Python中常见的文件格式处理

Python中常见的文件格式处理

1.读写EXCEL文件

python语言处理excel文件（xls、xlsx）时，一般会使用openyxl库和xlrd,xlwt库，这里推荐使用openyxl库进行处理，其处理的excel行数更大

1.1 EXCEL文件读取

from openpyxl import load_workbook
#读取的excel名称
excel = load_workbook("./test.xlsx") 
sheet = excel.get_sheet_by_name("Sheet1") #读取excel的sheet表格
rows = sheet.max_row      #获取行数
cols = sheet.max_column   #获取列数
for row in range(1,rows+1):
    id = sheet.cell(row = row,column=1).value     #第一列
    source = sheet.cell(row=row,column=2).value    #第二列
    target = sheet.cell(row=row,column=3).value    #第三列
    print(id,"->",target)
    
if __name__ == "__main__":
    print("excel读取完毕")

1.2 EXCEL文件书写

#!/usr/bin/python
# -*- coding: UTF-8 -*-
#Author: chengjinpei
import openpyxl
def write_xlsx_file(output_file):
    workbook = openpyxl.Workbook()                #创建excel对象
    worksheet = workbook.create_sheet("Sheet1")    #创建excel中的sheet
    i = 1
    for i in range(1,101):
        worksheet.cell(i,1,"flowid")
        worksheet.cell(i,2,"context")
    workbook.save(output_file)  #保存文件

if __name__ == "__main__":
    write_xlsx_file("test_output.xlsx")

1.3使用pandas读取excel文件

import pandas as pd
def read_file(filepath):
    data_list = []
    #使用pandas函数处理excel
    excel_data = pd.read_excel(filepath, sheet_name="Sheet4")#按照sheet处理文件夹
    for index, row in excel_data.iterrows():#遍历excel中的每行内容
        data = {}
        data["id"] = str(row["CASE_SERIAL"]).strip()
        data["text"] = str(row["CASE_CONTENT"]).strip().replace("【】", "").replace("*","")
        data["letertype"] = str(row["CASE_EX_ACCORD"]).strip()
        data["address"] = str(row["RQSTAREA"]).strip()
        data["time"] = str(row["TIME"]).strip()
        data_list.append(data)
    return data_list

2.txt文本的读写

python读取txt文本比较简单，直接使用open即可

input_file = "test.txt"
output_file = "test_out.txt"

fr = open(input_file,"r",encoding="utf-8")
fw = open(output_file,"w",encoding="utf-8")
lines = fr.readlines()
for line in lines:
    print(line)
    fw.write(line)
   #fw.flush()
if __name__ == "__main__":
    print("读写文件完毕")

3.json文本的读写

python读取json文本与txt比较相似，直接使用open即可

import json
import openpyxl
from openpyxl import load_workbook
workbook = openpyxl.Workbook()                #创建excel对象
worksheet = workbook.create_sheet("Sheet1")    #创建excel中的sheet
worksheet.cell(1,1,"secShortName")
worksheet.cell(1,2,"secFullName")
##读取json代码
with open("./company.json", "r", encoding="utf-8") as f:
    content = json.load(f)
    datas = content["data"]
    i= 2
    for data in datas:
        secShortName = ""
        secFullName = ""
        secShortNameChg = ""
        try:
            secShortName = data["secShortName"]
        except:
            secShortName = ""
        try:
            secFullName = data["secFullName"]
        except:
            secFullName = ""
        try:
            secShortNameChg = data["secShortNameChg"]
        except:
            secShortNameChg = ""
        short_name = secShortName+","+secShortNameChg
        #写入excel中方便统计
        worksheet.cell(i,1,short_name)
        worksheet.cell(i,2,secFullName)
        i+=1
    workbook.save("company_new.xlsx"
    #json文件写入
    with open("./conmpany_new.json", "w", encoding="utf-8") as f:
    	json.dump(datas, f, indent=4, ensure_ascii=False)

4.批量读取文件夹下的文件

批量读取某个文件夹下的文件需要使用os库以及python中list，实现代码如下：

def read_file(dir_name):
    filename_list = []
    for item in os.listdir(dir_name):
        filename_list.append(dir_name + item)
    output_path = dir_name+"out/"
    if not os.path.exists(output_path):
        os.makedirs(output_path)
    print(filename_list)#打印执行路径下所有文件
    #遍历文件夹下所有文件，开始批量处理
    for file in filename_list:
        print(file)
        output_file = file.replace(dir_name,output_path)
        ann_add_crf(file,output_file)#批量处理文件
        
if __name__ == "__main__": 
    read_file("/opt/jpcheng4/tuomin/src/train/original_data/")