使用Python实现批量删除Word文档空白行

pip install Spire.Doc

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

# 创建 Document 类的对象
doc = Document()

# 加载 Word 文档
doc.LoadFromFile("测试文档.docx")

# 遍历文档中的每一个节 (Section)
for i in range(doc.Sections.Count):
    section = doc.Sections.get_Item(i)
    j = 0
    # 遍历该节下的所有子对象
    while j < section.Body.ChildObjects.Count:
        # 判断子对象是否为段落 (Paragraph)
        if section.Body.ChildObjects[j].DocumentObjectType == DocumentObjectType.Paragraph:
            objItem = section.Body.ChildObjects[j]
            
            # 确保对象是 Paragraph 实例
            if isinstance(objItem, Paragraph):
                paraObj = Paragraph(objItem)
                
                # 检查段落文本长度是否为 0（即空白行）
                if len(paraObj.Text.strip()) == 0:
                    # 如果为空，从该节的 Body 中移除该对象
                    section.Body.ChildObjects.Remove(objItem)
                    # 移除后索引不递增，继续检查当前位置的新对象
                    j -= 1
        j += 1

# 保存文档
doc.SaveToFile("output/已清理文档.docx")
# 释放资源
doc.Close()

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

def remove_blank_lines(input_file, output_file):
    # 1. 初始化 Document 对象
    doc = Document()

    # 2. 加载文档
    doc.LoadFromFile(input_file)

    # 3. 执行删除逻辑
    for i in range(doc.Sections.Count):
        section = doc.Sections.get_Item(i)
        j = 0
        while j < section.Body.ChildObjects.Count:
            # 识别段落类型
            if section.Body.ChildObjects[j].DocumentObjectType == DocumentObjectType.Paragraph:
                objItem = section.Body.ChildObjects[j]
                
                if isinstance(objItem, Paragraph):
                    paraObj = Paragraph(objItem)
                    # 判断是否为空白行（包含纯空格的情况）
                    if len(paraObj.Text.strip()) == 0:
                        section.Body.ChildObjects.Remove(objItem)
                        j -= 1
            j += 1

    # 4. 保存并关闭
    doc.SaveToFile(output_file)
    doc.Close()
    print(f"处理完成！已保存至：{output_file}")

# 调用函数
if __name__ == "__main__":
    remove_blank_lines("Sample.docx", "RemoveBlankLines_Result.docx")

import os
from spire.doc import *

input_folder = "./docs"
output_folder = "./output"

# 遍历文件夹中的所有 Word 文件
for filename in os.listdir(input_folder):
    if filename.endswith(".docx") or filename.endswith(".doc"):
        input_path = os.path.join(input_folder, filename)
        output_path = os.path.join(output_folder, filename)

        doc = Document()
        doc.LoadFromFile(input_path)

        for i in range(doc.Sections.Count):
            section = doc.Sections.get_Item(i)
            j = 0
            while j < section.Body.ChildObjects.Count:
                if section.Body.ChildObjects[j].DocumentObjectType == DocumentObjectType.Paragraph:
                    objItem = section.Body.ChildObjects[j]
                    if isinstance(objItem, Paragraph):
                        paraObj = Paragraph(objItem)
                        if len(paraObj.Text.strip()) == 0:
                            section.Body.ChildObjects.Remove(objItem)
                            j -= 1
                j += 1

        doc.SaveToFile(output_path)
        doc.Close()
        print(f"{filename} 处理完成！")