应用场景：1.判断一个字符串是否符合规则 2.取出定制数据 3.爬虫数据 4.彩票网站匹配彩票信息等
- 模块re
- match()匹配字符串从头开始的信息，匹配成功，返回匹配对象，失败返回None
- 可以通过group调用
- compile 定义一个匹配规则的对象
- 简单来说就是定义一个匹配规则对象，直接调用re相关函数，返回匹配结果
import re
def contain_num(data):
result = re.findall('\d',data) # \d 匹配1个数字 \d+
print(result)
# for循环中，如果没有数据，是不会执行的
# 可以用for来替换if
for i in result:
print(i)
return True
return False
def remove_num(data):
res = re.findall('\D',data) # \D 非数字
print(res)
result = ''.join(res)
return result
def startwith(sub,data):
_sub = '\A%s' % sub
result = re.findall(_sub,data)
if len(result) != 0:
return True
else:
return False
def endwith(sub,data):
_sub = '%s\Z' % sub
result = re.findall(_sub,data)
for i in result:
return True
return False
# 计算字符串的真实长度，去掉空格的
def real_len(data):
res = re.findall('\S',data)# 匹配任意非空字符
print(res)
return len(res)
if __name__ =="__main__":
data = 'Do you like python? Mike\'s a_ge is 30 ，like apple'
result = contain_num(data)
print(result)
result = remove_num(data)
print(result)
print(re.findall('\W',data)) # \W 匹配非字母数字下划线
print(re.findall('\w', data))
print(type(re.search('\ADo',data)))
result = startwith('Do',data)
print(result)
result = endwith('apple',data)
print(result)
result = real_len(data)
print('原始长度：',len(data),' 真实长度：',result)
import re
url = 'https://www.sina.com'
def cheack_url(url):
result = re.findall('[a-z/A-Z]{4,5}://\w*\.*\w+\.\w+',url)
if len(result) != 0:
return True
else:
return False
#www.baidu.com
def get_url(url):
result = re.findall('^http\w*://(\w*\.*\w+\.\w+)',url)
if len(result) != 0:
print(result)
return result[0]
else:
return 'None，没有数据'
# nihaoa_mike@163.com
def get_mail(data):
result = re.findall('\w+\@\w+\.\w+',data)
# result = re.findall('[0-9a-zA-Z_]+@[0-9a-zA-Z]+\.[a-zA-Z]+', data)
# result = re.findall('.+@.+\.[a-zA-Z]+', data)
if len(result) != 0:
print(result)
return result[0]
else:
return '邮箱格式不正确'
html = ('<div class="s-top-nav" style="display:none;">'
'</div><div class="s-center-box"></div>')
def get_html_style(data):
result = re.findall('style="(.*?)"',data)
# .*会从上一个"匹配到最后一个",属于贪婪模式，加上？后-费贪婪模式，匹配一次结束
if len(result) != 0:
print(result)
return 'style=\"'+result[0]+'"'
else:
return '未查询到样式'
def get_html_alldata(data):
# result = re.findall('class=".*?"|style=".*?"',data)
# 如果只取=之后的信息
result = re.findall('="(.+?)"',data)
if len(result) != 0:
print(result)
return result[0]
else:
return '未匹配到结果'
if __name__ == "__main__":
result = cheack_url('https://www.sina.com/')
print(result)
result = get_url('https://www.baidu.com/')
print(result)
result = get_mail('nihaoa_mi1090ke@163.com')
print(result)
html = ('<div class="s-top-nav" style="display:none;"></div><div class="s-center-box"></div>')
result = get_html_style(html)
print(result)
result = get_html_alldata(html)
print(result)
import re
url = 'https://www.sina.com'
def cheack_url(url):
re_obj = re.compile('[a-z/A-Z]{4,5}://\w*\.*\w+\.\w+')
print(re_obj)
result = re_obj.findall(url)
if len(result) != 0:
return True
else:
return False
#www.baidu.com
def get_url(url):
re_obj = re.compile('^http\w*://(\w*\.*\w+\.\w+)')
result = re_obj.findall(url)
if len(result) != 0:
print(result)
return result[0]
else:
return 'None，没有数据'
# nihaoa_mike@163.com
def get_mail(data):
re_obj = re.compile('\w+\@\w+\.\w+')
result = re_obj.findall(data)
# result = re.findall('[0-9a-zA-Z_]+@[0-9a-zA-Z]+\.[a-zA-Z]+', data)
# result = re.findall('.+@.+\.[a-zA-Z]+', data)
if len(result) != 0:
print(result)
return result[0]
else:
return '邮箱格式不正确'
html = ('<div class="s-top-nav" style="display:none;">'
'</div><div class="s-center-box"></div>')
def get_html_style(data):
re_obj = re.compile('style="(.*?)"')
result = re_obj.findall(data)
# .*会从上一个"匹配到最后一个",属于贪婪模式，加上？后-费贪婪模式，匹配一次结束
if len(result) != 0:
print(result)
return 'style=\"'+result[0]+'"'
else:
return '未查询到样式'
def get_html_alldata(data):
# result = re.findall('class=".*?"|style=".*?"',data)
# 如果只取=之后的信息
re_obj = re.compile('="(.+?)"')
