一、Python标准库中的GUI界面
import turtle as t
t.pensize(10)
t.color('blue')
#绘制NEUSOFT，水平移动，抬笔
t.penup()
t.goto(-260,0)#默认坐标(0,0)
t.pendown()
#绘制N
t.left(90)#向左旋转90度
t.forward(80)#向前画80
#简写
t.rt(145)
t.fd(100)
t.lt(145)
t.fd(80)
#绘制E
t.pu()
t.goto(-170,80)
t.pd()
t.right(90)
t.fd(70)
t.pu()
t.goto(-170,80)
t.pd()
t.right(90)
t.fd(70)
t.lt(90)
t.fd(70)
t.pu()
t.goto(-170,40)
t.pd()
t.fd(70)
#绘制U
t.pu()
t.goto(-70,80)
t.pd()
t.right(90)
t.fd(50)
t.circle(30,180)
t.fd(50)
#绘制S
t.pu()
t.goto(60,60)
t.pd()
t.circle(22,270)
t.circle(-22,270)
# 绘制O
t.pu()
t.goto(160,35)
t.pd()
t.circle(40)
#绘制F
t.pu()
t.goto(190,75)
t.pd()
t.rt(90)
t.fd(60)
t.pu()
t.goto(190,75)
t.pd()
t.rt(90)
t.fd(80)
t.pu()
t.goto(190,30)
t.pd()
t.lt(90)
t.fd(60)
#绘制T
t.pu()
t.goto(270,75)
t.pd()
t.fd(60)
t.pu()
t.goto(300,75)
t.pd()
t.rt(90)
t.fd(80)
t.done()#让GUI界面一直显示
二、Python中的数据类型
1、列表：与c语言中的数组相似，只不过可以存储不同类型的数据
①优点：灵活，缺点：效率低
②定义方式 []
③常见操作
hero_name=['鲁班七号','安其拉','李白','亚瑟']
#输出
print(hero_name)
#遍历
for hero in hero_name:
print(hero)
a.列表的访问
列表名[索引]
print(hero_name[2])
#列表的添加append()
hero_name.append('后羿')
print('添加后的列表', hero_name)
b.列表的修改
hero_name[1] = 1000
print('修改后的列表', hero_name)
#列表的删除del
del hero_name[2]
print('删除后的列表', hero_name)
练习:
创建[1,2,3,,,,10]这样的一个数字列表
步骤：
1)创建空列表
empty_number=[]
2)使用for循环，在列表里面添加
i=1
for i in range(1, 11):
empty_number.append(i)
print(empty_number)
2、字符串
# 定义形式 '' ，""
# 切片： 对序列截取一部分的操作，适用于列表
name = 'abcdefg'
# [起始位置：终止位置：步长] 左闭右开
# b c
print(name[1:3])
# a c e g
print(name[0:7:2])
# 全切片的时候可以省略初始和终止位置
print(name[::2])
#常见方法
#去掉两端空格
name = ' abcdefg '
# 查看序列内元素个数 len()
print(len(name))
name = name.strip()
print('去空格之后',len(name))
# 替换
price = '￥999'
price = price.replace('￥','$')
print(price)
# 列表变成字符串方法 join
li = ['a','b','c','d']# a = '-'.join(li)
print(a)
print(type(a))
3、元祖（tuple）：元祖和列表很像，只不过元祖不可以修改
#定义()
a=('zhangsan','lisi','wangwu',1000)
print(a)
#遍历
print(a[1])
#修改
#a[3]='zhaoliu'
#关于元祖需要注意的是,只有一个元素的元祖
b=('list')#属于字符串类型，b=('list',)
c=(1000)#属于int,c=(1000,)
4、字典
#key-value 数据结构
#定义形式 {}
info={'name':'李四','age':'34','add':'重庆市'}
print(len(info))
print(info)
#1.字典访问
print(info['name'])
#2.修改
info['add']='四川省成都市'
print('修改后的字典',info)
#3.增加
info['sex']='female'
print('增加后的字典',info)
#获取字典中所有的键,返回类型，列表
print(info.keys())
#获取字典中所有的值
print(info.values())
#获取字典中所有的kay-value
print(info.items())
d=[('name', '李四'), ('age', '34'), ('add', '四川省成都市'), ('sex', 'female')]
d1=dict(d)
print(d1)
#遍历字典
for k,v in info.items():
print(k,v)
5、集合
# 无序，不重复
set1 = {'zhangshan','lili',222}
print(type(set1))
print(set1)
# 列表的排序
#shuffle() 方法将序列的所有元素随机排序。
li = []
for i in range(10):
li.append(i)
print(li)
from random import shuffle
shuffle(li)
print('随机打乱的列表',li)
li.sort(reverse=True) #排序，正序
stu_info = [
{"name":'zhangsan',"age":18},
{"name":'lisi',"age":23},
{"name":'wangwu',"age":15},
{"name":'zhaoliu',"age":11},
]
print('排序前',stu_info)
