python实现html转ubb代码(html2ubb)


            这两天在用python写一个采集器，有个功能模块是html代码转换为ubb，网上貌似没有现成程序，就自己写了个函数，顺便锻炼下自己的正则。





import re

def Html2UBB(content):

	#以下是将html标签转为ubb标签

	pattern = re.compile( '<a href=\"([sS]+?)\"[^>]*>([sS]+?)</a>',re.I)

	content = pattern.sub(r'[url=1]2[/url]',content)

	pattern = re.compile( '<img[^>]+src=\"([^\"]+)\"[^>]*>',re.I)

	content = pattern.sub(r'[img]1[/img]',content)

	pattern = re.compile( '<strong>([sS]+?)</strong>',re.I)

	content = pattern.sub(r'[b]1[/b]',content)

	pattern = re.compile( '<font color=\"([sS]+?)\">([sS]+?)</font>',re.I)

	content = pattern.sub(r'[1]2[/1]',content)

	pattern = re.compile( '<[^>]*?>',re.I)

	content = pattern.sub('',content)

	#以下是将html转义字符转为普通字符

	content = content.replace('<','<')

	content = content.replace('>','>')

	content = content.replace('&rdquo;','”')

	content = content.replace('&ldquo;','“')

	content = content.replace('&quot;','"')

	content = content.replace('&copy;','&copy;')

	content = content.replace('&reg;','&reg;')

	content = content.replace(' ',' ')

	content = content.replace('&mdash;','—')

	content = content.replace('&ndash;','–')

	content = content.replace('&lsaquo;','&#8249;')

	content = content.replace('&rsaquo;','&#8250;')

	content = content.replace('&hellip;','…')

	content = content.replace('&amp;','&')

	return content





使用时直接调用Html2UBB函数，返回值就是ubb码了html转ubb