These two days in Python to write a collector, there is a functional module is the HTML code conversion to UBB, online seemingly no ready-made program, wrote a function, by the way to exercise their own regular.
Import redef Html2ubb (content): #以下是将html标签转为ubb标签pattern = Re.compile (']*> ([ss]+?) ', Re. I) content = pattern.sub (R ' [Url=1]2[/url] ', content) pattern = Re.compile ("]+src=\" ([^\]]+) \ "[^>]*>", re. I) content = pattern.sub (R ' [img]1[/img] ', content) pattern = Re.compile ('([ss]+?)', Re. I) content = pattern.sub (R ' [b]1[/b] ', content) pattern = Re.compile (' ([ss]+?) ', 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 (' "', '" ') 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
The Html2ubb function is called directly when used, and the return value is the UBB code of the HTML turn UBB