I am trying to get the inner text of HTML string, using a JS function(the string is passed as an argument). Here is the code:
我试图使用JS函数获取HTML字符串的内部文本(字符串作为参数传递)。这是代码:
function extractContent(value) {
var content_holder = "";
for(var i=0;i<value.length;i++) {
if(value.charAt(i) === '>') {
continue;
while(value.charAt(i) != '<') {
content_holder += value.charAt(i);
}
}
}
console.log(content_holder);
}
extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>");
The problem is that nothing gets printed on the console(content_holder stays empty). I think the problem is caused by the "===" operator..
问题是控制台上没有打印任何内容(content_holder保持空白)。我认为问题是由“===”运算符引起的..
6 个解决方案
#1
23
Create an element, store the HTML in it, and get its textContent
:
创建一个元素,将HTML存储在其中,并获取其textContent:
function extractContent(s) {
var span = document.createElement('span');
span.innerHTML = s;
return span.textContent || span.innerText;
};
alert(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>"));
Here's a version that allows you to have spaces between nodes, although you'd probably want that for block-level elements only:
这是一个允许您在节点之间有空格的版本,尽管您可能只想要块级元素:
function extractContent(s, space) {
var span= document.createElement('span');
span.innerHTML= s;
if(space) {
var children= span.querySelectorAll('*');
for(var i = 0 ; i < children.length ; i++) {
if(children[i].textContent)
children[i].textContent+= ' ';
else
children[i].innerText+= ' ';
}
}
return [span.textContent || span.innerText].toString().replace(/ +/g,' ');
};
console.log(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>. Nice to <em>see</em><strong><em>you!</em></strong>"));
console.log(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>. Nice to <em>see</em><strong><em>you!</em></strong>",true));
#2
14
One line (more precisely, one statement) version:
一行(更确切地说,一个声明)版本:
function extractContent(html) {
return (new DOMParser).parseFromString(html, "text/html") .
documentElement . textContent;
}
#3
2
use this regax for remove html tags and store only the inner text in html
使用此regax删除html标记并仅在html中存储内部文本
it shows the HelloW3c only check it
它显示HelloW3c只检查它
var content_holder = value.replace(/<(?:.|\n)*?>/gm, '');
#4
1
Try This:-
<!DOCTYPE html>
<html>
<body>
<script type="text/javascript">
function extractContent(value){
var div = document.createElement('div')
div.innerHTML=value;
var text= div.textContent;
return text;
}
window.onload=function()
{
alert(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>"));
};
</script>
</body>
</html>
#5
-1
You could temporarily write it out to a block level element that is positioned off the page .. some thing like this:
你可以暂时将它写出一个位于页面外的块级元素..这样的事情:
HTML:
<div id="tmp" style="position:absolute;top:-400px;left:-400px;">
</div>
JavaScript:
<script type="text/javascript">
function extractContent(value){
var div=document.getElementById('tmp');
div.innerHTML=value;
console.log(div.children[0].innerHTML);//console out p
}
extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>");
</script>
#6
-3
you need array to hold values
你需要数组来保存值
function extractContent(value) {
var content_holder = new Array();
for(var i=0;i<value.length;i++) {
if(value.charAt(i) === '>') {
continue;
while(value.charAt(i) != '<') {
content_holder.push(value.charAt(i));
console.log(content_holder[i]);
}
}
}
}extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>");
#1
23
Create an element, store the HTML in it, and get its textContent
:
创建一个元素,将HTML存储在其中,并获取其textContent:
function extractContent(s) {
var span = document.createElement('span');
span.innerHTML = s;
return span.textContent || span.innerText;
};
alert(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>"));
Here's a version that allows you to have spaces between nodes, although you'd probably want that for block-level elements only:
这是一个允许您在节点之间有空格的版本,尽管您可能只想要块级元素:
function extractContent(s, space) {
var span= document.createElement('span');
span.innerHTML= s;
if(space) {
var children= span.querySelectorAll('*');
for(var i = 0 ; i < children.length ; i++) {
if(children[i].textContent)
children[i].textContent+= ' ';
else
children[i].innerText+= ' ';
}
}
return [span.textContent || span.innerText].toString().replace(/ +/g,' ');
};
console.log(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>. Nice to <em>see</em><strong><em>you!</em></strong>"));
console.log(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>. Nice to <em>see</em><strong><em>you!</em></strong>",true));
#2
14
One line (more precisely, one statement) version:
一行(更确切地说,一个声明)版本:
function extractContent(html) {
return (new DOMParser).parseFromString(html, "text/html") .
documentElement . textContent;
}
#3
2
use this regax for remove html tags and store only the inner text in html
使用此regax删除html标记并仅在html中存储内部文本
it shows the HelloW3c only check it
它显示HelloW3c只检查它
var content_holder = value.replace(/<(?:.|\n)*?>/gm, '');
#4
1
Try This:-
<!DOCTYPE html>
<html>
<body>
<script type="text/javascript">
function extractContent(value){
var div = document.createElement('div')
div.innerHTML=value;
var text= div.textContent;
return text;
}
window.onload=function()
{
alert(extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>"));
};
</script>
</body>
</html>
#5
-1
You could temporarily write it out to a block level element that is positioned off the page .. some thing like this:
你可以暂时将它写出一个位于页面外的块级元素..这样的事情:
HTML:
<div id="tmp" style="position:absolute;top:-400px;left:-400px;">
</div>
JavaScript:
<script type="text/javascript">
function extractContent(value){
var div=document.getElementById('tmp');
div.innerHTML=value;
console.log(div.children[0].innerHTML);//console out p
}
extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>");
</script>
#6
-3
you need array to hold values
你需要数组来保存值
function extractContent(value) {
var content_holder = new Array();
for(var i=0;i<value.length;i++) {
if(value.charAt(i) === '>') {
continue;
while(value.charAt(i) != '<') {
content_holder.push(value.charAt(i));
console.log(content_holder[i]);
}
}
}
}extractContent("<p>Hello</p><a href='http://w3c.org'>W3C</a>");