{"id":1140443,"date":"2025-01-08T22:21:00","date_gmt":"2025-01-08T14:21:00","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1140443.html"},"modified":"2025-01-08T22:21:02","modified_gmt":"2025-01-08T14:21:02","slug":"python%e5%a6%82%e4%bd%95%e5%8f%96excel%e4%b8%ad2%e4%b8%aa%e6%95%b0%e6%8d%ae%e5%ba%93","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1140443.html","title":{"rendered":"python\u5982\u4f55\u53d6excel\u4e2d2\u4e2a\u6570\u636e\u5e93"},"content":{"rendered":"

\"python\u5982\u4f55\u53d6excel\u4e2d2\u4e2a\u6570\u636e\u5e93\"<\/p>\n

Python\u53ef\u4ee5\u901a\u8fc7\u591a\u79cd\u65b9\u5f0f\u4eceExcel\u6587\u4ef6\u4e2d\u63d0\u53d6\u6570\u636e\uff0c\u5305\u62ec\u4f7f\u7528Pandas\u5e93\u3001Openpyxl\u5e93\u3001xlrd\u5e93\u7b49\u3002<\/strong>\u5176\u4e2d\uff0cPandas\u5e93<\/strong>\u662f\u6700\u5e38\u7528\u7684\u5de5\u5177\uff0c\u56e0\u4e3a\u5b83\u4e0d\u4ec5\u80fd\u591f\u5904\u7406Excel\u6587\u4ef6\uff0c\u8fd8\u53ef\u4ee5\u8fdb\u884c\u6570\u636e\u5206\u6790\u548c\u64cd\u4f5c\uff0c\u529f\u80fd\u975e\u5e38\u5f3a\u5927\u3002\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Pandas\u5e93\u4eceExcel\u6587\u4ef6\u4e2d\u63d0\u53d6\u4e24\u4e2a\u6570\u636e\u5e93\u3002<\/p>\n<\/p>\n

\u4f7f\u7528Pandas\u8bfb\u53d6Excel\u6587\u4ef6\u7684\u6b65\u9aa4\u5305\u62ec\uff1a\u5b89\u88c5Pandas\u5e93\u3001\u4f7f\u7528pd.read_excel()<\/code>\u51fd\u6570\u8bfb\u53d6Excel\u6587\u4ef6\u3001\u6307\u5b9a\u8981\u8bfb\u53d6\u7684\u5de5\u4f5c\u8868\u540d\u79f0\u6216\u7d22\u5f15\u3001\u5904\u7406\u8bfb\u53d6\u7684\u6570\u636e<\/strong>\u3002\u4e0b\u9762\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u8ba8\u8bba\u8fd9\u4e9b\u6b65\u9aa4\uff0c\u5e76\u5c55\u793a\u5982\u4f55\u7ed3\u5408\u5176\u4ed6\u65b9\u6cd5\uff0c\u5982Openpyxl\u5e93\u548cxlrd\u5e93\uff0c\u4ee5\u786e\u4fdd\u4f60\u80fd\u591f\u987a\u5229\u5b8c\u6210\u4efb\u52a1\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u5b89\u88c5\u548c\u5bfc\u5165\u6240\u9700\u5e93<\/h3>\n<\/p>\n

\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u786e\u4fdd\u4f60\u5df2\u7ecf\u5b89\u88c5\u4e86Pandas\u5e93\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install pandas<\/p>\n
pip install openpyxl<\/p>\n
pip install xlrd<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u5728\u4f60\u7684Python\u811a\u672c\u4e2d\u5bfc\u5165Pandas\u5e93\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Pandas\u8bfb\u53d6Excel\u6587\u4ef6<\/h3>\n<\/p>\n
