使用article parser提取网页内容

parser-article.js

var ArticleParser = require('article-parser');
var he = require('he');
 
var url = 'http://mp.weixin.qq.com/s/JJbZkcBoSMW0zPzmepUr1A';

ArticleParser.configure({
    htmlRules:{
        allowedTags: [ 'pre', 'p', 'img' ],
        allowedAttributes: {
          pre: ['style'],
          p: ['style'],
          img: ['src','data-src']
        }
    }
    
})

ArticleParser.extract(url).then((article) => {
  article.content = he.decode(article.content);
  article.description = he.decode(article.description);
  return article;
})
.then(article => console.log(article))
.catch((err) => {
  console.log(err);
});