使用python将现有excel工作表附加到新的数据框中

Question

我现在有这个代码。它工作得很好

它在文件夹中的excel文件中循环， 删除前两行，然后将其保存为单个excel文件， 它还将循环中的文件保存为附加文件

当前，每次运行代码时，附加的文件将覆盖现有文件

我需要将新数据附加到现有excel工作表的底部（'master_data.xlsx）

dfList = []
path = 'C:\\Test\\TestRawFile' 
newpath = 'C:\\Path\\To\\New\\Folder'

for fn in os.listdir(path): 
  # Absolute file path
  file = os.path.join(path, fn)
  if os.path.isfile(file): 
    # Import the excel file and call it xlsx_file 
    xlsx_file = pd.ExcelFile(file) 
    # View the excel files sheet names 
    xlsx_file.sheet_names 
    # Load the xlsx files Data sheet as a dataframe 
    df = xlsx_file.parse('Sheet1',header= None) 
    df_NoHeader = df[2:] 
    data = df_NoHeader 
    # Save individual dataframe
    data.to_excel(os.path.join(newpath, fn))

    dfList.append(data) 

appended_data = pd.concat(dfList)
appended_data.to_excel(os.path.join(newpath, 'master_data.xlsx'))

我以为这是一项简单的任务，但我想不是。 我想我需要将master_data.xlsx文件作为数据帧引入，然后将索引与新附加的数据进行匹配，并将其保存回原处。或者有更简单的方法。感谢您的帮助

Answer 1

如果每次在工作表上使用ExcelWriter，它将覆盖上一个工作表，并且所有可见的内容都是附加到工作簿的最后一个数据表。 相反，您可以维护一个最初为1的计数器，您需要为其初始化excel工作表，并使用现有的方法添加初始数据

writer = pd.ExcelWriter(output_file, engine='openpyxl')

df = pd.read_excel(output_file, sheet_name='TestSheet1')

或者你可以使用我使用的以下方法。若要在下次使用工作簿时加载工作簿，或在第一种情况下尝试加载工作簿时，文件未发现异常

用法：

from bs4 import BeautifulSoup
import requests
import pandas as pd
from openpyxl import load_workbook

urls = ["http://millenniumcricketleague.com/Home/ShowTeam.aspx?tid=22",
        "http://millenniumcricketleague.com/Home/ShowTeam.aspx?tid=40"]
path = "F:\meta_1.xlsx"
writer = pd.ExcelWriter(path,engine='openpyxl')
counter = 1
for url in urls:
    table_data = []
    final = []
    html_content = requests.get(url).text
    soup = BeautifulSoup(html_content, "lxml")
    x = soup.find_all('table')
    for table in x[1:]:
        for tr in table.find_all("tr"):
            newrow = []
            for td in tr.find_all("td"):
                newrow.append(td.text.replace('\n', ' ').strip())
            table_data.append(newrow)
    df = pd.DataFrame(table_data)
    sheetname = 'Sheet%s' % counter
    if(counter!=1):
        writer.book = load_workbook(path)
    df.to_excel(writer, sheet_name=sheetname)
    counter = counter + 1
    writer.save()

无需关闭excelwriter。这是一个自动功能。如果您明确定义，将显示警告

Answer 2

如果您没有严格地查找excel文件，则将输出作为csv文件，并将csv复制到新的excel文件中

df.to_csv('filepath', mode='a', index = False, header=None)

模式='a'

手段附加

这是一个迂回的方式，但工程整洁

Answer 3

请在下面找到一个用于将数据框附加到现有Excel文件的帮助函数

如果Excel文件不存在，则将创建它

---

更新[2021-09-12]：针对熊猫1.3.0+

以下功能已通过以下测试：

• 熊猫1.3.2
• OpenPyxl 3.0.7

from pathlib import Path
from copy import copy
from typing import Union, Optional
import numpy as np
import pandas as pd
import openpyxl
from openpyxl import load_workbook
from openpyxl.utils import get_column_letter


def copy_excel_cell_range(
        src_ws: openpyxl.worksheet.worksheet.Worksheet,
        min_row: int = None,
        max_row: int = None,
        min_col: int = None,
        max_col: int = None,
        tgt_ws: openpyxl.worksheet.worksheet.Worksheet = None,
        tgt_min_row: int = 1,
        tgt_min_col: int = 1,
        with_style: bool = True
) -> openpyxl.worksheet.worksheet.Worksheet:
    """
    copies all cells from the source worksheet [src_ws] starting from [min_row] row
    and [min_col] column up to [max_row] row and [max_col] column
    to target worksheet [tgt_ws] starting from [tgt_min_row] row
    and [tgt_min_col] column.

