Regex 用多个尖括号清理管柱

我有下面的HTML代码

<div class="article">this is a div article content</div>

虽然我真正需要的是：

<div class="article">this is a <hl>div</hl> <hl>article</hl> content</div>

现在，这可以工作，但只替换标记中的第一个匹配项，即div:

---

下面的代码可能对您有所帮助：

class HTMLCleaner(object):
    def parse(self, html):
        output = []
        parsing_tag = False

        html = iter(html)
        for char in html:
            if char == '<':
                if parsing_tag:
                    drop_char = html.next()
                    while drop_char != '>':
                        drop_char = html.next()
                    continue
                parsing_tag = True
            elif char == '>':
                parsing_tag = False

            output.append(char)

        return ''.join(output)

html = '<<hl>div</hl> <hl>class</hl>="<hl>article</hl>">this is a <hl>div</hl> <hl>article</hl> content</<hl>div</hl>>'

parser = HTMLCleaner()
print parser.parse(html)

给定输入的输出为：

<div class="article">this is a <hl>div</hl> <hl>article</hl> content</div>

我相信这就是你要找的

---

当另一个标记还没有被解析时，代码基本上会删除所有标记。

隔离原始标记的主体，在其上运行标记程序，然后重新包装标记的文本，不是更容易吗？我真的不能这样做，因为文本是直接从SolrI标记的，我喜欢这个解决方案，因为我被一个正则表达式卡住了脑袋。。。有时只是从不同的角度思考。

<div <hl>class</hl>="<hl>article</hl>">this is a <hl>div</hl> <hl>article</hl> content</div>

var stripIllegalTags = function(html) {

  var output = '',
    dropChar,
    parsingTag = false;

  for (var i=0; i < html.length; i++) {
    var character = html[i];

    if (character == '<') {
      if (parsingTag) {
        do {
          dropChar = html[i+1];
          i++;
        } while (dropChar != '>');
        continue;
      }
      parsingTag = true;
    } else if (character == '>') {
      parsingTag = false;
    }

    output += character;

  }

  return output;

}

class HTMLCleaner(object):
    def parse(self, html):
        output = []
        parsing_tag = False

        html = iter(html)
        for char in html:
            if char == '<':
                if parsing_tag:
                    drop_char = html.next()
                    while drop_char != '>':
                        drop_char = html.next()
                    continue
                parsing_tag = True
            elif char == '>':
                parsing_tag = False

            output.append(char)

        return ''.join(output)

html = '<<hl>div</hl> <hl>class</hl>="<hl>article</hl>">this is a <hl>div</hl> <hl>article</hl> content</<hl>div</hl>>'

parser = HTMLCleaner()
print parser.parse(html)

<div class="article">this is a <hl>div</hl> <hl>article</hl> content</div>