cheerio - npm Package Compare versions

Comparing version 0.6.0 to 0.6.1

lib/api/selectors.js

+var $ = require("../cheerio"),
+    selectors = $.fn.filters;
+
+selectors["root"] = function(){
+    return [$.root] || [];
+}

test/api.selectors.js

+var cheerio = require("../"),
+    should = require("should");
+
+describe('$(":root")', function() {
+        it('should return the root element', function() {
+            var $ = cheerio.load("<div><span>foo</span><span>bar</span></div>");
+
+            $(":root").append("<div id = 'test'></div>");
+            $.html().should.equal('<div><span>foo</span><span>bar</span></div><div id = "test"></div>');
+    });
+});

History.md

@@ -0,1 +1,11 @@
+0.6.1 / 2012-02-12
+==================
+
+* Added .first(), .last(), and .clone() commands.
+* Option to parse using whitespace added to `.load`.
+* Many bug fixes to make cheerio more aligned with jQuery.
+* Added $(':root') to select the highest level element.
+
+Many thanks to the contributors that made this release happen: @ironchefpython and @siddMahen
+
 0.6.0 / 2012-02-07
@@ -2,0 +12,0 @@ ==================

lib/api/manipulation.js

@@ -150,3 +150,3 @@ var _ = require('underscore'),
 var replaceWith = exports.replaceWith = function(content) {
-  var elems = parse.eval(content);
+  var elems = (content.cheerio) ? content : parse.eval(content);
 
@@ -159,3 +159,3 @@ this.each(function() {
 
-    siblings.splice.apply(siblings, [index, 1].concat(elems));
+    siblings.splice.apply(siblings, [index, 1].concat(elems.toArray()));
 
@@ -177,4 +177,4 @@ updateDOM(siblings, this.parent);
 var html = exports.html = function(str) {
-  if(!str || typeof(str) === 'object') {
-    if(!this[0] || !this[0].children) return '';
+  if(str === undefined || typeof(str) === 'object') {
+    if(!this[0] || !this[0].children) return null;
     return $.html(this[0].children);
@@ -222,2 +222,12 @@ }
 
+var clone = exports.clone = function() {
+    var result = [];
+    for (var i = 0; i < this.length; i++) {
+      // TODO: This could be more efficient
+      result = result.concat(parse.eval($.html(this[i])));
+    }
+    return $(result);
+};
+
+
 module.exports = $.fn.extend(exports);

lib/api/traversing.js

@@ -16,7 +16,7 @@ var _ = require("underscore"),
   else
-    return null;
+    return $();
 };
 
 var next = exports.next = function(elem) {
-  if(!this[0]) return null;
+  if(!this[0]) return $();
 
@@ -28,6 +28,7 @@ var nextSibling = this[0].next;
   }
+  return $();
 };
 
 var prev = exports.prev = function(elem) {
-  if(!this[0]) return null;
+  if(!this[0]) return $();
 
@@ -39,6 +40,7 @@ var prevSibling = this[0].prev;
   }
+  return $();
 };
 
 var siblings = exports.siblings = function(elem) {
-  if(!this[0]) return null;
+  if(!this[0]) return $();
 
@@ -57,3 +59,3 @@ var self = this,
 var children = exports.children = function(selector) {
-  if(!this[0] || !this[0].children) return null;
+  if(!this[0] || !this[0].children) return $();
 
@@ -74,2 +76,10 @@ var children = _.filter(this[0].children, function(elem) {
 
+var first = exports.first = function() {
+    return this[0] ? $(this[0]) : $();
+};
+
+var last = exports.last = function() {
+    return this[0] ? $(this[this.length - 1]) : $();
+};
+
 module.exports = $.fn.extend(exports);

lib/api/utils.js

@@ -229,4 +229,4 @@ /*
 
-var load = exports.load = function(html) {  
-  var root = parse(html);
+var load = exports.load = function(html, opts) {  
+  var root = parse(html, opts);
   
@@ -267,2 +267,2 @@ function fn(selector, context, r) {
 
-module.exports = $.extend(exports);
+module.exports = $.extend(exports);

lib/cheerio.js

 /*
   Module dependencies
 */
+
 var path = require('path'),
     soupselect = require('cheerio-soupselect'),
+    filters = soupselect.filters,
     _ = require('underscore'),
@@ -75,2 +77,3 @@ parse = require('./parse');
     },
+    filters : filters,
     selector : '',
@@ -97,5 +100,5 @@ sort : [].splice,
 */
-var api = 'core utils attributes traversing manipulation';
+var api = 'selectors core utils attributes traversing manipulation';
 api.split(' ').forEach(function(plugin) {
   require('./api/' + plugin);
 });

lib/parse.js

@@ -12,4 +12,4 @@ /*
 */
-var parser = exports = module.exports = function(content) {
-  var dom = eval(content),
+var parser = exports = module.exports = function(content, opts) {
+  var dom = eval(content, opts),
       root = {
@@ -29,9 +29,8 @@ type : 'root',
 
-var eval = exports.eval = function(content) {
-  var handler = new htmlparser.DefaultHandler({
-        ignoreWhitespace: true
-      }),
+var eval = exports.eval = function(content, opts) {
+  opts = opts || { ignoreWhitespace: true };
+
+  var handler = new htmlparser.DefaultHandler(opts),
       parser = new htmlparser.Parser(handler);
   
-  parser.includeLocation = false;
   parser.parseComplete(content);
@@ -38,0 +37,0 @@

lib/render.js

@@ -43,3 +43,3 @@ /*
   output = output || [];
-  dom = isArray(dom) ? dom : [dom];
+  dom = (isArray(dom) || dom.cheerio) ? dom : [dom];
   