result = re_obj.findall(data)
if len(result) != 0:
print(result)
return result[0]
else:
return '未匹配到结果'
if __name__ == "__main__":
result = cheack_url('https://www.sina.com/')
print(result)
result = get_url('https://www.baidu.com/')
print(result)
result = get_mail('nihaoa_mi1090ke@163.com')
print(result)
html = ('<div class="s-top-nav" style="display:none;"></div><div class="s-center-box"></div>')
result = get_html_style(html)
print(result)
result = get_html_alldata(html)
print(result)
re_obj = re.compile('<div class="(.+?)" style="(.+?)"></div><div class="(.+?)"></div>')
result = re_obj.search(html)
print(result,type(result))
print(result.groups())
print(result.group(2))
print(html)
# 使用特殊字符进行切割
re_obj = re.compile('\W')
result = re_obj.split(html)
print(result)
re_obj = re.compile('\S')
result = re_obj.split(html)
print(result)
re_obj = re.compile('\s')# 以空格切开
result = re_obj.split(html)
print(result)
# match函数
re_obj = re.compile('class="(.+?)"')
result = re_obj.match(html)# match从头开始匹配
print(result)
re_obj = re.compile('<div class="(.+?)"')
result = re_obj.match(html)# match从头开始匹配
print(result)
print(result.groups())
print(result.group())
print(result.span())
print(html[:22])
import re
# 匹配1-100内的任意数字
def re_num(data):
result = re.match('[0-9]\d[0-9]{0,2}',str(data))
print(result,type(result))
# return result
if result:
return result.group()
else:
return result
# 匹配座机号码，构成规则：[3位数字]-[8位数字] 010-23456789
# 或者[4位数字]-[7位数字] 0431-2345678
def re_tel_num(data):
# result = re.search(r'[0-9]{3,4}-[0-9]{7,8}',data)
result = re.search(r'^\d{3,4}-\d{7,8}$', data)
print(result,type(result))
if result:
return result.group()
else:
return result
# 匹配5-10位纯数字组成的qq号码，且不能以0开头
def re_qq_num(data):
result = re.match('^[1-9]\d{4,9}$',str(data))
print(result,type(result))
if result != None:
return result.group()
else:
return 'qq号输入不正确'
# 取出字符串中的所有字母
# 787juhu896775juehsj002jasdb3232mub#dws832Htr
def re_str(data):
# match是从头开始匹配，开头不匹配就返回None，别忘了
# result = re.match('[a-zA-Z]',data)
result = re.findall('[a-zA-Z]+',data)
print(result,type(result))
if result != None:
return result
else:
return '不存在字母串'
# 找出以e结尾的单词，忽略大小写
def re_str_e(data):
re_obj = re.compile('[a-zA-Z]+e',re.I)
#re.I不区分大小写的匹配,\b为边界
result = re_obj.findall(data)
print(result,type(result))
if result != None:
return result
else:
return '不存在以e结尾的单词'
# 将多个重复的字母替换成&
# pythonfffjavahhhhHTMLKKKPHP
# 输出python&java&HTML&PHP
def re_replace_nn(data):
# 因为在正则表达式的规范里，每一对小括号都代表了一个组，从左往右数第一个括号里的叫做第一组，第二个括号里的内容叫做第二组。
# \1就代表着：pattern中第一组正则表达式匹配到的内容
re_obj = re.compile(r'([a-zA-Z])\1+')
# re_tuple = ('&','#','$')
result = re_obj.sub('#',data)
print(result,type(result))
if result != None:
return result
else:
return '不存在以e结尾的单词'
# 字符串替换s = '我我……要要……我要……要要……学学……要学学……python……编编编……程程程'
def re_replace_str(data):
result = re.sub('\W+','',data)
return result
if __name__ == '__main__':
a = 13
result = re_num(a)
print(result)
# 字符串前面加r的作用：防止字符被转义，使字符保留原有的样子
print(r'sd1212',type(r'sd1212'))
result = re_tel_num('0431-2345678')
print(result)
result = re_qq_num('92457990')
print(result)
result = re_str('787juhu896775juehsj002jasdb3232mub#dws832Htr')
print('===',result)
result = re_str_e('Do you like me? right? Please HEE has NO ME')
print(result)
result = re_replace_nn('pythonfffjavahhhhHTMLKKKPHP')
print(result)
result = re.sub('(\w+),(\w+),(\w+)',r'test:','python,345,900')
print(result)
result = re.sub(r'(\d+)\1', r'test:', 'python,345,900')
print(result)
result = re_replace_str('我我……要要……我要……要要……学学……要学学……python……编编编……程程程')
print(result)
ret = re.sub('.*','2',result)
print(ret)
ret = re.sub('.+', '2', result)
print(ret)
# 见证re.sub强大功能的最简单方式就是在替换字符串中使用组号。在替换内容中以‘\\n
# '型式出现的任何转义序列都会被模式中与组n匹配的字符串替换掉。
ret = re.sub(r'(.)\1+', '\1', result)
print(ret)
1533
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
