文本的操作

函数的排序操作：

def func(i):

    return i[2]

list=[('曹操',101,'c'),('吕布',100,'d'),('刘备',200,'l'),('大乔',50,'x')]

list.sort(key=func)

#如果自己写个排序算法，无法如何都要把里面的值取出来一次的

print(list)

文本的读写操作：

##往文件内写入数据，覆盖写入

f=open(r"E:\实习\编程\01\day06\1.txt",'w')

data=f.write('xxxxxxxxxxxx')

f.close()

##将文本中的内容读出来

f=open(r"E:\实习\编程\01\day06\1.txt",'r')

data=f.read()

print(data)

f.close

##将一张图片读出来

f=open(r"E:\实习\编程\01\day06\2.jpg",'rb')

data=f.read()

print(data)

f.close

词频统计：

英文：

f=open(r'E:\实习\编程\01\day06\22.txt','r')     ##打开文件

data=f.read().lower()                          ##将文件内的内容转换为小写

data_split=data.split(' ')                     ##以空格进行分割

count_dict={}                                  ##创建一个空字典

for word in data_split:                     ##开始for循环，判断word是否在字典内如果不

    if word not in count_dict:              ##在字典内初始值为1，如果在字典内加一

        count_dict[word]=1

    else:

        count_dict[word]+=1

def func(i):                                 ##定义一个func函数，把字典转换成一个列表

    return i[1]

lt=list(count_dict.items())

lt.sort(key=func)                            ##把列表进行倒序排序

lt.reverse()

for i in lt[0:10]:                            ##用for循环循环列表并输出

    print(f'{i[0]:^7}{i[1]^5}')

中文：

import jieba

f=open(r'E:\实习\编程\01\day06\threekingdoms.txt','r',encoding='utf8')

data=f.read()

data_jieba = jieba.lcut(data)

count_dict={}

for word in data_jieba:

    if len(word)==1:

        continue

    if word in {"将军","却是","荆州","二人","不可","不幸","却说","不能","如此","商议","如何","追赶","二十余","听令","不计其数","欣然","大汉","丞相","主公","军士","左右","军马","不如","赶来","引兵","次曰","荆州","大喜","朝廷","当先","传令","次日","天下","东吴","于是","今日","不敢","魏兵","陛下"}:

        continue

    if '曰' in word:

        word=word.replace('曰','')

    if '云长' in word:

        word=word.replace('云长','关公')

    if word in count_dict:

        count_dict[word]+=1

    else:

        count_dict[word]=1

def func(i):

    return i[1]

data_list=list(count_dict.items())

data_list.sort(key=func)

data_list.reverse()

for i in data_list[0:10]:                            ##用for循环循环列表并输出

    print(f'{i[0]:^7}{i[1]^5}')

词云：

import wordcloud

from imageio import imread

mask=imread(r'E:\实习\编程\01\day06\1.png')

f=open(r'E:\实习\编程\01\day06\22.txt','r',encoding='utf8')

data=f.read()

w=wordcloud.WordCloud(font_path=r'C:\Windows\Fonts\simfang',mask=mask,width=500,height=600,

background_color="white")

w.generate(data)

w.to_file('outfile.png')