@@ -46,0 +46,0 @@ var len = dom.length,

package.json

@@ -6,3 +6,3 @@ {
   "keywords": ["htmlparser", "jquery", "selector", "scraper"],
-  "version": "0.6.0",
+  "version": "0.6.1",
   "repository":   {
@@ -9,0 +9,0 @@ "type": "git",

Readme.md

@@ -68,2 +68,6 @@ # cheerio
 
+By default, cheerio's parser will ignore whitespace, you can override this default by setting the second parameter:
+
+    $ = cheerio.load('<ul id = "fruits">...</ul>', { ignoreWhitespace: false });
+
 Optionally, you can also load in the HTML by passing the string as the context:
@@ -207,3 +211,14 @@
 
+#### .first()
+Will select the first element of a cheerio object
 
+    $('#fruits').children().first().text()
+    => Apple
+
+#### .last()
+Will select the last element of a cheerio object
+
+    $('#fruits').children().last().text()
+    => Pear
+
 ### Manipulation
@@ -336,2 +351,8 @@ Methods for modifying the DOM structure.
     => [ {...}, {...}, {...} ]
+    
+#### .clone() ####
+Clone the cheerio object.
+
+    var moreFruit = $('#fruits').clone()
+    
 ### Utilities
@@ -338,0 +359,0 @@

test/api.traversing.coffee

@@ -60,3 +60,3 @@ $ = require('../')
       # console.log $test.children()
-    
+  
   describe '.next', ->
@@ -94,3 +94,46 @@
     
+  describe '.first', ->
+    it '() : should return the first item', ->
+      src = $("<span>foo</span><span>bar</span><span>baz</span>")
+      elem = src.first()
+
+      elem.length.should.equal 1
+      elem.html().should.equal 'foo'
+      
+    it '() : should return an empty object for an empty object', ->
+      src = $();
+      first = src.first();
+      
+      first.length.should.equal 0
+      should.not.exist first.html()
+      
+  describe '.last', ->
+    it '() : should return the last element', ->
+      src = $("<span>foo</span><span>bar</span><span>baz</span>");
+      elem = src.last();
+
+      elem.length.should.equal 1
+      elem.html().should.equal 'baz'
+      
+    it '() : should return an empty object for an empty object', ->
+      src = $();
+      last = src.last();
+      
+      last.length.should.equal 0
+      should.not.exist last.html()
     
+  describe '.first & .last', ->
+    it '() : should return same object if only one object', ->
+      src = $("<span>bar</span>");
+      first = src.first();
+      last = src.last();
+
+      first.html().should.equal last.html()
+      first.length.should.equal 1
+      first.html().should.equal 'bar'
+      
+      last.length.should.equal 1
+      last.html().should.equal 'bar'
+      
+      
     

test/api.utils.js

@@ -1,2 +0,2 @@
-var cheerio = require('../'),
+var $ = require('../'),
     should = require('should');
@@ -13,11 +13,42 @@
     
-    it('(html) should return innerHTML of element', function() {
-      var html = "<div><span>foo</span><span>bar</span></div>",
-          $ = cheerio.load(html),
-          span = $('div').children().get(1);
+    it('() : should return innerHTML; $.html(obj) should return outerHTML', function() {
+      var div  = $('div', '<div><span>foo</span><span>bar</span></div>'),
+          span = div.children().get(1);
           
       $(span).html().should.equal('bar');
-      $.html(span).should.equal('<span>bar</span>')
+      $.html(span).should.equal('<span>bar</span>');
     });
+
+    it('(<obj>) : should accept an object, an array, or a cheerio object', function() {
+      var span = $("<span>foo</span>");
+          
+      $.html(span.get(0)).should.equal('<span>foo</span>');
+      $.html(span.get()).should.equal('<span>foo</span>');
+      $.html(span).should.equal('<span>foo</span>');
+    });
+    
+    it('(<value>) : should be able to set to an empty string', function() {
+        var elem = $("<span>foo</span>");
+        
+        elem.html('');
+        $.html(elem).should.equal('<span></span>');
+    });
+    
+    it('() : of empty cheerio object should return null', function() {
+      should.not.exist($().html());
+    });
+    
   });
+  
+  describe('.clone', function() {
+    
+    it('() : should return a copy', function() {
+        var src = $("<div><span>foo</span><span>bar</span><span>baz</span></div>").children(),
+            elem = src.clone();
+
+        elem.length.should.equal(3);
+        elem.parent().length.should.equal(0);
+    });
+    
+  });
 });

New alerts

Uses eval

Supply chain risk

Package uses dynamic code execution (e.g., eval()), which is a dangerous practice. This can prevent the code from running in certain environments and increases the risk that the code may contain exploits or malicious behavior.

Found 1 instance in 1 package

Filesystem access

Supply chain risk

Accesses the file system, and could potentially read sensitive data.

Found 1 instance in 1 package

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Found 1 instance in 1 package

Long strings

Supply chain risk

Contains long string literals, which may be a sign of obfuscated or packed code.

Found 1 instance in 1 package

Fixed alerts

Uses eval

Supply chain risk

Package uses dynamic code execution (e.g., eval()), which is a dangerous practice. This can prevent the code from running in certain environments and increases the risk that the code may contain exploits or malicious behavior.

Found 1 instance in 1 package

Filesystem access

Supply chain risk

Accesses the file system, and could potentially read sensitive data.

Found 1 instance in 1 package

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Found 2 instances in 1 package

Long strings

Supply chain risk

Contains long string literals, which may be a sign of obfuscated or packed code.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

75381

5.96%

Number of package files

27

8%

Lines of code

951

5.78%

Number of lines in readme file

449

4.91%

Number of low supply chain risk alerts

3

-25%

Worsened metrics

Number of medium supply chain risk alerts

5

25%

No dependency changes