在JavaScript中，如何替换HTML页面中的文本而不影响标签？ [英] In JavaScript, how can I replace text in an HTML page without affecting the tags?
问题描述
以下是一个示例：
< body>
< span id =keyword> blah< / span>
< div>
blah blah关键字blah< br />
无论什么关键字
< / div>
< / body>
< script type =text / javascript>
var replace_terms = {
'keyword'：{'url'：'http：//en.wikipedia.org/','target'：'_blank'}
}
jQuery.each（replace_terms，function（i，val）{
var re = new RegExp（i，gi）;
$（'body'）。html $ b $（'body'）。html（）。replace（re，'< a href ='+ val ['url'] +'target ='+ val ['target'] +'> ;'+ i +'< / a>'）
）;
}）;
< / script>
我正在寻找替换不在HTML标签内的所有关键字的实例（< 和> 之间）
我想我还需要忽略keyword是否在脚本或 style 元素中。
不要使用正则表达式来解析HTML。 [X] [HT] ML不是常规语言，无法使用正则表达式进行可靠的处理。您的浏览器内置了一个好的HTML解析器;这样就可以在标签所在的地方找到工作。
另外你也不希望在 html（）/ innerHTML 在身上。这将会对整个页面进行序列化和重新解析，这将很慢，并且会丢失HTML中无法序列化的任何信息，例如事件处理程序，表单值和其他JavaScript引用。
这是一个使用DOM的方法，似乎适用于我：
function replaceInElement（element，find，replace）{
//反向遍历子节点，因为替换可能会增加
//子节点列表的长度。
for（var i = element.childNodes.length; i - > 0;）{
var child = element.childNodes [i];
if（child.nodeType == 1）{// ELEMENT_NODE
var tag = child.nodeName.toLowerCase（）;
if（tag！='style'&& tag！='script'）//特殊情况下，不要碰CDATA元素
replaceInElement（child，find，replace）;
} else if（child.nodeType == 3）{// TEXT_NODE
replaceInText（child，find，replace）;
}
}
}
function replaceInText（text，find，replace）{
var match;
var matches = [];
while（match = find.exec（text.data））
matches.push（match）;
for（var i = matches.length; i - > 0;）{
match = matches [i];
text.splitText（match.index）;
text.nextSibling.splitText（match [0] .length）;
text.parentNode.replaceChild（replace（match），text.nextSibling）;
}
}
//要匹配的关键字。这个*必须是一个'g'全局正则表达式，否则会失败
var find = / \b（keyword | whatever）\b / gi;
//用wiki链接替换匹配的字符串
replaceInElement（document.body，find，function（match）{
var link = document.createElement（'a'）;
link.href ='http://en.wikipedia.org/wiki/'+match[0];
link.appendChild（document.createTextNode（match [0]））;
return link;
}）;
I'm trying to figure out how to do a replace with Javascript. I'm looking at the entire body of the page and would like to replace the keyword matches NOT within an HTML tag.
Here is an example:
<body>
<span id="keyword">blah</span>
<div>
blah blah keyword blah<br />
whatever keyword whatever
</div>
</body>
<script type="text/javascript">
var replace_terms = {
'keyword':{'url':'http://en.wikipedia.org/','target':'_blank'}
}
jQuery.each(replace_terms, function(i, val) {
var re = new RegExp(i, "gi");
$('body').html(
$('body').html().replace(re, '<a href="'+ val['url'] +'" target="'+val['target']+'">' + i + '</a>')
);
});
</script>
I'm looking to replace all instances of the "keyword" that isn't within an HTML tag (between < and >).
I guess I also need to ignore if "keyword" is within a script or style element.
Don't use regex to parse HTML. [X][HT]ML is not a regular language and cannot reliably be processed using regex. Your browser has a good HTML parser built-in; let that take the strain of working out where the tags are.
Also you don't really want to work on html()/innerHTML on body. This will serialise and re-parse the entire page, which will be slow and will lose any information that cannot be serialised in HTML, such as event handlers, form values and other JavaScript references.
Here's a method using DOM that seems to work for me:
function replaceInElement(element, find, replace) {
// iterate over child nodes in reverse, as replacement may increase
// length of child node list.
for (var i= element.childNodes.length; i-->0;) {
var child= element.childNodes[i];
if (child.nodeType==1) { // ELEMENT_NODE
var tag= child.nodeName.toLowerCase();
if (tag!='style' && tag!='script') // special case, don't touch CDATA elements
replaceInElement(child, find, replace);
} else if (child.nodeType==3) { // TEXT_NODE
replaceInText(child, find, replace);
}
}
}
function replaceInText(text, find, replace) {
var match;
var matches= [];
while (match= find.exec(text.data))
matches.push(match);
for (var i= matches.length; i-->0;) {
match= matches[i];
text.splitText(match.index);
text.nextSibling.splitText(match[0].length);
text.parentNode.replaceChild(replace(match), text.nextSibling);
}
}
// keywords to match. This *must* be a 'g'lobal regexp or it'll fail bad
var find= /\b(keyword|whatever)\b/gi;
// replace matched strings with wiki links
replaceInElement(document.body, find, function(match) {
var link= document.createElement('a');
link.href= 'http://en.wikipedia.org/wiki/'+match[0];
link.appendChild(document.createTextNode(match[0]));
return link;
});
这篇关于在JavaScript中，如何替换HTML页面中的文本而不影响标签？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
