{"id":1371,"date":"2020-10-12T09:36:18","date_gmt":"2020-10-12T09:36:18","guid":{"rendered":"https:\/\/www.ipcpu.com\/?p=1371"},"modified":"2021-07-15T02:24:44","modified_gmt":"2021-07-15T02:24:44","slug":"python-excel","status":"publish","type":"post","link":"https:\/\/c.ipcpu.com\/2020\/10\/python-excel\/","title":{"rendered":"Python\u5904\u7406Excel"},"content":{"rendered":"

Python\u5904\u7406Excel.md<\/p>\n

Excel\u9884\u5904\u7406<\/h2>\n

Python\u5904\u7406Excel\u6587\u4ef6\u7684\u5e93\u6709\u5f88\u591a\u5f88\u591a\uff0c\u4f46\u662fExcel\u7684\u683c\u5f0f\u4e5f\u6709\u5f88\u591a\uff0cxls\u3001xlsx\u3001xlsm\uff0c\u771f\u662f\u770b\u82b1\u773c\uff0c\u6709\u4eba\u5217\u4e3e\u4e86\u4e00\u4e9b\u5e38\u7528\u7684\u5e93\u7279\u70b9
\n
\n\u5f88\u663e\u7136\uff0c\u597d\u591a\u5e93\u5176\u4e2d\u7f3a\u70b9\u4e00\u9879\u5c31\u662f\u5bf9\u4e8exls\u6ca1\u6709\u652f\u6301\uff0c\u90a3\u548b\u529e\uff1f
\n\u4e00\u822c\u6765\u8bf4\u6211\u4eec\u5efa\u8bae\u5728Excel\u6587\u4ef6\u653e\u5165Python\u5904\u7406\u4e4b\u524d\uff0c\u5148\u8fdb\u884c\u683c\u5f0f\u8f6c\u6362\uff0c\u7edf\u4e00\u8f6c\u6362\u4e3axlsx\u683c\u5f0f\uff0c\u7136\u540e\u5728\u4f7f\u7528python\u8c03\u7528\u5904\u7406\u3002<\/p>\n

\n
import win32com.client as win32\nfname = \"full+path+to+xls_file\"\nexcel = win32.gencache.EnsureDispatch('Excel.Application')\nwb = excel.Workbooks.Open(fname)\n\nwb.SaveAs(fname+\"x\", FileFormat = 51)    \nwb.Close()                               \nexcel.Application.Quit()\n# FileFormat = 51 is for .xlsx extension\n# FileFormat = 56 is for .xls extension\n# \u51e0\u70b9\u6ce8\u610f\u4e8b\u9879\uff1a\n# 1. \u7cfb\u7edf\u9700\u8981\u5b89\u88c5Excel\u6216\u8005WPS\u5e76\u4e14\u6709\u9ed8\u8ba4excel\u7a0b\u5e8f\u5173\u8054\uff0cWPS\u8bbe\u7f6e\u6210\u9ed8\u8ba4\u7a0b\u5e8f\u4e5f\u53ef\u4ee5\n# 2. \u6587\u4ef6\u8def\u5f84\u5fc5\u987b\u5199\u5b8c\u6574\u8def\u5f84\uff0c\u56e0\u4e3aExcel\u7a0b\u5e8f\u65e0\u6cd5\u8bc6\u522bPython\u6587\u4ef6\u7684\u76ee\u5f55\n# 3. win32com\u5e93\uff0c\u4f7f\u7528pip install pypiwin32\u5b89\u88c5<\/code><\/pre>\n<\/div>\n
openpyxl\u5e93\u7684\u4f7f\u7528<\/h2>\n
openpyxl\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684Excel\u5904\u7406\u5e93\uff0c\u662f\u4e00\u4e2a\u6bd4\u8f83\u7efc\u5408\u7684\u5de5\u5177\uff0c\u80fd\u591f\u540c\u65f6\u8bfb\u53d6\u548c\u4fee\u6539Excel\u6587\u6863\u3002<\/p>\n
\n
