python如何每次读两个汉字，读取字符，为了实验，无法读取两个字符（自然语言处理）

Question

def getText():
    txt=open('Ci.txt','r',encoding ="utf-8").read()
    for ch in '\n \ / ，。、：！？”“#￥%':
        txt=txt.replace(ch,"")
    return txt

test=getText()

counts={}

for word in test:
    if len(word)==1:
        if word in counts:
            counts[word]=counts[word]+1
        else:
            counts[word]=1

items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)

with open('2.txt','w') as a:
    a.write(str(items))

文件就不上传了，就是无法读取两个字符（汉字），只能读出单个汉字，但是又不想用jieba包，如何处理，求解决方案

Answer 1

你这样每次读两个：

def getText():
    txt = open('1.txt', 'r', encoding="utf-8").read()
    for ch in '\n \ / ，。、：！？”“#￥%':
        txt = txt.replace(ch, "")
    return txt

test = getText()
print(test)
counts = {}
for i in range(len(test)-1):
    t=test[i]+test[i+1]
    if len(t) == 2:
        if t in counts:
            counts[t] = counts[t] + 1
        else:
            counts[t] = 1
items = list(counts.items())
print(items)
items.sort(key=lambda x: x[1], reverse=True)
with open('2.txt', 'w') as a:
    a.write(str(items))