使用python的zipfile模块进行word批量生成
- 平台：windows10
- 解释器：python3.7
- 需求：一包含目标数据的excel文档，需要将其中的每一行数据的对应内容替换到指定word中，并逐一保存
使用zipfile模块
from shutil import rmtree
import zipfile
from copy import deepcopy
from pathlib import Path
from win32com import client as wc # pip install pypiwin32
import pandas as pd
# doc文档不包含所需xml文件，使用win32com转存为docx文档
def doctransform2docx(doc_path):
docx_path = doc_path + 'x'
suffix = doc_path.split('.')[1]
assert 'doc' in suffix, '传入的不是word文档，请重新输入！'
if suffix == 'docx':
return Path(doc_path)
word = wc.Dispatch('Word.Application')
doc = word.Documents.Open(doc_path)
doc.SaveAs2(docx_path, 16) # docx为16
doc.Close()
word.Quit()
return Path(docx_path)
# docx文档解压
def docx_unzip(docx_path):
docx_path = Path(docx_path) if isinstance(docx_path, str) else docx_path
upzip_path = docx_path.with_name(docx_path.stem)
with zipfile.ZipFile(docx_path, 'r') as f:
for file in f.namelist():
f.extract(file, path=upzip_path)
xml_path = upzip_path.joinpath('word/document.xml')
with xml_path.open(encoding='utf-8') as f:
xml_file = f.read()
return upzip_path, xml_path, xml_file
# 讲文件夹中的所有文件压缩成docx文档
def docx_zipped(docx_path, zipped_path):
docx_path = Path(docx_path) if isinstance(docx_path, str) else docx_path
with zipfile.ZipFile(zipped_path, 'w', zipfile.zlib.DEFLATED) as f:
for file in docx_path.glob('**/*.*'):
f.write(file, file.as_posix().replace(docx_path.as_posix() + '/', ''))
# 删除生成的解压文件夹
def remove_folder(path):
path = Path(path) if isinstance(path, str) else path
if path.exists():
rmtree(path)
else:
raise "系统找不到指定的文件"
# 替换docx中的特定字符，重新保存document.xml至需要压缩的目录下
def replace_docx(name, values, xml_file, xml_path, unzip_path, path_name='Company'):
xml_path = Path(xml_path) if isinstance(xml_path, str) else xml_path
xml_file_copy = deepcopy(xml_file) # 深复制xml内容
for col_name, value in zip(name, values):
if col_name == 'Company':
path_name = str(value)
xml_file_copy = xml_file_copy.replace(col_name, str(value))
with xml_path
使用python-docx.Document读取word文档（备注：解决不了特殊字符的问题）
from copy import deepcopy
from pathlib import Path
from win32com import client as wc # pip install pypiwin32
from docx import Document # pip install python-docx
import pandas as pd
# python-docx不能处理doc文档，使用win32com转存为docx文档
def doctransform2docx(doc_path):
docx_path = doc_path + 'x'
suffix = doc_path.split('.')[1]
assert 'doc' in suffix, '传入的不是word文档，请重新输入！'
if suffix == 'docx':
return Document(doc_path)
word = wc.Dispatch('Word.Application')
doc = word.Documents.Open(doc_path)
doc.SaveAs2(docx_path, 16) # docx为16
doc.Close()
word.Quit()
return Document(docx_path)
# 替换docx中的特定字符，由于run方法在有格式的docx文件中展示效果很差，故将docx中的文本的需要填充出英文字符占位
def replace_docx(name, values, wordfile, path_name='Company'):
wordfile_copy = deepcopy(wordfile) # 防止原文件被篡改，deepcopy为副本
for col_name, value in zip(name, values):
if col_name == 'Company':
path_name = str(value)
for paragraphs in wordfile_copy.paragraphs:
for run in paragraphs.runs:
run.text = run.text.replace(col_name, str(value))
# docx文档替换完毕，另存为，一定要用绝对路径
wordfile_copy.save(f'{save_folder}/{path_name}.docx')
if __name__ == '__main__':
# 定义需处理的文件路径
doc_path = r"D:\solve_path\单位.doc"
excel_path = r"D:\solve_path\信息.xls"
save_folder = Path('D:/docx_save')
save_folder.mkdir(parents=True, exist_ok=True) # 文件夹没有时自动创建
# 获取excel数据
data = pd.read_excel(excel_path)
wordfile = doctransform2docx(doc_path)
data_save = data.apply(lambda x: replace_docx(x.index, x.values, wordfile), axis=1)
