這兩天在用python寫一個(gè)采集器，有個(gè)功能模塊是html代碼轉(zhuǎn)換為ubb，網(wǎng)上貌似沒(méi)有現(xiàn)成程序，就自己寫了個(gè)函數(shù)，順便鍛煉下自己的正則。

import redef Html2UBB(content):	#以下是將html標(biāo)簽轉(zhuǎn)為ubb標(biāo)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(zhuǎn)義字符轉(zhuǎn)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(shí)直接調(diào)用Html2UBB函數(shù)，返回值就是ubb碼了html轉(zhuǎn)ubb