Dim textBoxText As String
 Dim para As Paragraph
 Dim destPath As String
 
 ' 当前活动文档作为源文档
 Set srcDoc = ActiveDocument
 ' 创建一个新文档来存储提取的文本
 Set destDoc = Documents.Add
 
 ' 遍历源文档中的所有形状
 For Each shape In srcDoc.Shapes
 ' 检查形状是否是文本框
 If shape.Type = msoTextBox Then
 ' 获取文本框中的文本
 textBoxText = shape.TextFrame.TextRange.Text
 ' 将文本写入到目标文档
 Set para = destDoc.Content.Paragraphs.Add
 para.Range.Text = textBoxText & vbNewLine
 End If
 Next shape
 
 ' 构建目标文件的完整路径
 destPath = srcDoc.Path & "\ExtractedTextBoxContent.docx"
 
 ' 保存目标文档到当前文档所在目录
 destDoc.SaveAs2 FileName:=destPath
 
 ' 显示保存成功的消息
 MsgBox "文本框内容已提取到：" & destPath, vbInformation, "完成"
 
 ' 清理
 Set srcDoc = Nothing
 Set destDoc = Nothing
End Sub