from openpyxl import load_workbook\nfrom openpyxl.styles import colors, Font, Fill, NamedStyle\n\n\n#\u57fa\u7840\u6982\u5ff5\uff1a\u4e00\u4e2aExcel\u6587\u4ef6\u5c31\u662f\u4e00\u4e2aworkbook\uff0c\u91cc\u9762\u6709\u591a\u4e2aworksheet\n#\u6bcf\u4e2asheet\u4e2d\u6709\u82e5\u5e72\u4e2a\u5355\u5143\u683ccell\n\n# \u52a0\u8f7d\u6587\u4ef6, \u5982\u679c\u6587\u4ef6\u6709\u516c\u5f0f\u9700\u8981\u52a0\u4e0adata_only\nwb = load_workbook('.\/5a.xlsx', data_only=True)\n# \u8bfb\u53d6sheetname\nprint('==\u8f93\u51fa\u6587\u4ef6\u6240\u6709\u5de5\u4f5c\u8868\u540d\uff1a\\n', wb.sheetnames)\n\n\n#\u6dfb\u52a0\u5220\u9664sheet\n# \u521b\u5efa\u7684sheet\u5fc5\u987b\u8981\u8d4b\u503c\u7ed9\u4e00\u4e2a\u5bf9\u8c61\uff0c\u4e0d\u7136\u53ea\u6709\u540d\u5b57\u4f46\u662f\u6ca1\u6709\u5b9e\u9645\u7684\u65b0\u8868\nws4 = wb.create_sheet(index=0, title='newsheet')\n# \u4ec0\u4e48\u53c2\u6570\u90fd\u4e0d\u5199\u7684\u8bdd\uff0c\u9ed8\u8ba4\u63d2\u5165\u5230\u6700\u540e\u4e00\u4e2a\u4f4d\u7f6e\u4e14\u540d\u5b57\u4e3asheet,sheet1...\u6309\u7167\u987a\u5e8f\u6392\u5217\nws5 = wb.create_sheet()\n# \u5220\u9664sheet\nwb.remove(ws4)  # \u8fd9\u91cc\u53ea\u80fd\u5199worksheet\u5bf9\u8c61\uff0c\u4e0d\u80fd\u5199sheetname\n\n\n# \u8bfb\u53d6sheet1\u4e2d\u7684\u6709\u6548\u533a\u57df\nws1 = wb['Sheet1']\nprint('==\u6700\u5927\u5217\u6570\u4e3a\uff1a', ws1.max_column)\nprint('==\u6700\u5927\u884c\u6570\u4e3a\uff1a', ws1.max_row)\n\n#\u8bfb\u53d6A1\u5355\u5143\u683c\u7684\u503c\nprint('==\u8bfb\u53d6B2\u5355\u5143\u683c\u5185\u5bb9')\nprint(ws1['B2'].coordinate, ws1['B2'].value)\n\n#\u7ed9A1\u5355\u5143\u683c\u8bbe\u7f6e\u5b57\u4f53\u683c\u5f0f\nft = Font(name='\u5fae\u8f6f\u96c5\u9ed1', color='000000', size=15, b=True)\ntitle = ws1['A1']\ntitle.font = ft\n\n#\u8bfb\u53d6B4:C5\ndata = ws1['B4:C5']\nprint(data, type(data))\n\n\n#\u904d\u5386sheet1\nfor row in ws1.iter_rows():\n    for cell in row:\n        print(cell.coordinate, cell.value)\n\n#\u4fdd\u5b58\u4fee\u6539\nwb.save('.\/5a.xlsx')<\/code><\/pre>\n<\/div>\n
\u6267\u884c\u7ed3\u679c<\/p>\n
\n
==\u8f93\u51fa\u6587\u4ef6\u6240\u6709\u5de5\u4f5c\u8868\u540d\uff1a\n ['Sheet1', 'Sheet2', 'Sheet3']\n==\u6700\u5927\u5217\u6570\u4e3a\uff1a 4\n==\u6700\u5927\u884c\u6570\u4e3a\uff1a 4\n==\u8bfb\u53d6B2\u5355\u5143\u683c\u5185\u5bb9\nB2 66756\n((<Cell 'Sheet1'.B4>, <Cell 'Sheet1'.C4>), (<Cell 'Sheet1'.B5>, <Cell 'Sheet1'.C5>)) <class 'tuple'>\n<\/code><\/pre>\n<\/div>\n
pandas\u5e93\u7684\u4f7f\u7528<\/h2>\n
