Unit4字符串以及正则表达式

常用方法1

s1 = "HelloWorld"
new_s1 = s1.lower()
print(s1, new_s1)
s2 = new_s1.upper()
print(new_s1,s2)

#字符串的分割
e_mail = "zhl@qq.com"
lst = e_mail.split("@")
print("邮箱名：", lst[0],"邮箱服务器域名：",lst[1])

#统计出行次数
print(s1.count("l"))

#检索操作
print(s1.find("o"))#首次出现位置
print(s1.find("p"))#-1没有找到
print(s1.index("o"))
#print(s1.index("p"))#ValueError: substring not found

#判断前缀和后缀
print(s1.startswith("h"))
print(s1.startswith("H"))

print("demo.py".endswith(".py"))#True
print("text.txt".endswith(".txt"))#Ture

常用方法2

s = "helloworld"
#替换
'''
    def replace(self,
            __old: str,
            __new: str,
            __count: SupportsIndex = ...) -> str
'''
new_s = s.replace("o","你好",1)#最后一个参数是替换次数，默认是全部替换
print(s,new_s)

'''
    字符串在指定的宽度范围内居中
    def center(self,
           __width: SupportsIndex,
           __fillchar: str = ...) -> str
'''
print(s.center(20))
print(s.center(20, "-"))

'''
    去掉字符串左右的空格
    def strip(self, __chars: str | None = ...) -> str
'''
s = "    hello    world   "
print(s.strip())
print(s.lstrip())
print(s.rstrip())

#去掉指定的字符 与顺序无关
s3 = "dl_Helloworld"
print(s3.strip("ld"))
print(s3.lstrip("ld"))
print(s3.rstrip("ld"))

格式化

name = "马冬梅"
age = 18
score = 98.4
print("name：%s,age:%d,score:%.1f"%(name,age,score))

#f-string
print(f"name:{name},age:{age},score{score}")

#format()
print("name:{0},age{1},score{2}".format(name,age,score))

详细格式

s = "helloworld"
print("{0:*<20}".format(s))
print("{0:*>20}".format(s))
print("{0:*^20}".format(s))

#居中对齐
print(s.center(20,"*"))

#千位分隔符（只适用于整数和读点书
print("{0:,}".format(123456789))
print("{0:,}".format(123456789.312313))
print("{0:.2f}".format(123456789.312313))
print("{0:.5}".format(s))

#整数类型
a = 425
print(
    "2进制：{0:b},8进制：{0:o},10进制：{0:d},16进制：{0:X},".format(a)
)

#科学计数法
pi = 3.1415926
print("{0:.2f},{0:.2E},{0:.2e},{0:.2%}".format(pi))

字符串的编码和解码

s = "伟大的人民"
#编码 str -> bytes
#默认UTF-8
scode = s.encode(errors="replace")
print(scode)
'''
    def encode(self,
           encoding: str = ...,
           errors: str = ...) -> bytes
'''
scode_gbk= s.encode("gbk",errors="replace") #gbk中中文占两个字节
print(scode_gbk)

#编码中的出错问题
s2 = "✌ye耶"
#errors = strickt(default) or replace or ignore or xmlcharrefreplace
scode_error = s2.encode("gbk",errors='replace')
print(scode_error)

# 解码过程 bytes -》 str
print(bytes.decode(scode_gbk, "gbk"))
print(bytes.decode(scode, "utf-8"))
print(s2)

数据的验证

#阿拉伯数据判定
print("12345".isdigit())#True
print("一二三".isdigit())#False
print("0x123".isdigit())#False
print("Ⅰ".isdigit())#False
print("一1".isdigit())#False

