如何告诉“sanitize-html”实际删除 html 标签(只保留其中的内容)?目前,例如,如果我将其设置为保留 div 部分,则在输出中它还会写入<div>some content</div>
-我只想要内部...('一些内容')
简而言之 - 我不想要标签、属性等 - 只有这些元素的内容..
var Crawler = require("js-crawler");
var download = require("url-download");
var sanitizeHtml = require('sanitize-html');
var util = require('util');
var fs = require('fs');
new Crawler().configure({depth: 1})
.crawl("http://www.cnn.com", function onSuccess(page) {
var clean = sanitizeHtml(page.body,{
allowedTags: [ 'p', 'em', 'strong','div' ],
});
console.log(clean);
fs.writeFile('sanitized.txt', clean, function (err) {
if (err) throw err;
console.log('It\'s saved! in same location.');
});
console.log(util.inspect(clean, {showHidden: false, depth: null}));
var str = JSON.stringify(clean.toString());
console.log(str);
/*download(page.url, './download')
.on('close', function () {
console.log('One file has been downloaded.');
});*/
});