在JS中是否有一种方法可以在HTML标签中获取整个HTML,作为字符串?
document.documentElement.??
在JS中是否有一种方法可以在HTML标签中获取整个HTML,作为字符串?
document.documentElement.??
当前回答
我只需要doctype html,应该可以在IE11, Edge和Chrome中正常工作。我使用下面的代码,它工作得很好。
function downloadPage(element, event) {
var isChrome = /Chrome/.test(navigator.userAgent) && /Google Inc/.test(navigator.vendor);
if ((navigator.userAgent.indexOf("MSIE") != -1) || (!!document.documentMode == true)) {
document.execCommand('SaveAs', '1', 'page.html');
event.preventDefault();
} else {
if(isChrome) {
element.setAttribute('href','data:text/html;charset=UTF-8,'+encodeURIComponent('<!doctype html>' + document.documentElement.outerHTML));
}
element.setAttribute('download', 'page.html');
}
}
在你的锚标签中像这样使用。
<a href="#" onclick="downloadPage(this,event);" download>Download entire page.</a>
例子
function downloadPage(element, event) { var isChrome = /Chrome/.test(navigator.userAgent) && /Google Inc/.test(navigator.vendor); if ((navigator.userAgent.indexOf("MSIE") != -1) || (!!document.documentMode == true)) { document.execCommand('SaveAs', '1', 'page.html'); event.preventDefault(); } else { if(isChrome) { element.setAttribute('href','data:text/html;charset=UTF-8,'+encodeURIComponent('<!doctype html>' + document.documentElement.outerHTML)); } element.setAttribute('download', 'page.html'); } } I just need doctype html and should work fine in IE11, Edge and Chrome. Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. <p> <a href="#" onclick="downloadPage(this,event);" download><h2>Download entire page.</h2></a></p> <p>Some image here</p> <p><img src="https://placeimg.com/250/150/animals"/></p>
其他回答
还可以获取<html>…</html>,最重要的是<!DOCTYPE……>声明,你可以遍历文档。childNodes,将它们转换为字符串:
const html = [...document.childNodes]
.map(node => nodeToString(node))
.join('\n') // could use '' instead, but whitespace should not matter.
function nodeToString(node) {
switch (node.nodeType) {
case node.ELEMENT_NODE:
return node.outerHTML
case node.TEXT_NODE:
// Text nodes should probably never be encountered, but handling them anyway.
return node.textContent
case node.COMMENT_NODE:
return `<!--${node.textContent}-->`
case node.DOCUMENT_TYPE_NODE:
return doctypeToString(node)
default:
throw new TypeError(`Unexpected node type: ${node.nodeType}`)
}
}
我把这段代码作为document-outerhtml发布在npm上。
注意上面的代码依赖于doctypeToString函数;它的实现可以如下所示(下面的代码以doctype-to-string的形式发布在NPM上):
function doctypeToString(doctype) {
if (doctype === null) {
return ''
}
// Checking with instanceof DocumentType might be neater, but how to get a
// reference to DocumentType without assuming it to be available globally?
// To play nice with custom DOM implementations, we resort to duck-typing.
if (!doctype
|| doctype.nodeType !== doctype.DOCUMENT_TYPE_NODE
|| typeof doctype.name !== 'string'
|| typeof doctype.publicId !== 'string'
|| typeof doctype.systemId !== 'string'
) {
throw new TypeError('Expected a DocumentType')
}
const doctypeString = `<!DOCTYPE ${doctype.name}`
+ (doctype.publicId ? ` PUBLIC "${doctype.publicId}"` : '')
+ (doctype.systemId
? (doctype.publicId ? `` : ` SYSTEM`) + ` "${doctype.systemId}"`
: ``)
+ `>`
return doctypeString
}
如果你想获取DOCTYPE之外的所有内容,这将有效:
document.getElementsByTagName('html')[0].outerHTML;
如果你想要doctype也可以这样:
new XMLSerializer().serializeToString(document.doctype) + document.getElementsByTagName('html')[0].outerHTML;
我总是用
document.getElementsByTagName('html')[0].innerHTML
可能不是正确的方式,但当我看到它时,我能理解它。
document.documentElement.innerHTML
你可以这样做
new XMLSerializer().serializeToString(document)
在比ie9更新的浏览器中
看到https://caniuse.com/壮举= xml序列化