27.python正则练习

class match_singe_character(object):

    def digital(self):
        re_digital1 = re.match(r"速度与激情\d\d", "速度与激情98")
        re_digital2 = re.match(r"速度与激情[12345678]", "速度与激情8")
        re_digital3 = re.match(r"速度与激情[1-8]", "速度与激情8")
        re_digital4 = re.match(r"速度与激情[1-35-8]", "速度与激情5")
        re_no_digital = re.match(r"速度与激情\D", "速度与激情h")

        print(re_digital1.group())
        print(re_digital2.group())
        print(re_digital3.group())
        print(re_digital4.group())
        print(re_no_digital.group())

    def word(self):
        re_word1 = re.match(r"速度与激情\w", "速度与激情aA8_")
        re_word2 = re.match(r"速度与激情[a-z]", "速度与激情b")
        re_word3 = re.match(r"速度与激情[A-Z]", "速度与激情Z")
        re_no_word = re.match(r"速度与激情\W", '速度与激情。')

        print(re_word1.group())
        print(re_word2.group())
        print(re_word3.group())
        print(re_no_word.group())

    def space(self):
        re_space1 = re.match(r"速度与激情\s", "速度与激情 1")
        re_no_space = re.match(r"速度与激情\S", "速度与激情啊")
        re_any_character = re.match(r"速度与激情.", "速度与激情¥")

        print(re_space1.group())
        print(re_no_space.group())
        print(re_any_character.group())

class match_multiple_characters(object):
    def digital(self):
        re_digital1 = re.match(r"123\d{1,3}","1234567")
        re_digital2 = re.match(r"\d{3}-?\d{8}","02112345678")
        re_digital3 = re.match(r"\d*","")
        re_digital4 = re.match(r"\d+","21212")

        print(re_digital1.group())
        print(re_digital2.group())
        print(re_digital3.group())
        print(re_digital4.group())

#  match默认从头匹配， ^匹配开头， $匹配结尾, \w会匹配到中文
def Check_if_the_variable_is_valid():
    variables = ['sdf_', 'dsf df ', '1_2df']
    for variable in variables:
        re_variable = re.match(r"^[a-zA-Z_][a-zA-Z_0-9]*$", variable)
        if re_variable:
            print("variable: %s, re_variable: %s NO problem" % (variable, re_variable.group()))
        else:
            print("variable: %s has a problem" %variable)

def Check_if_the_email_is_valid():
    emails = ['dsff@163.com', 'sdfdfdsf@163.comcom ', 'asfs@163acom','fdsf333@gmail.com']
    for email in emails:
        re_email = re.match(r"^([a-zA-Z_0-9]{4,20})@(163|gmail)\.com$", email)
        if re_email:
            print("email: %s, re_email: %s NO problem" % (email, re_email.group()))
            print('%s 是 %s邮箱' % (email, re_email.group(2)))
        else:
            print("email: %s has a problem" %email)

def Check_the_html():
    html_str = "<h1>dsfsdfdsf</h1>"
    re_html1 = re.match(r"<(\w*)>.*</\1>", html_str)
    re_html2 = re.match(r"<(?P<p1>\w*)>.*</(?P=p1)>", html_str)
    print(re_html1.group())
    print(re_html2.group())

def search_findall_sub_split():
    str = "电话110，电话119"
    re_search = re.search(r"\d+", str)
    re_findall = re.findall(r"\d+", str)
    re_sub = re.sub(r"\d+",'250', str)
    re_sub_add = re.sub(r"\d+", sub_add, str)
    re_split = re.split(r":| ","name:fuck you")

    print(re_search.group())
    print(re_findall)
    print(re_sub, str)
    print(re_sub_add, str)
    print(re_split)

#sub支持替代和函数调用
def sub_add(temp):
    str_num = temp.group()
    num = int(str_num) + 1
    return str(num)

def html_clear():
    with open('content.html','r') as f:
        content = f.read()
    re_content = re.sub(r"<p>&nbsp;&nbsp;-|<.*>", '', content)
    print(re_content)