print("="*20)
#所有字符都是数字
'''       
    def isnumeric(self) -> bool
        Return True if the string is a numeric string, False otherwise.
        A string is numeric if all characters in the string are numeric and there is at
        least one character in the string.
'''
print("123".isnumeric())#True
print("一二三".isnumeric())#True
print("0b100".isnumeric())#Fakse
print("ⅠⅡⅢ".isnumeric())#True
print("壹贰叁".isnumeric())#True
print("="*20)
#所有字母都是字母（包含中文字符）
'''
    def isalpha(self) -> bool
        Return True if the string is an alphabetic string, False otherwise. 
'''
print("hello你好".isalpha())#True
print("hello你好123".isalpha())#False
print("hello你好一二三".isalpha())#True
print("hello你好0b100".isalpha())#False
print("hello你好ⅠⅡⅢ".isalpha())#False
print("hello你好壹贰叁".isalpha())#True\
print("="*20)
#判断字符的大小写 判断是读取全部字母
print("hello你好".islower())
print("hellO你好".islower())
print("Hello你好".islower())
print("hello=".islower())
print("Hello=".isupper())
print("="*20)
# isspace
print(" ".isspace())
print("hello  ".isspace())
print("   hello  ".isspace())

字符串拼接

s1 = "hello"
s2 = "world"
#(1)
print(s1 + s2)

#join()
print("-".join([s1,s2]))

#直接拼接
print("hello""world")

#format
print("%s%s" % (s1,s2))
print(f"{s1}{s2}")
print("{0}{1}".format(s1,s2))

去重

s = "hello world"
new_s = ""
for item in s:
    if item not in new_s:
        new_s += item
print(new_s)

#使用索引
new_s2 = ""
for i in range(len(s)):
    if s[i] not in new_s2:
        new_s2 += s[i]
print(new_s2)
print(new_s2 == new_s)
print(id(new_s2))
print(id(new_s))

#通过集合
new_s3 = set(s)
print(new_s3)
lst = list(new_s3)
print(lst)
lst.sort(key=s.index)
print(lst)
print("".join(lst))

正则表达式

import re #导入
pattern = '\d\.\d+' #限定符+ \d 0-9数字出现一次或多次
s = "I study Python3 every day"
match = re.match(pattern, s, re.I)
print(match) #None
s2 = "3.11Python I study every day"
match1 = re.match(pattern, s2)
print(match1)#<re.Match object; span=(0, 4), match='3.11'>

print("匹配值的起始位置：",match1.start())
print("匹配值的结束位置：",match1.end())
print("匹配值的区间的位置：",match1.span())
print("待匹配值的字符串：",match1.string)
print("匹配的数据：",match1.group())
'''
    匹配值的起始位置： 0
    匹配值的结束位置： 4
    匹配值的区间的位置： (0, 4)
    待匹配值的字符串： 3.11Python I study every day
   匹配的数据： 3.11`
'''


#search
pattern = "\d\.\d+"
s = "I study python3.11 every day python2.7 i used"
match = re.search(pattern, s)
print(match)

s1 = "2.71I study python3.11 every day python i used"
match1 = re.search(pattern, s1)
print(match1)


#findall
lst = re.findall(pattern,s)
lst1 = re.findall(pattern,s1)
print(lst)
print(lst1)


#sub and split
import re
#sub()
pattern = "黑客|破解|反爬"
s = "我需要学习python，想当黑客，破解一些VIP视频，python可以实现无底线反爬吗"
'''
    def sub(pattern, repl, string, count=0, flags=0):
    """Return the string obtained by replacing the leftmost
    non-overlapping occurrences of the pattern in string by the
    replacement repl.  repl can be either a string or a callable;
    if a string, backslash escapes in it are processed.  If it is
    a callable, it's passed the Match object and must return
    a replacement string to be used."""
    return _compile(pattern, flags).sub(repl, string, count)
'''
new_s = re.sub(pattern, "XXX", s)
print(new_s)

#split
s1 = "https://cn.bing.com/search?q=zhl&cvid=016dc0451cab427eaa8d8f04787fae17"
pattern1 = "[?|&]"
lst = re.split(pattern1,s1)
print(lst)

