99 lines
3.4 KiB
Python
99 lines
3.4 KiB
Python
|
import os
|
|||
|
|
import docx
|
|||
|
|
from spire.doc import *
|
|||
|
|
from spire.doc.common import *
|
|||
|
|
|
|||
|
|
|
|||
|
|
def split_and_clean_docx(input_file, output_folder):
|
|||
|
|
"""
|
|||
|
|
拆分指定的Word文档为多个节，并去除文档中的水印。
|
|||
|
|
|
|||
|
|
参数:
|
|||
|
|
input_file (str): 需要拆分的源Word文档路径。
|
|||
|
|
output_folder (str): 拆分后的文档输出目录。
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
# 检查输出目录是否存在，如果不存在则创建
|
|||
|
|
if not os.path.exists(output_folder):
|
|||
|
|
os.makedirs(output_folder)
|
|||
|
|
|
|||
|
|
# 加载源文档
|
|||
|
|
with Document() as document:
|
|||
|
|
document.LoadFromFile(input_file)
|
|||
|
|
|
|||
|
|
# 遍历文档中的所有节
|
|||
|
|
for sec_index in range(document.Sections.Count):
|
|||
|
|
# 访问当前节
|
|||
|
|
section = document.Sections[sec_index]
|
|||
|
|
|
|||
|
|
# 为当前节创建一个新文档
|
|||
|
|
with Document() as new_document:
|
|||
|
|
# 将当前节复制到新文档
|
|||
|
|
new_document.Sections.Add(section.Clone())
|
|||
|
|
|
|||
|
|
# 复制源文档的主题和样式到新文档以确保格式一致
|
|||
|
|
document.CloneThemesTo(new_document)
|
|||
|
|
document.CloneDefaultStyleTo(new_document)
|
|||
|
|
|
|||
|
|
# 将新文档保存为单独的文件
|
|||
|
|
output_file = os.path.join(output_folder, f"节{sec_index + 1}.docx")
|
|||
|
|
new_document.SaveToFile(output_file, FileFormat.Docx2016)
|
|||
|
|
|
|||
|
|
# 去除水印
|
|||
|
|
remove_watermark(output_folder)
|
|||
|
|
|
|||
|
|
print("文档拆分并去除水印完成！")
|
|||
|
|
|
|||
|
|
|
|||
|
|
def remove_watermark(output_folder):
|
|||
|
|
"""
|
|||
|
|
去除指定目录下所有docx文件中的水印。
|
|||
|
|
|
|||
|
|
参数:
|
|||
|
|
output_folder (str): 需要去除水印的文档所在的文件夹。
|
|||
|
|
"""
|
|||
|
|
bookmark_name = "Evaluation Warning: The document was created with Spire.Doc for Python."
|
|||
|
|
|
|||
|
|
for file_name in os.listdir(output_folder):
|
|||
|
|
if file_name.endswith(".docx"):
|
|||
|
|
doc_path = os.path.join(output_folder, file_name)
|
|||
|
|
doc = docx.Document(doc_path)
|
|||
|
|
# 查找并替换水印内容
|
|||
|
|
for paragraph in doc.paragraphs:
|
|||
|
|
if bookmark_name in paragraph.text:
|
|||
|
|
# 替换水印文本为空
|
|||
|
|
inline = paragraph.runs
|
|||
|
|
for i in range(len(inline)):
|
|||
|
|
if bookmark_name in inline[i].text:
|
|||
|
|
inline[i].text = inline[i].text.replace(bookmark_name, "")
|
|||
|
|
break
|
|||
|
|
# 保存文档
|
|||
|
|
doc.save(doc_path)
|
|||
|
|
|
|||
|
|
import os
|
|||
|
|
|
|||
|
|
def test_split_and_clean_docx():
|
|||
|
|
"""
|
|||
|
|
测试文档拆分和水印去除功能。
|
|||
|
|
"""
|
|||
|
|
input_file = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfilesdocx\\2-招标文件.docx" # 替换为你的源文档路径
|
|||
|
|
output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\zboutpub" # 指定输出文件夹
|
|||
|
|
|
|||
|
|
# 执行拆分和去除水印
|
|||
|
|
split_and_clean_docx(input_file, output_folder)
|
|||
|
|
|
|||
|
|
# 验证输出文件是否生成
|
|||
|
|
if os.path.exists(output_folder):
|
|||
|
|
print("测试通过: 输出文件夹已生成。")
|
|||
|
|
output_files = os.listdir(output_folder)
|
|||
|
|
if output_files:
|
|||
|
|
print(f"测试通过: 生成了 {len(output_files)} 个文档。")
|
|||
|
|
else:
|
|||
|
|
print("测试失败: 没有生成任何文档。")
|
|||
|
|
else:
|
|||
|
|
print("测试失败: 输出文件夹未生成。")
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
test_split_and_clean_docx()
|