Python实现批量提取Excel数据

pip install pandas openpyxl

import pandas as pd

# 读取 Excel 文件
df = pd.read_excel('data.xlsx')

# 显示前几行数据
print(df.head())

import os

# 存放 Excel 文件的文件夹路径
folder_path = 'path_to_folder'

# 获取所有 Excel 文件路径
file_list = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.endswith('.xlsx')]

# 初始化一个空的 DataFrame
all_data = pd.DataFrame()

# 逐个读取并合并
for file in file_list:
    df = pd.read_excel(file)
    all_data = all_data.append(df, ignore_index=True)

# 显示合并后的数据
print(all_data.head())

pip install openpyxl

from openpyxl import load_workbook

# 加载 Excel 文件
wb = load_workbook('data.xlsx')

# 选择活动工作表
ws = wb.active

# 读取所有数据
data = []
for row in ws.iter_rows(values_only=True):
    data.append(row)

# 打印数据
for row in data:
    print(row)

import os
from openpyxl import load_workbook

# 存放 Excel 文件的文件夹路径
folder_path = 'path_to_folder'

# 获取所有 Excel 文件路径
file_list = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.endswith('.xlsx')]

# 初始化一个空的列表
all_data = []

# 逐个读取并合并
for file in file_list:
    wb = load_workbook(file)
    ws = wb.active
    for row in ws.iter_rows(values_only=True):
        all_data.append(row)

# 打印合并后的数据
for row in all_data:
    print(row)

pip install xlrd

import xlrd

# 打开 Excel 文件
workbook = xlrd.open_workbook('data.xls')

# 选择工作表
sheet = workbook.sheet_by_index(0)

# 读取所有数据
data = []
for row_idx in range(sheet.nrows):
    row = sheet.row_values(row_idx)
    data.append(row)

# 打印数据
for row in data:
    print(row)

import os
import xlrd

# 存放 Excel 文件的文件夹路径
folder_path = 'path_to_folder'

# 获取所有 Excel 文件路径
file_list = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.endswith('.xls') or f.endswith('.xlsx')]

# 初始化一个空的列表
all_data = []

# 逐个读取并合并
for file in file_list:
    workbook = xlrd.open_workbook(file)
    sheet = workbook.sheet_by_index(0)
    for row_idx in range(sheet.nrows):
        row = sheet.row_values(row_idx)
        all_data.append(row)

# 打印合并后的数据
for row in all_data:
    print(row)