這兩天在用python寫一個采集器，有個功能模塊是html代碼轉換為ubb，網上貌似沒有現成程序，就自己寫了個函數，順便鍛煉下自己的正則。

import redef Html2UBB(content):	#以下是將html標簽轉為ubb標簽	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)	#以下是將html轉義字符轉為普通字符	content = content.replace('<','<')	content = content.replace('>','>')	content = content.replace('”','”')	content = content.replace('“','“')	content = content.replace('"','"')	content = content.replace('©','©')	content = content.replace('®','®')	content = content.replace(' ',' ')	content = content.replace('—','—')	content = content.replace('–','–')	content = content.replace('‹','‹')	content = content.replace('›','›')	content = content.replace('…','…')	content = content.replace('&','&')	return content

使用時直接調用Html2UBB函數，返回值就是ubb碼了html轉ubb