# def 函数名(参数)
# 函数体
def sort_by_age(x):
return x['age']
# 根据年龄大小排序
stu_info.sort(key=sort_by_age)
print('排序后的列表',stu_info)
# 练习
name_info_list = [
('张三',4500),
('李四',9900),
('王五',2000),
('赵六',5500)
]
# 根据元组第二个元素进行正序排序
def sort_by_money(x):
return x[1]
name_info_list.sort(key=sort_by_money)
print('排序后的列表',name_info_list)
三、本地文件读取
#本地读取
# python中使用open内置函数进行文件的读取
f=open(file='./novel/threekingdom.txt',mode='r',encoding='utf-8')
print(f.read())
f.close()
# with as 上下文管理器 不用手动关闭流
# with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
# data = f.read()
# print(data)
# 写入
# txt = 'i like python'
# with open('python.txt','w', encoding='utf-8') as f:
# f.write(txt)
text = """<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Title</title>
</head>
<body>
<h1>重庆师范欢迎你</h1>
</body>
</html>"""
print(text)
with open('chongqingshifan.html','w', encoding='utf-8') as f:
f.write(text)
四、中文分词
# 3.中文分词 jieba
#安装jieba分词库
#指定国内镜像安装
#1.在用户目录下xinjianpip文件夹
#2.新建pip.ini文件
#添加
"""
[global]
index-url = http://mirrors.aliyun.com/pypi/simple/
[install]
trusted-host=mirrors.aliyun.com
"""
#pip install jieba 安装jieba
#pip uninstalll jieba 卸载jieba
#导入jieba分词
import jieba
#三种分词模式
seg="我来到重庆师范大学"
#精确模式 精确分词
seg_list=jieba.lcut(seg)
print(seg_list)
#全模式 找出所有可能的分词结果，冗余性大
seg_list1=jieba.lcut(seg,cut_all=True)
print(seg_list1)
#搜索引擎模式 先执行精确模式，再对其中的长词进行处理
seg_list2=jieba.lcut_for_search(seg)
print(seg_list2)
五、词云
# 词云展示
#安装
# 在Terminal中输入 pip install wordcloud
from wordcloud import WordCloud
import jieba
import imageio
# # 绘制词云
text = 'He was an old man who fished alone in a skiff in the Gulf Stream and he had gone eighty-four days now without taking a fish. In the first forty days a boy had been with him. But after forty days without a fish the boy’s parents had told him that the old man was now definitely and finally salao, which is the worst form of unlucky, and the boy had gone at their orders in another boat which caught three good fish the first week. It made the boy sad to see the old man come in each day with his skiff empty and he always went down to help him carry either the coiled lines or the gaff and harpoon and the sail that was furled around the mast. The sail was patched with flour sacks and, furled, it looked like the flag of permanent defeat.'
wc = WordCloud().generate(text)
wc.to_file('老人与海.png')
# 三国演义小说词云绘制
#
# 三国演义小说分词
# 读取三国演义小说
mask = imageio.imread('./china.jpg')
with open('./novel/threekingdom.txt','r', encoding='utf-8') as f:
words = f.read()
print(len(words)) # 字数 55万
words_list = jieba.lcut(words)
print(len(words_list)) # 分词后的词语数 35万
print(words_list)
# 将words_list转化成字符串
novel_words = " ".join(words_list)
print(novel_words)
# WordCloud()里面设置参数
wc = WordCloud(
font_path='msyh.ttc', #字体
background_color='white',
width=800,
height=600,
mask=mask
).generate(novel_words)
wc.to_file('三国词云.png')
