|
|
|
|
|
import os
|
|
|
|
|
|
import win32com
|
|
|
|
|
|
from win32com.client import Dispatch
|
|
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
|
|
# pip install pywin32 openpyxl
|
|
|
|
|
|
# pip install pywin32
|
|
|
|
|
|
working_dir = r"D:/dsWork/YunNanDsBase/Doc/全省及州市县区人口与教育报告集20241023/16个州市报告2022/分析报告20240510/"
|
|
|
|
|
|
import openpyxl
|
|
|
|
|
|
|
|
|
|
|
|
# 在工作目录下创建Excel目录
|
|
|
|
|
|
excel_dir = working_dir + 'Excel'
|
|
|
|
|
|
if not os.path.exists(excel_dir):
|
|
|
|
|
|
os.mkdir(excel_dir)
|
|
|
|
|
|
|
|
|
|
|
|
# 关键词
|
|
|
|
|
|
keyword = '人口变化及其对教育的影响'
|
|
|
|
|
|
|
|
|
|
|
|
# 是不是打Word显示
|
|
|
|
|
|
docApp = win32com.client.Dispatch('Word.Application')
|
|
|
|
|
|
# 是不是打Word显示
|
|
|
|
|
|
docApp.Visible = False
|
|
|
|
|
|
docApp.DisplayAlerts = 0
|
|
|
|
|
|
|
|
|
|
|
|
# 遍历工作目录下所有的docx文件，将文件名用keyword进行分隔，前一半是州市名称，后一半是上报的时间，我们取前一半的州市名称
|
|
|
|
|
|
for file in os.listdir(working_dir):
|
|
|
|
|
|
if file.endswith('.docx') and not file.startswith('~'):
|
|
|
|
|
|
file_name = file.split('.')[0]
|
|
|
|
|
|
# 判断一下file_name中是不是存在keyword,如果不存在，则输出错误，并结束程序
|
|
|
|
|
|
if keyword not in file_name:
|
|
|
|
|
|
print('Error: ' + file_name + ' 文件名称中并不包含:' + keyword)
|
|
|
|
|
|
exit()
|
|
|
|
|
|
# 确认包含后，提取出前半部分作为城市名称
|
|
|
|
|
|
city_name = file_name.split(keyword)[0]
|
|
|
|
|
|
# 在excel_dir目录下创建这个城市的子目录，准备将生成的excel文件放在这个子目录下
|
|
|
|
|
|
city_dir = excel_dir + '/' + city_name
|
|
|
|
|
|
if not os.path.exists(city_dir):
|
|
|
|
|
|
os.mkdir(city_dir)
|
|
|
|
|
|
# 将当前docx进行读取其中的每一个段落，要求以 "图"+数字开头，这是图例的意思
|
|
|
|
|
|
doc_path = working_dir + '/' + file
|
|
|
|
|
|
# print(doc_path)
|
|
|
|
|
|
doc = docApp.Documents.Open(doc_path)
|
|
|
|
|
|
# 遍历文档中所有的文字段落,判断是不是以 图+数字开头
|
|
|
|
|
|
idx = 1
|
|
|
|
|
|
# 图表的名称列表
|
|
|
|
|
|
tb_list = []
|
|
|
|
|
|
for para in doc.Paragraphs:
|
|
|
|
|
|
x = para.Range.Text.strip().replace("图 ", "图").replace(" ", " ")
|
|
|
|
|
|
if x.startswith("图"):
|
|
|
|
|
|
tb_list.append(x)
|
|
|
|
|
|
idx = idx + 1
|
|
|
|
|
|
|
|
|
|
|
|
# 遍历文档中的所有内嵌形状
|
|
|
|
|
|
idx = 1
|
|
|
|
|
|
for inline_shape in doc.InlineShapes:
|
|
|
|
|
|
if inline_shape.Type == win32com.client.constants.wdInlineShapeChart: # 检查是否为内嵌图表
|
|
|
|
|
|
shape = doc.InlineShapes(idx)
|
|
|
|
|
|
sheet = shape.Chart.ChartData.Workbook.Worksheets(1)
|
|
|
|
|
|
# 创建一个新的Excel工作簿
|
|
|
|
|
|
wb = openpyxl.Workbook()
|
|
|
|
|
|
ws = wb.active
|
|
|
|
|
|
|
|
|
|
|
|
# 遍历Excel工作表中的所有单元格，并将其写入新的工作簿
|
|
|
|
|
|
for row in range(1, sheet.UsedRange.Rows.Count + 1):
|
|
|
|
|
|
for col in range(1, sheet.UsedRange.Columns.Count + 1):
|
|
|
|
|
|
cell_value = sheet.Cells(row, col).Value
|
|
|
|
|
|
ws.cell(row=row, column=col, value=cell_value)
|
|
|
|
|
|
# 保存新的Excel文件
|
|
|
|
|
|
original_string = tb_list[idx - 1]
|
|
|
|
|
|
# 使用正则表达式过滤，只保留中文、英文和数字
|
|
|
|
|
|
original_string = original_string[1:]
|
|
|
|
|
|
if ' ' in original_string:
|
|
|
|
|
|
original_string = original_string.split(" ")[1]
|
|
|
|
|
|
filtered_string = re.sub(r'[^\u4e00-\u9fa5a-zA-Z0-9]', '', original_string)
|
|
|
|
|
|
fileName = '【' + str(idx) + '】' + filtered_string + ".xlsx"
|
|
|
|
|
|
wb.save(city_dir + '/' + fileName)
|
|
|
|
|
|
print("保存文件：" + fileName)
|
|
|
|
|
|
# 下一个图表的索引号
|
|
|
|
|
|
idx = idx + 1
|
|
|
|
|
|
# print(idx - 1)
|
|
|
|
|
|
# 关闭文档和Word应用
|
|
|
|
|
|
doc.Close()
|
|
|
|
|
|
docApp.Quit()
|
|
|
|
|
|
print("恭喜，所有市州数据整理工作成功完成！")
|