pandas\u662f\u6211\u4eec\u65e5\u5e38\u7ecf\u5e38\u7528\u5230\u7684\u6570\u636e\u5206\u6790\u5e93\uff0c\u6211\u4eec\u4ee5\u524d\u4e5f\u8bf4\u8fc7\u4ed6\u7684DataFrame\u6570\u636e\u7ed3\u6784\u7c7b\u4f3c\u4e8eExcel\u8868\u7684\u5b58\u50a8\u65b9\u5f0f\uff0c\u56e0\u6b64pandas\u5904\u7406Excel\u6587\u4ef6\u7f3a\u5931\u5f88\u65b9\u4fbf<\/p>\n
\n
import pandas as pd\n\nprint('==\u6253\u5370sheet\u5185\u5bb9')\ndf = pd.read_excel('.\/5a.xlsx', sheet_name=0)  # \u8bfb\u53d6\u7b2c1\u4e2asheet\nprint(df)\n\nprint('==\u6253\u5370\u6240\u6709sheet\u540d\u5b57\u5217\u8868')\nworkbook = pd.ExcelFile('.\/5a.xlsx')\nprint(workbook)\nprint(workbook.sheet_names)\n\n\nprint('==\u8f93\u51fa\u884c\u53f7', df.index.values)\nprint('==\u8f93\u51fa\u5217\u6807\u9898', df.columns.values)\n\nprint('==\u8bfb\u53d6\u67d0\u4e00\u884c\u6570\u636e\\n', df.iloc[0].values)\n#\u8fd9\u91cc\u8bfb\u53d6\u6570\u636e\u5e76\u4e0d\u5305\u542b\u8868\u5934\nprint('==\u8bfb\u53d6\u591a\u884c\u6570\u636e\\n', df.iloc[[0, 1]].values)\n#\u5d4c\u5957\u5217\u8868\nprint('==\u8bfb\u53d6\u67d0\u4e00\u5217\u6570\u636e\\n', df['\u603b\u548c'].values)\nprint('==\u8bfb\u53d6\u67d0\u5355\u5143\u683c\u6570\u636e\\n', df.iloc[1, 3])\n#\u8fd9\u91cc\u4e0d\u9700\u8981\u5d4c\u5957\u5217\u8868\uff0c\u4e5f\u6ca1\u6709values\n\n\n#\u628a\u6bcf\u4e00\u884c\u90fd\u8f6c\u6362\u6210\u5b57\u5178\ntest_data=[]\nkeys = df.columns.values\nfor i in df.index.values:#\u83b7\u53d6\u884c\u53f7\u7684\u7d22\u5f15\uff0c\u5e76\u5bf9\u5176\u8fdb\u884c\u904d\u5386\uff1a\n    # \u6839\u636ei\u6765\u83b7\u53d6\u6bcf\u4e00\u884c\u6307\u5b9a\u7684\u6570\u636e \u5e76\u5229\u7528to_dict\u8f6c\u6210\u5b57\u5178,# loc\u4e3a\u6309\u5217\u540d\u7d22\u5f15 iloc \u4e3a\u6309\u4f4d\u7f6e\u7d22\u5f15\uff0c\u4f7f\u7528\u7684\u662f [[\u884c\u53f7], [\u5217\u540d]]\n    row_data = df.loc[i, keys].to_dict()\n    # \u5c06\u6bcf\u4e00\u884c\u8f6c\u6362\u6210\u5b57\u5178\u540e\u6dfb\u52a0\u5230\u5217\u8868\n    test_data.append(row_data)\nprint('==\u6700\u7ec8\u83b7\u53d6\u5230\u7684\u6570\u636e\u662f\uff1a\\n{0}'.format(test_data))\n\n\nprint('==\u5199\u5230\u65b0\u7684Excel\u4e2d')\npd.DataFrame(df).to_excel('new_excel.xlsx', sheet_name='guess', index=False, header=True)<\/code><\/pre>\n<\/div>\n
\u8f93\u51fa\u7ed3\u679c\u5982\u4e0b<\/p>\n
\n
==\u6253\u5370sheet\u5185\u5bb9\n   \u6708\u4efd    \u963f\u91cc\u4e91    cdn     \u603b\u548c\n0   7  66756  14021  80777\n1   8  65345  16532  81877\n2   9  65872  17872  83744\n==\u6253\u5370\u6240\u6709sheet\u540d\u5b57\u5217\u8868\n<pandas.io.excel._base.ExcelFile object at 0x0000023CD8D614F0>\n['Sheet1', 'Sheet2', 'Sheet3']\n==\u8f93\u51fa\u884c\u53f7 [0 1 