pandas读取excel时获取读取进度的实现

def get_sheet_data(self, sheet, convert_float: bool) -> List[List[Scalar]]:
        # GH 39001
        # Reading of excel file depends on dimension data being correct but
        # writers sometimes omit or get it wrong
        import openpyxl

        version = LooseVersion(get_version(openpyxl))

        # There is no Good way of determining if a sheet is read-only
        # https://foss.heptapod.net/openpyxl/openpyxl/-/issues/1605
        is_readonly = hasattr(sheet, "reset_dimensions")

        if version >= "3.0.0" and is_readonly:
            sheet.reset_dimensions()

        data: List[List[Scalar]] = []
        last_row_with_data = -1
        for row_number, row in enumerate(sheet.rows):
            converted_row = [self._convert_cell(cell, convert_float) for cell in row]
            if not all(cell == "" for cell in converted_row):
                last_row_with_data = row_number
            data.append(converted_row)

        # Trim trailing empty rows
        data = data[: last_row_with_data + 1]

        if version >= "3.0.0" and is_readonly and len(data) > 0:
            # With dimension reset, openpyxl no longer pads rows
            max_width = max(len(data_row) for data_row in data)
            if min(len(data_row) for data_row in data) < max_width:
                empty_cell: List[Scalar] = [""]
                data = [
                    data_row + (max_width - len(data_row)) * empty_cell
                    for data_row in data
                ]

        return data

import pandas as pd
from datetime import datetime

'''
定义回调函数
cur: 读取时的当前行数
tt: 读取文件的总行数
'''
def show_pd_read_excel_progress(cur, tt):
    # 进度数值
    progress = " {:.2f}%".fORMat(cur/tt*100)
    # 进度条
    bar = " ".join("█" for _ in range(int(cur/tt*100/10)))
    # 显示进度
    print("\r进度:" + bar + progress, end="", flush=True)

# 记录开始时间
t = datetime.now()
# 开始读取excel
print("pd.read_excel: test_4.xlsx...")
xl_data = pd.read_excel("test_4.xlsx", callback=show_pd_read_excel_progress)
# 打印excel头几行
print(xl_data.head())
print("\n")
# 显示花费的时间
print("Time spent:", datetime.now()-t)

def read_excel(
    io,
    sheet_name=0,
    header=0,
    names=None,
    index_col=None,
    usecols=None,
    squeeze=False,
    dtype=None,
    engine=None,
    converters=None,
    true_values=None,
    false_values=None,
    skiprows=None,
    nrows=None,
    na_values=None,
    keep_default_na=True,
    na_filter=True,
    verbose=False,
    parse_dates=False,
    date_parser=None,
    thousands=None,
    comment=None,
    skipfooter=0,
    convert_float=True,
    mangle_dupe_cols=True,
    storage_options: StorageOptions = None,
    callback = None, # 增加callback参数
):

    should_close = False
    if not isinstance(io, ExcelFile):
        should_close = True
        io = ExcelFile(io, storage_options=storage_options, engine=engine)
    elif engine and engine != io.engine:
        raise ValueError(
            "Engine should not be specified when passing "
            "an ExcelFile - ExcelFile already has the engine set"
        )

    try:
        data = io.parse(
            sheet_name=sheet_name,
            header=header,
            names=names,
            index_col=index_col,
            usecols=usecols,
            squeeze=squeeze,
            dtype=dtype,
            converters=converters,
            true_values=true_values,
            false_values=false_values,
            skiprows=skiprows,
            nrows=nrows,
            na_values=na_values,
            keep_default_na=keep_default_na,
            na_filter=na_filter,
            verbose=verbose,
            parse_dates=parse_dates,
            date_parser=date_parser,
            thousands=thousands,
            comment=comment,
            skipfooter=skipfooter,
            convert_float=convert_float,
            mangle_dupe_cols=mangle_dupe_cols,
            callback = callback, # 增加callback参数
        )
    finally:
        # make sure to close opened file handles
        if should_close:
            io.close()
    return data
... # 省略代码

def parse(
        self,
        sheet_name=0,
        header=0,
        names=None,
        index_col=None,
        usecols=None,
        squeeze=False,
        dtype=None,
        true_values=None,
        false_values=None,
        skiprows=None,
        nrows=None,
        na_values=None,
        verbose=False,
        parse_dates=False,
        date_parser=None,
        thousands=None,
        comment=None,
        skipfooter=0,
        convert_float=True,
        mangle_dupe_cols=True,
        callback = None, # 增加callback参数
        **kwds,
    ):
... # 省略代码

for asheetname in sheets:
            if verbose:
                print(f"Reading sheet {asheetname}")

            if isinstance(asheetname, str):
                sheet = self.get_sheet_by_name(asheetname)
            else:  # assume an integer if not a string
                sheet = self.get_sheet_by_index(asheetname)

            data = self.get_sheet_data(sheet, convert_float, callback) # 传递callback参数给get_sheet_data方法
            usecols = maybe_convert_usecols(usecols)
... # 省略代码

def get_sheet_data(self, sheet, convert_float: bool, callback) -> List[List[Scalar]]: # 传递参数增加callback
        # GH 39001
        # Reading of excel file depends on dimension data being correct but
        # writers sometimes omit or get it wrong
        import openpyxl
				# 获取sheet的总行数
        max_row = sheet.max_row
        print("sheet_max_row:", sheet.max_row)

        version = LooseVersion(get_version(openpyxl))

        # There is no good way of determining if a sheet is read-only
        # Https://foss.heptapod.net/openpyxl/openpyxl/-/issues/1605
        is_readonly = hasattr(sheet, "reset_dimensions")

        if version >= "3.0.0" and is_readonly:
            sheet.reset_dimensions()

        data: List[List[Scalar]] = []
        last_row_with_data = -1
        for row_number, row in enumerate(sheet.rows):
						# 调用回调函数
            if callback is not None:
                callback(row_number+1, max_row)
            converted_row = [self._convert_cell(cell, convert_float) for cell in row]
            if not all(cell == "" for cell in converted_row):
                last_row_with_data = row_number
            data.append(converted_row)

        # Trim trailing empty rows
        data = data[: last_row_with_data + 1]

        if version >= "3.0.0" and is_readonly and len(data) > 0:
            # With dimension reset, openpyxl no longer pads rows
            max_width = max(len(data_row) for data_row in data)
            if min(len(data_row) for data_row in data) < max_width:
                empty_cell: List[Scalar] = [""]
                data = [
                    data_row + (max_width - len(data_row)) * empty_cell
                    for data_row in data
                ]

        return data