t_zht的博客

#-*-coding:utf-8 -*-import csvwith open('file.csv', 'w+',newline='') as csvfile: spamwriter = csv.writer(csvfile, dialect='excel') # 读要转换的txt文件，文件每行各词间以@@@字符分隔 with open('1.txt', 'r',e...

import xml.dom.minidom as xmldomimport osxml_filepath = os.path.abspath("./originalData/train.xml")# xml_filepath=os.path.abspath("V5-13.xml")# 得到文件对象dom_obj = xmldom.parse(xml_filepath)# 得到元...

import reres = [ re.compile(r'<[^>]+>',re.S), re.compile(r'\&[a-zA-Z]+;',re.S), re.compile(r'\n|\t',re.S), re.compile(r'\[|\]|\(|\)',re.S), # r...

import shutilreadPath='cnews.test1.txt'writePath='cnews.test2.txt'lines_seen=set()outfiile=open(writePath,'a+',encoding='utf-8')f=open(readPath,'r',encoding='utf-8')for line in f: if line n...

import osfiles = os.listdir("D:\\JustForNLP\\script\\contentAll")#列出当前目录下所有的文件# D:\JustForNLP\script\contentAllfor filename in files: portion = os.path.splitext(filename)#分离文件名字和后缀 print(...

with open('weibo_test.txt', 'r', encoding='utf-8') as f: raw_data=f.readlines() for line in raw_data: label=line.split('\t')[0] content=line.split('\t')[1] # 1 ...

import osroot='./jointFile'filelist=os.listdir('./jointFile')print(filelist)with open('all.txt','a+',encoding='utf-8') as newfile: for file in filelist: print(file) txt=open(o...

import openpyxlwb=openpyxl.load_workbook('fear2Expand.xlsx') #打开excel文件# sheet=wb.get_sheet_by_name('Sheet3') #获取工作表sheet=wb["sheet1"]for i in range(1,260,1): text=sheet.cell(row=i,column=...