94｜理论盘点：文件类型与对应的 Python 函数库-零基础学Python（2023版）-极客时间

from docx import Document from openpyxl import Workbook,load_workbook Workbook1=load_workbook("import.xlsx",data_only=True) wb_sheet_actived = Workbook1['Sheet1'] document = Document() table = document.add_table(rows=0, cols=wb_sheet_actived.max_column) table.style='Table Grid' for row_cells in wb_sheet_actived.rows: table_cells = table.add_row().cells i=0 for cell in row_cells: # print(cell.value) # print(type(cell.value)) cell_value = str(cell.value) if cell.value is not None else "" table_cells[i].text = cell_value i += 1 document.save('export.docx') 教师请教一个问题，如果读取的表格中有合并的单元格，如何把它获取出来，并写入到docx文件中呢

作者回复: 我提供一个代码样例： from docx import Document from openpyxl import load_workbook # 加载Excel文件 Workbook1 = load_workbook("import.xlsx", data_only=True) wb_sheet_actived = Workbook1['Sheet1'] # 创建docx文档 document = Document() table = document.add_table(rows=0, cols=wb_sheet_actived.max_column) table.style = 'Table Grid' # 获取合并单元格的信息 merged_cells_ranges = wb_sheet_actived.merged_cells.ranges # 遍历Excel表格的行 for row_cells in wb_sheet_actived.rows: table_cells = table.add_row().cells i = 0 # 遍历每行的单元格 for cell in row_cells: cell_value = "" # 判断单元格是否属于合并单元格 for merged_range in merged_cells_ranges: if cell.coordinate in merged_range: # 获取合并单元格的首个单元格的值 cell_value = merged_range.start_cell.value break # 如果单元格不属于合并单元格，则获取单元格的值 if not cell_value: cell_value = str(cell.value) if cell.value is not None else "" # 将值写入到docx表格的单元格中 table_cells[i].text = cell_value i += 1 # 保存docx文件 document.save('export.docx') 上述代码使用`openpyxl`库的`merged_cells`属性获取Excel中的合并单元格范围，并检查当前单元格是否在合并范围内，如果在，则获取合并范围的首个单元格的值。然后，将单元格的值写入到`docx`文件的表格中，处理合并单元格时替换为合并范围首个单元格的值。 ps：可以在讨论群中和我沟通，留言区问题经常会被打卡信息给淹没，导致问题被忽略，我也是翻查视频才看到的问题

2023-06-11





hwj

老师请叫一个问题，如何对word中图片批量添加题注

作者回复: import win32com.client as win32 from win32com.client import constants import os curr_path = os.getcwd() doc_app = win32.gencache.EnsureDispatch('Word.Application')#打开word应用程序 doc_app.Visible =1#设置应用程序可见 doc = doc_app.Documents.Open(r'%s\批量插入题注示例文档.docx'%curr_path)#打开文档 print(doc.InlineShapes.Count) # 插入图片题注 for pic in doc.InlineShapes: rng = pic.Range rng.InsertCaption(Label= constants.wdCaptionFigure,Position=constants.wdCaptionPositionBelow,Title="咖啡杯") 参考链接： https://zhuanlan.zhihu.com/p/480345307

2023-05-10





Geek_631607

import pandas as pd from docx import Document # 读取 Excel 文件的第一张表格 df = pd.read_excel('sample.xlsx', sheet_name=0) # 创建一个新的 docx 文件 doc = Document() # 将表格的内容添加到 docx 文件中 for index, row in df.iterrows(): # 创建一个新的段落 paragraph = doc.add_paragraph() # 将每一行的内容添加到段落中 for col in df.columns: paragraph.add_run(f'{col}: {row[col]} ') # 添加一个空行 doc.add_paragraph() # 保存 docx 文件 doc.save('file.docx')

2023-12-11





醉后不知天在水

import sys !{sys.executable} -m pip install pandas !{sys.executable} -m pip install python-docx import pandas as pd from docx import Document df = pd.read_excel("./sample2.xlsx") print(df.shape[1]) doc = Document() table = doc.add_table(df.shape[0]+1, df.shape[1]) for i, column_name in enumerate(df.columns): table.cell(0, i).text = column_name for index, row in df.iterrows(): for i, value in enumerate(row): table.cell(index+1, i).text = str(value) doc.save("./output.docx")