    @param src_ws:  source worksheet
    @param min_row: smallest row index in the source worksheet (1-based index)
    @param max_row: largest row index in the source worksheet (1-based index)
    @param min_col: smallest column index in the source worksheet (1-based index)
    @param max_col: largest column index in the source worksheet (1-based index)
    @param tgt_ws:  target worksheet.
                    If None, then the copy will be done to the same (source) worksheet.
    @param tgt_min_row: target row index (1-based index)
    @param tgt_min_col: target column index (1-based index)
    @param with_style:  whether to copy cell style. Default: True

    @return: target worksheet object
    """
    if tgt_ws is None:
        tgt_ws = src_ws

    # https://stackoverflow.com/a/34838233/5741205
    for row in src_ws.iter_rows(min_row=min_row, max_row=max_row,
                                min_col=min_col, max_col=max_col):
        for cell in row:
            tgt_cell = tgt_ws.cell(
                row=cell.row + tgt_min_row - 1,
                column=cell.col_idx + tgt_min_col - 1,
                value=cell.value
            )
            if with_style and cell.has_style:
                # tgt_cell._style = copy(cell._style)
                tgt_cell.font = copy(cell.font)
                tgt_cell.border = copy(cell.border)
                tgt_cell.fill = copy(cell.fill)
                tgt_cell.number_format = copy(cell.number_format)
                tgt_cell.protection = copy(cell.protection)
                tgt_cell.alignment = copy(cell.alignment)
    return tgt_ws


def append_df_to_excel(
        filename: Union[str, Path],
        df: pd.DataFrame,
        sheet_name: str = 'Sheet1',
        startrow: Optional[int] = None,
        max_col_width: int = 30,
        autofilter: bool = False,
        fmt_int: str = "#,##0",
        fmt_float: str = "#,##0.00",
        fmt_date: str = "yyyy-mm-dd",
        fmt_datetime: str = "yyyy-mm-dd hh:mm",
        truncate_sheet: bool = False,
        storage_options: Optional[dict] = None,
        **to_excel_kwargs
) -> None:
    """
    Append a DataFrame [df] to existing Excel file [filename]
    into [sheet_name] Sheet.
    If [filename] doesn't exist, then this function will create it.

    @param filename: File path or existing ExcelWriter
                     (Example: '/path/to/file.xlsx')
    @param df: DataFrame to save to workbook
    @param sheet_name: Name of sheet which will contain DataFrame.
                       (default: 'Sheet1')
    @param startrow: upper left cell row to dump data frame.
                     Per default (startrow=None) calculate the last row
                     in the existing DF and write to the next row...
    @param max_col_width: maximum column width in Excel. Default: 40
    @param autofilter: boolean - whether add Excel autofilter or not. Default: False
    @param fmt_int: Excel format for integer numbers
    @param fmt_float: Excel format for float numbers
    @param fmt_date: Excel format for dates
    @param fmt_datetime: Excel format for datetime's
    @param truncate_sheet: truncate (remove and recreate) [sheet_name]
                           before writing DataFrame to Excel file
    @param storage_options: dict, optional
        Extra options that make sense for a particular storage connection, e.g. host, port,
        username, password, etc., if using a URL that will be parsed by fsspec, e.g.,
        starting “s3://”, “gcs://”.
    @param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
                            [can be a dictionary]
    @return: None

    Usage examples:

    >>> append_df_to_excel('/tmp/test.xlsx', df, autofilter=True,
                           freeze_panes=(1,0))

    >>> append_df_to_excel('/tmp/test.xlsx', df, header=None, index=False)

    >>> append_df_to_excel('/tmp/test.xlsx', df, sheet_name='Sheet2',
                           index=False)

    >>> append_df_to_excel('/tmp/test.xlsx', df, sheet_name='Sheet2',
                           index=False, startrow=25)

    >>> append_df_to_excel('/tmp/test.xlsx', df, index=False,
                           fmt_datetime="dd.mm.yyyy hh:mm")

    (c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
    """
    def set_column_format(ws, column_letter, fmt):
        for cell in ws[column_letter]:
            cell.number_format = fmt
    filename = Path(filename)
    file_exists = filename.is_file()
    # process parameters
    # calculate first column number
    # if the DF will be written using `index=True`, then `first_col = 2`, else `first_col = 1`
    first_col = int(to_excel_kwargs.get("index", True)) + 1
    # ignore [engine] parameter if it was passed
    if 'engine' in to_excel_kwargs:
        to_excel_kwargs.pop('engine')
    # save content of existing sheets
    if file_exists:
        wb = load_workbook(filename)
        sheet_names = wb.sheetnames
        sheet_exists = sheet_name in sheet_names
        sheets = {ws.title: ws for ws in wb.worksheets}

    with pd.ExcelWriter(
        filename.with_suffix(".xlsx"),
        engine="openpyxl",
        mode="a" if file_exists else "w",
        if_sheet_exists="new" if file_exists else None,
        date_format=fmt_date,
        datetime_format=fmt_datetime,
        storage_options=storage_options
    ) as writer:
        if file_exists:
            # try to open an existing workbook
            writer.book = wb
            # get the last row in the existing Excel sheet
            # if it was not specified explicitly
            if startrow is None and sheet_name in writer.book.sheetnames:
                startrow = writer.book[sheet_name].max_row
            # truncate sheet
            if truncate_sheet and sheet_name in writer.book.sheetnames:
                # index of [sheet_name] sheet
                idx = writer.book.sheetnames.index(sheet_name)
                # remove [sheet_name]
                writer.book.remove(writer.book.worksheets[idx])
                # create an empty sheet [sheet_name] using old index
                writer.book.create_sheet(sheet_name, idx)
            # copy existing sheets
            writer.sheets = sheets
        else:
            # file doesn't exist, we are creating a new one
            startrow = 0

