init

excel2word.py

@@ -0,0 +1,90 @@
+import glob
+import pandas as pd
+from docx import Document
+
+# 目录级别后移，最小为0
+level_offset = 1
+name = False
+header = False
+headline = []
+# sheet页黑名单，当前所有表格中均不含退役军人项，该项为excel模版中带有的sheet页，如有例外需特殊处理。
+sheet_name_black_list = ['填表说明', '数据资源目录结构', '新增需求填报', '退役军人']
+column_black_list = ['期望更新周期']
+
+# 获取全部excel表格
+# xlsx_files = glob.glob('./附件2*.xlsx')
+
+# sheet_name_black_list = ['填表说明', '数据资源目录结构', '新增需求填报']
+xlsx_files = ['附件2：自治区文化旅游主题共享资源库需求对接表_3932232206984868.xlsx']
+
+for file in xlsx_files:
+    # 打开模板word文件
+    doc = Document('temp.docx')
+    print(f"正在处理文件: {file}")
+
+    # 读取Excel文件
+    xls = pd.ExcelFile(file)
+    # 逐sheet处理
+    for sheet_name in xls.sheet_names:
+        level_offset = 1
+        name = False
+        header = False
+        if sheet_name in sheet_name_black_list:
+            continue
+        print(f"正在处理工作表: {sheet_name}")
+        # 读取当前工作表到DataFrame
+        df = xls.parse(sheet_name)
+        doc.add_heading(sheet_name, 1 + level_offset)
+        initialized_header = False
+
+        third_index = 1
+        items_index = 1
+        for index, row in df.iterrows():
+            # 检查当前行的E列是否为空，为空则说明为新表，重置表名及表头标记
+            if pd.isnull(row[4]):
+                level_offset = 1
+                name = False
+                header = False
+            # 检查当前行的B列是否为空，为空说明整行为空要跳过
+            if pd.isnull(row[1]):
+                continue
+            # 只要符合模式，新表第一行B列一定为表名
+            if not name:
+                # 去除表名开头的“中文数字、”
+                table_name = str.split(row[1], '、', 1)[1]
+                name = True
+                if table_name == sheet_name:
+                    level_offset -= 1
+                    continue
+                else:
+                    doc.add_heading(table_name, 2 + level_offset)
+                    continue
+            # 只要符合模式，新表第二行一定为表头
+            if not header:
+                if not initialized_header:
+                    initialized_header = True
+                    headline.clear()
+                    new_row = row[4:]
+                    for cell in new_row:
+                        headline.append(cell)
+                header = True
+                continue
+            # 只要符合模式，新表从第三行开始，非空的D列一定为子表名
+            if not pd.isnull(row[3]):
+                if sheet_name == str(row[3]).replace(' ', '') or table_name == str(row[3]).replace(' ', ''):
+                    level_offset -= 1
+                else:
+                    doc.add_heading(str(row[3]).replace(' ', ''), 3 + level_offset)
+                items_index = 1
+            # 默认正常的E列（非表中间间隔）不为空，为空会出错
+            doc.add_heading(row[4], 4 + level_offset)
+            for head, cell in zip(headline, row[4:]):
+                if head in column_black_list:
+                    continue
+                doc.add_paragraph(head + "：" + str(cell).replace('\n', '').replace('nan', '无'))
+            items_index += 1
+    # 文件另存为
+    out_file_name = file.split('：')[1].split('_')[0]
+    doc.save(out_file_name + ".docx")
+    xls.close()
+print("处理完成")