2023-11-16





MarkG

import pandas as pd from docx import Document # 读取 excel 文件 df = pd.read_excel('./sample.xlsx', sheet_name=0) # 创建一个 docx 对象 doc = Document() # 遍历表格的行 for i, row in df.iterrows(): # 创建一个断了对象 paragraph = doc.add_paragraph() # print('row', i, row) # 遍历行中的每个单元格 for cell in row: print('cell', cell) paragraph.add_run(str(cell)).bold = True # 保存 docx 文件 doc.save('output.docx')

2023-11-02





Geek_Mike

import pandas import docx excl = '/Users/mike/Desktop/zero-basics-python/0/sample.xlsx' word = '/Users/mike/Desktop/zero-basics-python/0/sample_1.docx' pd = pandas.ExcelFile(excl) dataframe = pandas.read_excel(pd, 'Sheet') data = dataframe.values.tolist() doc = docx.Document() table = doc.add_table(rows = len(data), cols = len(data[0])) table.style = 'Table Grid' for i in range(len(data)): for j in range(len(data[0])): cell = table.cell(i, j) cell.text = str(data[i][j]) doc.save(word)

2023-10-23





Greenery

#%% from os import chdir from openpyxl import load_workbook chdir(r'C:\Projects\python\0base_py\ch12\exp1') wb = load_workbook(filename = 'hk.xlsx') sheet_ranges = wb['Sheet1'] #%% values=[] for i in range(1,9): row = [] for j in ['A','B','C','D']: row.append(sheet_ranges[j+str(i)].value) values.append(row) print(values) #%% from docx import Document document = Document() document.add_heading('用户权限表', 0) table=document.add_table(rows=1,cols=4) hdr_cells = table.rows[0].cells for i in range(4): hdr_cells[i].text = values[0][i] for i in range(2,8): row_cells = table.add_row().cells for j in range(4): row_cells[j].text = str(values[i][j]) document.add_page_break() # 保存文件名 document.save('hk.docx')

2023-07-27





Geek_fb1a3e

from docx import Document from openpyxl import workbook, load_workbook wb = load_workbook('12\excel1.xlsx') # print(wb) #wb.sheetnames: 取得工作簿中所有表名的列表 ws = wb[wb.sheetnames[0]] # ws.calculate_dimension(): 获取工作表全部数据的单元格区域 # ws.max_row 获取工作表最大行 # ws.max_column 获取工作表最大列 # ws.rows 迭代所有行 # ws.columns 迭代所有列 cell_area = ws[ws.calculate_dimension()] records = [] for row in cell_area: row_list = [] for cell in row: row_list.append(cell.value) records.append(row_list) document = Document() #表格：document.add_table()添加指定行数列数的表格 max_row = ws.max_row max_col = ws.max_column print(f"行数：{max_row}，列数{max_col}") table = document.add_table(rows=0, cols=5) for i in range(max_row): row_cells = table.add_row().cells for j in range(max_col): row_cells[j].text = str(records[i][j]) document.save('toWord.docx')

2023-03-09





Cy23

from docx import Document from openpyxl import Workbook,load_workbook wb = load_workbook("1.xlsx") ws = wb.active data_row = [] for row in ws.values: data_row.append(row) document = Document() table = document.add_table(rows = 0, cols = ws.max_column) table.style = 'Table Grid' for row in data_row: row_cells = table.add_row().cells for index, val in enumerate(row): row_cells[index].text = str(val) document.save('1.docx')

2023-01-31





Matthew

from docx import Document from openpyxl import Workbook,load_workbook # 打开要访问的 Excel wb = load_workbook("1.xlsx") ws = wb.active data_row = [] # 遍历 Excel 默认 SHEET 的每一行，存入 data_row for row in ws.values: data_row.append(row) ########################################################### # 创建要写入的 Word document = Document() table = document.add_table(rows = 0, cols = ws.max_column) table.style = 'Table Grid' # 遍历 data_row 的每个元素（元组），为 table 的每一行逐一赋值 for i, j, k in data_row: row_cells = table.add_row().cells row_cells[0].text = str(i) row_cells[1].text = str(j) row_cells[2].text = str(k) document.save('111.docx')

2023-01-28





收起评论