From a73d24c571e344257a88cc6ca6cdead48a4594a3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=BB=84=E6=B5=B7?= <10402852@qq.com>
Date: Fri, 8 Nov 2024 21:45:12 +0800
Subject: [PATCH] 'commit'

---
 BaiHu/Tools/DocxTuBiaoRead.py | 43 ++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 18 deletions(-)

diff --git a/BaiHu/Tools/DocxTuBiaoRead.py b/BaiHu/Tools/DocxTuBiaoRead.py
index 7ffeaaa1..fa926ab5 100644
--- a/BaiHu/Tools/DocxTuBiaoRead.py
+++ b/BaiHu/Tools/DocxTuBiaoRead.py
@@ -13,27 +13,34 @@ docApp.DisplayAlerts = 0
 doc = docApp.Documents.Open('c:/红河哈尼族彝族自治州人口变化及其对教育的影响20240419.docx')
 
 # 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)
+#         # 获取图表的标题,此项目中图表没有标题
+#         # print(shape.Chart.ChartTitle.Text)
+#         sheet = shape.Chart.ChartData.Workbook.Worksheets("Sheet1")
+#         # 行数
+#         row_size = sheet.UsedRange.rows.Count
+#         # 列数
+#         col_size = sheet.UsedRange.columns.Count
+#         # 遍历获取表格中的数据
+#         for i in range(1, row_size + 1):
+#             for j in range(1, col_size + 1):
+#                 print(sheet.Cells(i, j).Value, end=" ")
+#             print("")
+#         print("")
+#         # 下一个图表的索引号
+#         idx = idx + 1
+# print(idx)
+# 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
-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)
-        # 获取图表的标题,此项目中图表没有标题
-        # print(shape.Chart.ChartTitle.Text)
-        sheet = shape.Chart.ChartData.Workbook.Worksheets("Sheet1")
-        # 行数
-        row_size = sheet.UsedRange.rows.Count
-        # 列数
-        col_size = sheet.UsedRange.columns.Count
-        # 遍历获取表格中的数据
-        for i in range(1, row_size + 1):
-            for j in range(1, col_size + 1):
-                print(sheet.Cells(i, j).Value, end=" ")
-            print("")
-        print("")
-        # 下一个图表的索引号
+for para in doc.Paragraphs:
+    x = para.Range.Text.strip().replace("图 ", "图").replace("  ", " ")
+    if x.startswith("图"):
+        print(x)
         idx = idx + 1
 
-print(idx)
 # 关闭文档和Word应用
 doc.Close()
 docApp.Quit()