        # write out the DataFrame to an ExcelWriter
        df.to_excel(writer, sheet_name=sheet_name, **to_excel_kwargs)
        worksheet = writer.sheets[sheet_name]

        if autofilter:
            worksheet.auto_filter.ref = worksheet.dimensions

        for xl_col_no, dtyp in enumerate(df.dtypes, first_col):
            col_no = xl_col_no - first_col
            width = max(df.iloc[:, col_no].astype(str).str.len().max(),
                        len(df.columns[col_no]) + 6)
            width = min(max_col_width, width)
            column_letter = get_column_letter(xl_col_no)
            worksheet.column_dimensions[column_letter].width = width
            if np.issubdtype(dtyp, np.integer):
                set_column_format(worksheet, column_letter, fmt_int)
            if np.issubdtype(dtyp, np.floating):
                set_column_format(worksheet, column_letter, fmt_float)

    if file_exists and sheet_exists:
        # move (append) rows from new worksheet to the `sheet_name` worksheet
        wb = load_workbook(filename)
        # retrieve generated worksheet name
        new_sheet_name = set(wb.sheetnames) - set(sheet_names)
        if new_sheet_name:
            new_sheet_name = list(new_sheet_name)[0]
        # copy rows written by `df.to_excel(...)` to
        copy_excel_cell_range(
            src_ws=wb[new_sheet_name],
            tgt_ws=wb[sheet_name],
            tgt_min_row=startrow + 1,
            with_style=True
        )
        # remove new (generated by Pandas) worksheet
        del wb[new_sheet_name]
        wb.save(filename)
        wb.close()

---

旧版本（使用Pandas 1.2.3和Openpyxl 3.0.5测试）：

&13； 第13部分,；

import os
from openpyxl import load_workbook


def append_df_to_excel(filename, df, sheet_name='Sheet1', startrow=None,
                       truncate_sheet=False, 
                       **to_excel_kwargs):
    """
    Append a DataFrame [df] to existing Excel file [filename]
    into [sheet_name] Sheet.
    If [filename] doesn't exist, then this function will create it.

    @param filename: File path or existing ExcelWriter
                     (Example: '/path/to/file.xlsx')
    @param df: DataFrame to save to workbook
    @param sheet_name: Name of sheet which will contain DataFrame.
                       (default: 'Sheet1')
    @param startrow: upper left cell row to dump data frame.
                     Per default (startrow=None) calculate the last row
                     in the existing DF and write to the next row...
    @param truncate_sheet: truncate (remove and recreate) [sheet_name]
                           before writing DataFrame to Excel file
    @param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
                            [can be a dictionary]
    @return: None

    Usage examples:

    >>> append_df_to_excel('d:/temp/test.xlsx', df)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, header=None, index=False)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
                           index=False)

    >>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2', 
                           index=False, startrow=25)

    (c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
    """
    # Excel file doesn't exist - saving and exiting
    if not os.path.isfile(filename):
        df.to_excel(
            filename,
            sheet_name=sheet_name, 
            startrow=startrow if startrow is not None else 0, 
            **to_excel_kwargs)
        return
    
    # ignore [engine] parameter if it was passed
    if 'engine' in to_excel_kwargs:
        to_excel_kwargs.pop('engine')

    writer = pd.ExcelWriter(filename, engine='openpyxl', mode='a')

    # try to open an existing workbook
    writer.book = load_workbook(filename)
    
    # get the last row in the existing Excel sheet
    # if it was not specified explicitly
    if startrow is None and sheet_name in writer.book.sheetnames:
        startrow = writer.book[sheet_name].max_row

    # truncate sheet
    if truncate_sheet and sheet_name in writer.book.sheetnames:
        # index of [sheet_name] sheet
        idx = writer.book.sheetnames.index(sheet_name)
        # remove [sheet_name]
        writer.book.remove(writer.book.worksheets[idx])
        # create an empty sheet [sheet_name] using old index
        writer.book.create_sheet(sheet_name, idx)
    
    # copy existing sheets
    writer.sheets = {ws.title:ws for ws in writer.book.worksheets}

    if startrow is None:
        startrow = 0

    # write out the new sheet
    df.to_excel(writer, sheet_name, startrow=startrow, **to_excel_kwargs)

    # save the workbook
    writer.save()

；

和#13；