练习

Exer1

'''
判断车牌归属地
    使用列表存储N个车牌号码，通过遍历列表以及字符串的切片操作判断车牌的归属地
'''
lst = ["湘A0001","京A0001","沪A0001","粤A0001"]
for item in lst:
    area = item[0:1]
    print(item, "归属地为：",area)

Exer2

'''
统计字符串中出现指定字符的次数
    内容为 ”HelloPython，HelloJava，HelloC++“
    用户从键盘录入要查询的字符，不区分大小写
    要求统计出要查找的字符串出现的次数
'''
s1 = "HelloPython，HelloJava，HelloC++"
word = input("输入要统计的字符：")
print(f"{word}在{s1}一共出现了{s1.upper().count(word.upper())}")

Exer3

'''
    格式化输出商品的名称和价格
        使用列表存储一些商品数据，使用循环遍历输出商品的信息，要求对商品的编号进行格式化为6位
        单价保存2位小鼠，并在前面添加人名币符号输出
'''
lst = [
    ["01","PC","MS",5000],
    ["02","car","BYD",50000],
    ["03","mp","NS",5],
    ["04","TV","TCL",500],
]
print("编号\t\t\t名称\t\t\t品牌\t\t\t单价")
for item in lst:
    for i in item:
        print(i,end="\t\t\t")
    print()

#格式化操作
for item in lst:
    item[0] = "0000" + item[0]
    item[3] = "￥{0:.2f}".format(item[3])
print("编号\t\t\t\t名称\t\t\t\t品牌\t\t\t\t单价")
for item in lst:
    for i in item:
        print(i,end="\t\t\t")
    print()

Exer4

'''
    提取文本中所有图片的链接地址
'''
import random
import string

# 定义基础URL
base_url = "https://example.com/image"

# 定义可能的查询参数
params = {
    "resolution": ["1080p", "720p", "4k"],
    "format": ["jpg", "png", "gif"],
    "quality": ["high", "medium", "low"],
    "random": lambda: ''.join(random.choices(string.ascii_letters + string.digits, k=6))
}

# 生成随机查询参数
def generate_query_params():
    query_params = []
    for key, values in params.items():
        if callable(values):
            value = values()
        else:
            value = random.choice(values)
        query_params.append(f"{key}={value}")
    return "&".join(query_params)

# 生成完整的图片URL
def generate_complex_image_url():
    query_string = generate_query_params()
    return f"{base_url}?{query_string}"

# 生成并打印10个复杂的图片URL
for _ in range(10):
    print(generate_complex_image_url())

import re
# 编译正则表达式模式
pattern = re.compile(r"\d+")

# 使用编译后的正则表达式对象进行匹配
text = "There are 123 apples and 456 oranges."
match = pattern.search(text)
if match:
    print("Found:", match.group())


test_s = '"https://example.com/image?resolution=1080p&format=jpg&quality=high&random=abcdef","https://example.com/image?resolution=4k&format=jpg&quality=medium&random=saxkir","asd",sad,"asd",d"""""https://example.com/image?resolution=4k&format=jpg&quality=medium&random=driv3X",https://example.com/image?resolution=1080p&format=png&quality=low&random=xG7jqi'
# 使用捕获组
regex_pattern_with_groups = r'(https://example\.com/image\?resolution=(1080p|720p|4k)&format=(jpg|png|gif)&quality=(high|medium|low)&random=([a-zA-Z0-9]{6}))'
# 不使用捕获组
regex_pattern_without_groups = r'https://example\.com/image\?resolution=[0-9a-z]+&format=[0-9a-z]+&quality=[0-9a-z]+&random=[0-9a-zA-Z]{6}'

# 使用findall查找所有匹配的URL
lst_with_groups = re.findall(regex_pattern_with_groups, test_s)
lst_without_groups = re.findall(regex_pattern_without_groups, test_s)

# 打印所有匹配的URL
print("With groups:")
for item in lst_with_groups:
    print(item)  # item是一个元组

print("\nWithout groups:")
for item in lst_without_groups:
    print(item)  # item是整个匹配的字符串