综合应用，jieba,去标点，分词保存，统计，删词，输出

Posted 2022-09-14 huigebj

import jieba

fp1=r‘D:/python/a.txt‘
outph=r‘D:/python/out.txt‘
f=open(fp1,‘r‘,encoding=‘utf-8‘)
txt=f.read().strip()
f.close()

words=jieba.lcut(txt)
f=open(outph,‘w‘,encoding=‘utf-8‘)
for word in words:
    f.write(word)
    f.write(‘\n‘)
f.close()


#第二题去标点，统计词频
bd=‘[’!"#$%&\‘()*+,-./:;<=>?@[\\]^_`|~]+，。！？“”《》：、． ‘
counts= 
exlutes=‘作者‘,‘之后‘
for i in bd:
    txt=txt.replace(i,‘‘)   #字符串替换去标点符号

words=jieba.lcut(txt)  #分词
for word in words:
    if len(word)==1:
        continue
    else:
        counts[word]=counts.get(word,0)+1   #所有词全统计
for word in exlutes:
    del(counts[word])   #删除a,b
items=list(counts.items())

items.sort(key=lambda x:x[1],reverse=True)
for i  in range(15):
    word,count=items[i]
    print("0:>10---1:<5".format(word,count))