2]\n==\u8f93\u51fa\u5217\u6807\u9898 ['\u6708\u4efd' '\u963f\u91cc\u4e91' 'cdn' '\u603b\u548c']\n==\u8bfb\u53d6\u67d0\u4e00\u884c\u6570\u636e\n [    7 66756 14021 80777]\n==\u8bfb\u53d6\u591a\u884c\u6570\u636e\n [[    7 66756 14021 80777]\n [    8 65345 16532 81877]]\n==\u8bfb\u53d6\u67d0\u4e00\u5217\u6570\u636e\n [80777 81877 83744]\n==\u8bfb\u53d6\u67d0\u5355\u5143\u683c\u6570\u636e\n 81877\n==\u6700\u7ec8\u83b7\u53d6\u5230\u7684\u6570\u636e\u662f\uff1a\n[{'\u6708\u4efd': 7, '\u963f\u91cc\u4e91': 66756, 'cdn': 14021, '\u603b\u548c': 80777}, {'\u6708\u4efd': 8, '\u963f\u91cc\u4e91': 65345, 'cdn': 16532, '\u603b\u548c': 81877}, {'\u6708\u4efd': 9, '\u963f\u91cc\u4e91': 65872, 'cdn': 17872, '\u603b\u548c': 83744}]\n==\u5199\u5230\u65b0\u7684Excel\u4e2d<\/code><\/pre>\n<\/div>\n
\u6ce8\u610f\u4e8b\u9879\uff1a\u5728\u4f7f\u7528pandas\u7684 df.to_excel(file_path)\u60f3\u8981\u5bf9\u4e00\u4e2a\u6709\u591a\u5f20sheet\u7684workbook\u64cd\u4f5c\u65f6\u4e00\u5b9a\u4f1a\u5c34\u5c2c\u7684\u53d1\u73b0\uff1a\u6c38\u8fdc\u53ea\u5b58\u5728\u6700\u540e\u4e00\u6b21\u5199\u8fdb\u53bb\u7684sheet\uff0c\u5176\u4ed6\u7684\u90fd\u88ab\u6e05\u7a7a\u4e86\u3002\u8fd9\u65f6\u5019\u9700\u8981\u4f7f\u7528ExcelWriter\uff0c\u5982\u4e0b<\/p>\n
\n
import pandas as pd\nimport numpy as np\n\n\nwriter = pd.ExcelWriter('demo.xlsx')  #\u9ed8\u8ba4\u662f\u8986\u76d6\u6a21\u5f0f\uff0c\u4f1a\u628a\u6587\u4ef6\u6e05\u7a7a\u518d\u5199\u6570\u636e\n#writer = pd.ExcelWriter('demo.xlsx', mode='a')  #\u8ffd\u52a0\u6a21\u5f0f\uff0c\u6587\u4ef6\u5fc5\u987b\u5148\u5b58\u5728\n\n\n'''\u521b\u5efa\u6570\u636e\u68461'''\ndf1 = pd.DataFrame({'V1': np.random.rand(10),\n                    'V2': np.random.rand(10),\n                    'V3': np.random.rand(10)})\ndf1.to_excel(writer, sheet_name='sheet1', index=False)\n\n'''\u521b\u5efa\u6570\u636e\u68462'''\ndf2 = pd.DataFrame({'V1': np.random.rand(10),\n                    'V2': np.random.rand(10),\n                    'V3': np.random.rand(10)})\ndf2.to_excel(writer, sheet_name='sheet2', index=False)\n\n'''\u6570\u636e\u5199\u51fa\u5230excel\u6587\u4ef6\u4e2d'''\nwriter.save()<\/code><\/pre>\n<\/div>\n
\u53c2\u8003\u8d44\u6599<\/h2>\n
https:\/\/www.jianshu.com\/p\/720c6653d9b7<\/a><\/p>\n
\u8f6c\u8f7d\u8bf7\u6ce8\u660e\uff1aIPCPU-\u7f51\u7edc\u4e4b\u8def<\/a> » Python\u5904\u7406Excel<\/a><\/p>","protected":false},"excerpt":{"rendered":"