excel2word2.py

@@ -0,0 +1,80 @@
+import glob
+import pandas as pd
+from docx import Document
+
+# 目录级别后移，最小为0
+level_offset = 1
+name = False
+header = False
+headline = []
+# sheet页黑名单，当前所有表格中均不含退役军人项，该项为excel模版中带有的sheet页，如有例外需特殊处理。
+sheet_name_black_list = ['指标体系', '资源目录']
+column_black_list = ['期望更新周期']
+
+# 获取全部excel表格
+xlsx_files = glob.glob('./附件2*.xlsx')
+
+# sheet_name_black_list = ['填表说明', '数据资源目录结构', '新增需求填报']
+# xlsx_files = ['附件2：自治区文化旅游主题共享资源库需求对接表_3932232206984868.xlsx']
+
+for file in xlsx_files:
+    # 打开模板word文件
+    doc = Document('temp.docx')
+    print(f"正在处理文件: {file}")
+
+    # 读取Excel文件
+    xls = pd.ExcelFile(file)
+    # 逐sheet处理
+    for sheet_name in xls.sheet_names:
+        name = False
+        header = False
+        if sheet_name in sheet_name_black_list:
+            continue
+        print(f"正在处理工作表: {sheet_name}")
+        # 读取当前工作表到DataFrame
+        df = xls.parse(sheet_name)
+        doc.add_heading(sheet_name, 1 + level_offset)
+        initialized_header = False
+
+        third_index = 1
+        items_index = 1
+        for index, row in df.iterrows():
+            # 检查当前行的E列是否为空，为空则说明为新表，重置表名及表头标记
+            if pd.isnull(row[4]):
+                name = False
+                header = False
+            # 检查当前行的B列是否为空，为空说明整行为空要跳过
+            if pd.isnull(row[1]):
+                continue
+            # 只要符合模式，新表第一行B列一定为表名
+            if not name:
+                # 去除表名开头的“中文数字、”
+                doc.add_heading(str.split(row[1], '、', 1)[1], 2 + level_offset)
+                name = True
+                continue
+            # 只要符合模式，新表第二行一定为表头
+            if not header:
+                if not initialized_header:
+                    initialized_header = True
+                    headline.clear()
+                    new_row = row[4:]
+                    for cell in new_row:
+                        headline.append(cell)
+                header = True
+                continue
+            # 只要符合模式，新表从第三行开始，非空的D列一定为子表名
+            if not pd.isnull(row[3]):
+                doc.add_heading(str(row[3]).replace(' ', ''), 3 + level_offset)
+                items_index = 1
+            # 默认正常的E列（非表中间间隔）不为空，为空会出错
+            doc.add_heading(row[4], 4 + level_offset)
+            for head, cell in zip(headline, row[4:]):
+                if head in column_black_list:
+                    continue
+                doc.add_paragraph(head + "：" + str(cell).replace('\n', '').replace('nan', '无'))
+            items_index += 1
+    # 文件另存为
+    out_file_name = file.split('：')[1].split('_')[0]
+    doc.save(out_file_name + ".docx")
+    xls.close()
+print("处理完成")

execl.py

@@ -0,0 +1,53 @@
+import glob
+import pandas as pd
+
+name = False
+header = False
+headline = []
+sheet_name_black_list = ['填表说明', '数据资源目录结构', '新增需求填报']
+
+xlsx_files = glob.glob('./附件2*.xlsx')
+for file in xlsx_files:
+    print(f"正在处理文件: {file}")
+    out_file_name = file.split('：')[1].split('_')[0]
+    # 读取Excel文件
+    xls = pd.ExcelFile(file)
+    # 打开一个文件用于写入
+    with open(out_file_name + '.txt', 'w', encoding='utf-8') as file:
+        for sheet_name in xls.sheet_names:
+            name = False
+            header = False
+            if sheet_name in sheet_name_black_list:
+                continue
+            print(f"正在处理工作表: {sheet_name}")
+            # 读取当前工作表到DataFrame
+            df = xls.parse(sheet_name)
+            file.write(sheet_name + "\n")
+            initialized_header = False
+            for index, row in df.iterrows():
+                # 检查当前行的B列是否为空
+                if pd.isnull(row[1]):
+                    file.write("\n\n")
+                    name = False
+                    header = False
+                    continue
+                if not name:
+                    file.write(row[1] + "\n")
+                    name = True
+                    continue
+                if not header:
+                    if not initialized_header:
+                        initialized_header = True
+                        new_row = [row[1]]
+                        new_row.extend(row[4:])
+                        for cell in new_row:
+                            headline.append(cell)
+                    header = True
+                    continue
+                new_row = [row[1]]
+                new_row.extend(row[4:])
+                for head, cell in zip(headline, new_row):
+                    file.write(head + ":" + str(cell).replace('\n', '') + "\n")
+                file.write("\n")
+    xls.close()
+print("处理完成")

wordformat.py

@@ -0,0 +1,31 @@
+from docx import Document
+
+# 打开目标Word文档
+document = Document('数据库概要设计说明书.docx')
+# 打开样板文件
+doc = Document('temp.docx')
+database_index = 0
+table_index = 1
+empty_table = False
+
+# 遍历文档中的所有段落
+for paragraph in document.paragraphs:
+    if paragraph.text.startswith('数据库：'):
+        database_index += 1
+        doc.add_heading(str(database_index) + "." + paragraph.text, 1)
+        table_index = 1
+    elif paragraph.text.startswith('表名：'):
+        if len(paragraph.text) == 3:
+            empty_table = True
+            continue
+        else:
+            empty_table = False
+        doc.add_heading(str(database_index) + "." + str(table_index) + "." + paragraph.text, 2)
+        table_index += 1
+    elif empty_table:
+        continue
+    else:
+        doc.add_paragraph(paragraph.text)
+
+# 保存修改后的文档
+doc.save('modified_document.docx')