openpyxl逐行读取xlsx文件，读取子表

from openpyxl import load_workbook

def get_newwords(read_file):
    wb = load_workbook(read_file)
    sh = wb["Sheet1"]        # "Sheet1"表示子表名称
    for item in list(sh.rows)[1:]:
        values = []
        for val in item:
            values.append(val.value)
        # values 存储的是xlsx的文件

读取子表

import pandas as pd

def read_excel(path):   # 读取多个子表
    data_xls = pd.io.excel.ExcelFile(path)
    data = []
    query_set = set()
    print(data_xls.sheet_names)    # 获取子表名称
    for name in data_xls.sheet_names:
        df = pd.read_excel(data_xls, sheet_name=name, header=None)
        query_set = query_set.union(set(df[0].unique()))
        query_set = query_set.union(set(df[1].unique()))
        data.append([name, len(df[0].unique())])  # 第一列中不重复的query
        # print(data[name][:4])
    return data, list(query_set)

按行遍历DataFame

for index, row in df.iterrows():
    print(index)   # 行号
    print([row[0], row[1])  # 输出第一第二列