Python\u5904\u7406Excel.md Excel\u9884\u5904\u7406 Python\u5904\u7406Excel\u6587\u4ef6\u7684\u5e93\u6709\u5f88\u591a\u5f88\u591a\uff0c\u4f46\u662fExcel\u7684\u683c\u5f0f\u4e5f\u6709\u5f88\u591a\uff0cxls\u3001xlsx\u3001xlsm\uff0c\u771f\u662f\u770b\u82b1\u773c\uff0c\u6709\u4eba\u5217\u4e3e\u4e86\u4e00\u4e9b\u5e38\u7528\u7684\u5e93\u7279\u70b9 \u5f88\u663e\u7136\uff0c\u597d\u591a\u5e93\u5176\u4e2d\u7f3a\u70b9\u4e00\u9879\u5c31\u662f\u5bf9\u4e8exls\u6ca1\u6709\u652f\u6301\uff0c\u90a3\u548b\u529e\uff1f \u4e00\u822c\u6765\u8bf4\u6211\u4eec\u5efa\u8bae\u5728Excel\u6587\u4ef6\u653e\u5165Python\u5904\u7406\u4e4b\u524d\uff0c\u5148\u8fdb\u884c\u683c\u5f0f\u8f6c\u6362\uff0c\u7edf\u4e00\u8f6c\u6362\u4e3axlsx\u683c\u5f0f\uff0c\u7136\u540e\u5728\u4f7f\u7528python\u8c03\u7528\u5904\u7406\u3002 import win32com.client as win32 fname = “full+path+to+xls_file” excel = win32.gencache.EnsureDispatch(‘Excel.Application’) wb = excel.Workbooks.Open(fname) wb.SaveAs(fname+”x”, FileFormat = 51) wb.Close() excel.Application.Quit() # FileFormat = 51 is for .xlsx extension # FileFormat = 56 is for .xls extension # \u51e0\u70b9\u6ce8\u610f\u4e8b\u9879\uff1a # 1. \u7cfb\u7edf\u9700\u8981\u5b89\u88c5Excel\u6216\u8005WPS\u5e76\u4e14\u6709\u9ed8\u8ba4excel\u7a0b\u5e8f\u5173\u8054\uff0cWPS\u8bbe\u7f6e\u6210\u9ed8\u8ba4\u7a0b\u5e8f\u4e5f\u53ef\u4ee5 # 2. \u6587\u4ef6\u8def\u5f84\u5fc5\u987b\u5199\u5b8c\u6574\u8def\u5f84\uff0c\u56e0\u4e3aExcel\u7a0b\u5e8f\u65e0\u6cd5\u8bc6\u522bPython\u6587\u4ef6\u7684\u76ee\u5f55 # 3. win32com\u5e93\uff0c\u4f7f\u7528pip install pypiwin32\u5b89\u88c5 openpyxl\u5e93\u7684\u4f7f\u7528 openpyxl\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684Excel\u5904\u7406\u5e93\uff0c\u662f\u4e00\u4e2a\u6bd4\u8f83\u7efc\u5408\u7684\u5de5\u5177\uff0c\u80fd\u591f\u540c\u65f6\u8bfb\u53d6\u548c\u4fee\u6539Excel\u6587\u6863\u3002 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[59],"_links":{"self":[{"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/posts\/1371"}],"collection":[{"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/comments?post=1371"}],"version-history":[{"count":1,"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/posts\/1371\/revisions"}],"predecessor-version":[{"id":1372,"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/posts\/1371\/revisions\/1372"}],"wp:attachment":[{"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/media?parent=1371"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/categories?post=1371"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/c.ipcpu.com\/wp-json\/wp\/v2\/tags?post=1371"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}