read-art - npm Package Compare versions

Comparing version 0.3.7 to 0.3.8

lib/article.js

		@@ -156,3 +156,3 @@ "use strict";
		try {
		html = html.replace(/<\s(\w+).?>/g, '<$1>');
		html = html.replace(/<([a-z][a-z0-9])(?:[^>](\s(?:src\|href)=['\"][^'\"]['\"]))?[^>]?(\/?)>/ig, '<$1$2$3>');
		} catch (err) {}
		@@ -159,0 +159,0 @@ }

package.json

		{
		"name": "read-art",
		"version": "0.3.7",
		"version": "0.3.8",
		"description": "Scrape/Crawl article from any site automatically. Make any web page readable, no matter Chinese or English.",
		@@ -5,0 +5,0 @@ "main": "index.js",

test/html.js

		@@ -34,3 +34,3 @@ var read = require('../'),
		it('should have no attributes on element',function(done){
		read('<title>文章抓取</title><body><div><p style="font-size: 12px" data-id="10000">Hola!!!! Real Madrid!!!!!!!!!!!!!!</p></div></body>', {tidyAttrs: true}, function(err, art){
		read('<title>TIDY!!!!!</title><body><div><p style="font-size: 12px" data-id="10000">Hola!!!! <a href="real_madrid.htm">Real Madrid</a>!!!!!!!!!!!!!!<img src="real_madrid.jpg" /></p></div></body>', {tidyAttrs: true}, function(err, art){
		should.not.exist(err);
		@@ -41,2 +41,4 @@ expect(art).to.be.an('object');
		art.content.should.contain('Real Madrid');
		art.content.should.contain(' href="real_madrid.htm"');
		art.content.should.contain(' src="real_madrid.jpg"');
		done();
		@@ -43,0 +45,0 @@ });

Improved metrics