Question

我要遍历每个CSV文件中具有标题/列名的许多CSV文件，然后将数据放入单个Excel文件中。但是每次标题/列名都被复制到Excel文件中，尽管它仅被复制到新行中，但是事实是，我只需要一次将标题/列名复制到excel文件中。

仅供参考，我正在使用Pandas的to_excel（）函数将数据放入Excel文件中。

谢谢。

这是我的代码：

import time
from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler
import pandas as pd
from openpyxl import load_workbook

class Watcher:
    DIRECTORY_TO_WATCH = "/home/viral/Testing"
def __init__(self):
    self.observer = Observer()

def run(self):
    event_handler = Handler()
    self.observer.schedule(event_handler, self.DIRECTORY_TO_WATCH, recursive=True)
    self.observer.start()
    try:
        while True:
            time.sleep(5)
    except:
        self.observer.stop()
        print("Error")

    self.observer.join()


class Handler(FileSystemEventHandler):

@staticmethod
def on_any_event(event):
    if event.is_directory:
        return None

    elif event.event_type == 'created':
        # Take any action here when a file is first created.
        print("Received created event - %s." % event.src_path)
        df = pd.read_csv(event.src_path, header=0)
        append_df_to_excel('/home/viral/myfile.xlsx', df, index = False)
        # all_data = pd.read_excel('/home/viral/myfile.xls')
        # combined = all_data.append(new_data)
        # combined.to_excel('myfile.xlsx', header = False)

    elif event.event_type == 'modified':
        # Taken any action here when a file is modified.
        print("Received modified event - %s." % event.src_path)

@staticmethod
def append_df_to_excel(filename, df, sheet_name='Sheet1', startrow=None,
                   truncate_sheet=False,
                   **to_excel_kwargs):
                   # ignore [engine] parameter if it was passed
    if 'engine' in to_excel_kwargs:
        to_excel_kwargs.pop('engine')

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

# Python 2.x: define [FileNotFoundError] exception if it doesn't exist
    try:
        FileNotFoundError
    except NameError:
        FileNotFoundError = IOError


    try:
        # 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}
    except FileNotFoundError:
    # file does not exist yet, we will create it
        pass

    if startrow is None:
        startrow = 0
    #if ((pd.read_excel(filename).column) is None):
        # write out the new sheet

        df.to_excel(writer, sheet_name, startrow=startrow, **to_excel_kwargs)
    #else:
        #df.to_excel(writer, sheet_name, startrow=startrow, **to_excel_kwargs, header=None)

    # save the workbook
    writer.save()

if __name__ == '__main__':
    w = Watcher()
    w.run()

Answer 1

信息有些有限，但是下面的方法可以解决问题。显然，您无需手动设置csv1，csv2数据框，而是阅读它们，例如，与read_csv。

如果这不是您想要的，请张贴您的当前代码以获取更多信息。

import pandas

cols = ["colname1", "colname2", "colname3"]
vals1 = [[1],[2],[3]]
vals2 = [[1000, 10000],[2000, 6000],[3000, 4000]]
csv1 = pandas.DataFrame({k:v for k,v in zip(cols, vals1)})
print(csv1)
csv2 = pandas.DataFrame({k:v for k,v in zip(cols, vals2)})
print(csv2)
outputdf = pandas.concat([csv1, csv2])
print(outputdf)
outputdf.to_excel("test.xlsx")

输出

检查Excel文件中的标题/列名称

1 个答案: