随笔：正则表达式（二）

随笔：正则表达式（二）

一、方法封装：

import re


def regular_expression(value, start_value='', end_value='', match_type=0):
    """
    :param value: 待测文本
    :param start_value: 开始的字段，注意特殊符号，需要转换
    :param end_value: 结束的字段，注意特殊符号，需要转换
    :param match_type:匹配模式，0表示开头结尾不包含start_value、end_value
    :return: 返回正则截取的结果
    """
    # 去除空格和换行符
    text = re.sub('\s+', '', value)
    if start_value == '' and end_value != '':
        """
        到end_value截止，不包含end_value
        """
        pattern = re.compile(r"(.*)%s" % end_value)
        result = re.search(pattern, text).group(1)
    elif start_value != '' and end_value == '':
        """
        从start_value开始，不包含start_value
        """
        pattern = re.compile(r'%s(.*)' % start_value)
        result = re.search(pattern, text).group(1)
    elif start_value != '' and end_value != '' and match_type == 0:
        """
        从start_value开始，不包含start_value;到end_value截止，不包含end_value
        """
        pattern = start_value + '(.*?)' + end_value
        result = re.search(pattern, text).group(1)
    else:
        """
        从start_value开始，到end_value截止，包含start_value、end_value
        """
        pattern = re.compile(r"%s+(.*?)+%s" % (start_value, end_value))
        result = pattern.search(value).group()
    return result

二、示例

value = '1tagtask_ogdata_c2...'
start_value = '1'
end_value = '2'
s = regular_expression(value, start_value, end_value)
print(s)
s1 = regular_expression(value, end_value=end_value)
print(s1)
s2 = regular_expression(value, start_value=start_value)
print(s2)
s3 = regular_expression(value, start_value, end_value, match_type=1)
print(s3)

三、结果

tagtask_ogdata_c
1tagtask_ogdata_c
tagtask_ogdata_c2...
1tagtask_ogdata_c2