Pandas\u7684read_excel()<\/code>\u51fd\u6570<\/strong>\u662f\u8bfb\u53d6Excel\u6587\u4ef6\u7684\u4e3b\u8981\u5de5\u5177\u3002\u4f60\u53ef\u4ee5\u6307\u5b9a\u8981\u8bfb\u53d6\u7684\u6587\u4ef6\u8def\u5f84\u3001\u5de5\u4f5c\u8868\u540d\u79f0\u6216\u7d22\u5f15\u7b49\u53c2\u6570\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
# \u8bfb\u53d6Excel\u6587\u4ef6\u4e2d\u7684\u4e24\u4e2a\u5de5\u4f5c\u8868<\/p>\n
df1 = pd.read_excel('data.xlsx', sheet_name='Sheet1')<\/p>\n
df2 = pd.read_excel('data.xlsx', sheet_name='Sheet2')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u5904\u7406\u8bfb\u53d6\u7684\u6570\u636e<\/h3>\n<\/p>\n
\u5728\u6210\u529f\u8bfb\u53d6\u6570\u636e\u540e\uff0c\u4f60\u53ef\u4ee5\u5bf9\u6570\u636e\u8fdb\u884c\u5404\u79cd\u64cd\u4f5c\uff0c\u5982\u6570\u636e\u6e05\u6d17\u3001\u5206\u6790\u3001\u5408\u5e76\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u6570\u636e\u5904\u7406\u64cd\u4f5c\uff1a<\/p>\n<\/p>\n
1\u3001\u67e5\u770b\u6570\u636e<\/h4>\n<\/p>\n
\u4f60\u53ef\u4ee5\u4f7f\u7528head()<\/code>\u51fd\u6570\u67e5\u770b\u6570\u636e\u7684\u524d\u51e0\u884c\uff1a<\/p>\n<\/p>\n
print(df1.head())<\/p>\n
print(df2.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u6570\u636e\u6e05\u6d17<\/h4>\n<\/p>\n
\u6570\u636e\u6e05\u6d17\u662f\u6570\u636e\u5206\u6790\u7684\u4e00\u4e2a\u91cd\u8981\u6b65\u9aa4\u3002\u4f60\u53ef\u80fd\u9700\u8981\u5220\u9664\u7f3a\u5931\u503c\u3001\u5904\u7406\u91cd\u590d\u6570\u636e\u7b49\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
# \u5220\u9664\u7f3a\u5931\u503c<\/p>\n
df1.dropna(inplace=True)<\/p>\n
df2.dropna(inplace=True)<\/p>\n
\u5220\u9664\u91cd\u590d\u884c<\/strong><\/h2>\n
df1.drop_duplicates(inplace=True)<\/p>\n
df2.drop_duplicates(inplace=True)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u6570\u636e\u5408\u5e76<\/h4>\n<\/p>\n
\u5982\u679c\u4f60\u9700\u8981\u5c06\u4e24\u4e2a\u6570\u636e\u8868\u5408\u5e76\uff0c\u53ef\u4ee5\u4f7f\u7528merge()<\/code>\u51fd\u6570\u3002\u4f8b\u5982\uff0c\u6309\u67d0\u4e2a\u5171\u540c\u5217\u5408\u5e76\u4e24\u4e2a\u6570\u636e\u8868\uff1a<\/p>\n<\/p>\n
merged_df = pd.merge(df1, df2, on='common_column')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u4ece\u591a\u4e2aExcel\u6587\u4ef6\u8bfb\u53d6\u6570\u636e<\/h3>\n<\/p>\n
\u6709\u65f6\u5019\uff0c\u4f60\u53ef\u80fd\u9700\u8981\u4ece\u591a\u4e2aExcel\u6587\u4ef6\u4e2d\u8bfb\u53d6\u6570\u636e\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e2a\u5faa\u73af\u6765\u8bfb\u53d6\u6bcf\u4e2a\u6587\u4ef6\u4e2d\u7684\u6570\u636e\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
