Python讀寫文件的幾種方式

1、pandas

pandas模塊是數據分析的大殺器，它使得對於文件相關的操做變得簡單。

看一下它的簡單使用

import pandas as pd

# 讀取
df = pd.read_csv('all_forum_info.csv')
print(df.info())

# 寫入
df.to_csv('data.csv')

具體用法參照個人博客pandas系列 http://www.javashuo.com/article/p-cpbmpkek-bm.html

2、csv

1.讀取

import csv

# 讀取
with open('all_forum_info.csv', encoding='utf-8') as myFile:
    lines = csv.reader(myFile)
    for line in lines:
        print(line)

['hgroup', 'forum_topic', 'forum_url', 'count_topic', 'count_post']
['Welcome to Breastcancer.org', 'Info & Resources for New Patients & Members - Please No Posts!', 'https://community.breastcancer.org/forum/131', '11', '11']
['Welcome to Breastcancer.org', 'Acknowledging and honoring our Community', 'https://community.breastcancer.org/forum/135', '111', '5,372']
['Not Diagnosed but Concerned', 'Not Diagnosed But Worried', 'https://community.breastcancer.org/forum/83', '16,638', '133,217']
['Not Diagnosed but Concerned', 'Waiting for Test Results', 'https://community.breastcancer.org/forum/62', '6,712', '62,439']
['Not Diagnosed but Concerned', 'Benign Breast Conditions', 'https://community.breastcancer.org/forum/148', '795', '4,094']
['Not Diagnosed but Concerned', 'High Risk for Breast Cancer', 'https://community.breastcancer.org/forum/47', '2,146', '23,435']
['Tests, Treatments & Side Effects', 'Just Diagnosed', 'https://community.breastcancer.org/forum/5', '6,894', '103,851']
['Tests, Treatments & Side Effects', 'Diagnosed and Waiting for Test Results', 'https://community.breastcancer.org/forum/147', '592', '6,442']

2. 寫入

"""
寫入
'w'表示寫模式。
首先open()函數打開當前路徑下的名字爲't.csv'的文件，若是不存在這個文件，則建立它，返回myFile文件對象。
csv.writer(myFile)返回writer對象myWriter。
writerow()方法是一行一行寫入，writerows方法是一次寫入多行。
注意：若是文件't.csv'事先存在，調用writer函數會先清空原文件中的文本，再執行writerow/writerows方法。
"""

with open('data.csv', 'w', encoding='utf-8') as myFile:
    myWriter = csv.writer(myFile)
    myWriter.writerow(['title', '數學'])
    myWriter.writerow([8, 'h'])
    myList = [[1, 2, 3], [4, 5, 6]]
    myWriter.writerows(myList)

data.csv

title,數學
8,h
1,2,3
4,5,6

修改分割符

csv.register_dialect('mydialect', delimiter='|', quoting=csv.QUOTE_ALL)
with open('test.csv', 'r') as myFile:
    lines = csv.reader(myFile, 'mydialect')
    # print(lines.line_num)
    for line in lines:
        print(line)

['1', '2', '3']
['2', '3', '4']　　

3、xlrd, xlwt

1. 讀取

import xlrd

myWorkbook = xlrd.open_workbook('data.xlsx')

# 讀取excel的三種方式

# 方式一
mySheets = myWorkbook.sheets()  # 獲取工做表list。
mySheet = mySheets[0]  # 經過索引順序獲取。
# 方式二
# mySheet1 = myWorkbook.sheet_by_index(0)  # 經過索引順序獲取。
# 方式三
# mySheet2 = myWorkbook.sheet_by_name('table')  # 經過名稱獲取。

# 獲取行數和列數
nrows = mySheet.nrows
ncols = mySheet.ncols
print(nrows, ncols)

# 獲取一行和一列
myRowValues = mySheet.row_values(0)  # i是行數，從0開始計數，返回list對象。

myColValues = mySheet.col_values(0)  # i是列數，從0開始計數，返回list對象。

print(myRowValues, myColValues)

# 讀取單元格數據
# myCell = mySheet.cell(0, 0)  # 獲取單元格，i是行數，j是列數，行數和列數都是從0開始計數。
# myCellValue = myCell.value  # 經過單元格獲取單元格數據。
myCellValue = mySheet.cell_value(0, 0)  # 直接獲取單元格數據，i是行數，j是列數，行數和列數都是從0開始計數。
print(myCellValue)

2. 寫入

# 寫入
import xlwt

# 建立Excel工做薄
myWorkbook = xlwt.Workbook()

# 添加Excel工做表
mySheet = myWorkbook.add_sheet('A Test Sheet')

# 寫入數據
myStyle = xlwt.easyxf('font: name Times New Roman, color-index red, bold on', num_format_str='#,##0.00')   #數據格式
mySheet.write(1, 1, 1234.56, myStyle)
mySheet.write(2, 0, 1)                          #寫入A3，數值等於1
mySheet.write(2, 1, 1)                          #寫入B3，數值等於1
mySheet.write(2, 2, xlwt.Formula("A3+B3"))      #寫入C3，數值等於2（A3+B3）

# 保存
myWorkbook.save('excelFile.xlsx')

xlutils結合xlrd能夠達到修改excel文件目的

import xlrd
from xlutils.copy import copy

workbook = xlrd.open_workbook('excelFile.xlsx')
workbooknew = copy(workbook)
ws = workbooknew.get_sheet(0)
ws.write(3, 0, 'changed!')
workbooknew.save('excelFilecopy.xls')　

openpyxl能夠對excel文件進行讀寫操做

from openpyxl import Workbook
from openpyxl import load_workbook
from openpyxl.writer.excel import ExcelWriter

workbook_ = load_workbook("data.xlsx")
sheetnames = workbook_.get_sheet_names()  # 得到表單名字
print(sheetnames)
sheet = workbook_.get_sheet_by_name(sheetnames[0])
print(sheet.cell(row=3, column=3).value)
sheet['A1'] = '47'
workbook_.save("data_new.xlsx")
wb = Workbook()
ws = wb.active
ws['A1'] = 4
wb.save("data_new2.xlsx")

xlsxwriter能夠寫excel文件並加上圖表

import xlsxwriter


def get_chart(series):
    chart = workbook.add_chart({'type': 'line'})
    for ses in series:
        name = ses["name"]
        values = ses["values"]
        chart.add_series({
            'name': name,
            'categories': 'A2:A10',
            'values': values
        })
    chart.set_size({'width': 700, 'height': 350})
    return chart


if __name__ == '__main__':
    workbook = xlsxwriter.Workbook('H5應用中心關鍵數據及趨勢.xlsx')
    worksheet = workbook.add_worksheet("每日PV,UV")
    headings = ['日期', '平均值']
    worksheet.write_row('A1', headings)
    index = 0
    for row in range(1, 10):
        for com in [0, 1]:
            worksheet.write(row, com, index)
            index += 1
    series = [{"name": "平均值", "values": "B2:B10"}]
    chart = get_chart(series)
    chart.set_title({'name': '每日頁面分享數據'})
    worksheet.insert_chart('H7', chart)
    workbook.close()