import os<\/p>\n
\u83b7\u53d6\u5f53\u524d\u76ee\u5f55\u4e0b\u6240\u6709Excel\u6587\u4ef6<\/strong><\/h2>\n
files = [f for f in os.listdir('.') if f.endswith('.xlsx')]<\/p>\n
\u8bfb\u53d6\u6240\u6709\u6587\u4ef6\u4e2d\u7684\u6570\u636e<\/strong><\/h2>\n
data_frames = []<\/p>\n
for file in files:<\/p>\n
    df = pd.read_excel(file, sheet_name='Sheet1')<\/p>\n
    data_frames.append(df)<\/p>\n
\u5408\u5e76\u6240\u6709\u6570\u636e<\/strong><\/h2>\n
all_data = pd.concat(data_frames)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u4f7f\u7528Openpyxl\u548cxlrd\u5e93<\/h3>\n<\/p>\n
\u5c3d\u7ba1Pandas\u5e93\u975e\u5e38\u5f3a\u5927\uff0c\u6709\u65f6\u5019\u4f60\u53ef\u80fd\u9700\u8981\u4f7f\u7528\u5176\u4ed6\u5e93\u6765\u5904\u7406\u4e00\u4e9b\u7279\u6b8a\u9700\u6c42\u3002\u4f8b\u5982\uff0c\u4f7f\u7528Openpyxl\u5e93\u8bfb\u53d6Excel\u6587\u4ef6\uff1a<\/p>\n<\/p>\n
from openpyxl import load_workbook<\/p>\n
\u6253\u5f00Excel\u6587\u4ef6<\/strong><\/h2>\n
wb = load_workbook('data.xlsx')<\/p>\n
\u83b7\u53d6\u5de5\u4f5c\u8868<\/strong><\/h2>\n
sheet1 = wb['Sheet1']<\/p>\n
sheet2 = wb['Sheet2']<\/p>\n
\u83b7\u53d6\u6570\u636e<\/strong><\/h2>\n
data1 = sheet1.values<\/p>\n
data2 = sheet2.values<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u6216\u8005\u4f7f\u7528xlrd\u5e93\uff1a<\/p>\n<\/p>\n
import xlrd<\/p>\n
\u6253\u5f00Excel\u6587\u4ef6<\/strong><\/h2>\n
wb = xlrd.open_workbook('data.xlsx')<\/p>\n
\u83b7\u53d6\u5de5\u4f5c\u8868<\/strong><\/h2>\n
sheet1 = wb.sheet_by_name('Sheet1')<\/p>\n
sheet2 = wb.sheet_by_name('Sheet2')<\/p>\n
\u83b7\u53d6\u6570\u636e<\/strong><\/h2>\n
data1 = [sheet1.row_values(row) for row in range(sheet1.nrows)]<\/p>\n
data2 = [sheet2.row_values(row) for row in range(sheet2.nrows)]<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u4f60\u5e94\u8be5\u80fd\u591f\u4f7f\u7528Pandas\u5e93\u4eceExcel\u6587\u4ef6\u4e2d\u63d0\u53d6\u4e24\u4e2a\u6570\u636e\u5e93\uff0c\u5e76\u5bf9\u6570\u636e\u8fdb\u884c\u5404\u79cd\u64cd\u4f5c\u3002Pandas\u5e93\u529f\u80fd\u5f3a\u5927\u4e14\u6613\u4e8e\u4f7f\u7528\uff0c\u662f\u5904\u7406Excel\u6587\u4ef6\u7684\u9996\u9009\u5de5\u5177\u3002Openpyxl\u548cxlrd\u5e93\u4e5f\u63d0\u4f9b\u4e86\u4e00\u4e9b\u6709\u7528\u7684\u529f\u80fd\uff0c\u53ef\u4ee5\u5e2e\u52a9\u4f60\u5904\u7406\u7279\u6b8a\u9700\u6c42\u3002\u5e0c\u671b\u8fd9\u4e9b\u4fe1\u606f\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff01<\/p>\n<\/p>\n
\u53c2\u8003\u8d44\u6599<\/h3>\n<\/p>\n