crawlit - npm Package Compare versions

Comparing version 0.1.2 to 0.1.3

lib/crawlQueue.js

@@ -14,3 +14,4 @@ "use strict";
   maxConnections: 2,
-  crawlingTaskCount: 0
+  crawlingTaskCount: 0,
+  updateMode: true
 };
@@ -20,2 +21,3 @@
   PREPARE: 0,
+  UPDATE: 5,
   RETRY: 1,
@@ -33,4 +35,6 @@ PROCESS: 2,
 
+//crawl objects queue data cache.
+var QUEUE = [];
+
 var crawlQueue = function (baseDir, crawl) {
-  var QUEUE = [];
   var that = {};
@@ -59,2 +63,11 @@
     QUEUE = utilBox.loadJSON(queueDumFile, []);
+    QUEUE.forEach(function (uriObj) {
+      if (uriObj.status === QUEUE_STATUS.PROCESS) {
+        process.nextTick(crawl.bind(null, uriObj));
+        queueConfig.crawlingTaskCount += 1;
+      }
+      if (queueConfig.updateMode && uriObj.status === QUEUE_STATUS.CRAWLED && uriObj.type === 'link') {
+        uriObj.status = QUEUE_STATUS.UPDATE;
+      }
+    });
     assert(Array.isArray(QUEUE));
@@ -71,2 +84,5 @@ };
        */
+
+      var memUsage = process.memoryUsage().rss / (1024 * 1024);
+
       var next = function () {
@@ -79,14 +95,20 @@ var count = 0;
 
-          if (queueConfig.crawlingTaskCount < queueConfig.maxConnections &&
-              (uriObj.status === QUEUE_STATUS.PREPARE ||
-                  uriObj.status === QUEUE_STATUS.RETRY && uriObj.failedCount < maxRetryCount)) {
+          if (memUsage < queueConfig.maxMem &&
+              queueConfig.crawlingTaskCount < queueConfig.maxConnections &&
+              ( uriObj.status === QUEUE_STATUS.PREPARE ||
+                  (uriObj.status === QUEUE_STATUS.RETRY && uriObj.failedCount < maxRetryCount) ||
+                  (uriObj.status === QUEUE_STATUS.UPDATE && queueConfig.updateMode) )) {
 
-            process.nextTick(crawl.bind(null, uriObj));
+            setImmediate(crawl.bind(null, uriObj));
+            //process.nextTick(crawl.bind(null, uriObj));
+            uriObj.status = QUEUE_STATUS.PROCESS;
             count += 1;
             queueConfig.crawlingTaskCount += 1;
+            return queueConfig.crawlingTaskCount >= queueConfig.maxConnections;
           }
         });
         queueConfig.crawlingTaskCount = count;
+
         if (queueConfig.crawlingTaskCount === 0) {
-          if (retry > 2) {
+          if (retry > 0) {
             clearInterval(timer);
@@ -109,3 +131,2 @@ console.log('queue is empty Exit dump Queue listener....');
 
-      var memUsage = process.memoryUsage().rss / (1024 * 1024);
 
@@ -116,3 +137,3 @@ console.log('Memory usage:', memUsage.toFixed(2), 'Mb');
       }
-      if (memUsage > queueConfig.maxMem) {
+      if (memUsage > queueConfig.maxMem && queueConfig.crawlingTaskCount === 0) {
         console.error("Over max memory usage, exit process.");
@@ -125,3 +146,3 @@ process.exit(1);
     //TODO Update and dump queue by Event driven, remove setInterval() calling..
-    var timer = setInterval(dump, 5 * 1000);
+    var timer = setInterval(dump, 8 * 1000);
   };
@@ -134,5 +155,4 @@
    * type:[attachment,css,link.img],
-   * status:0:未开始 1:更新, 2:Retry 3：进行中,4:成功,5:失败，
+   * status: @see QUEUE_STATUS
    * failedCount:3,
-   * updateFlag:anyeType}
    */
@@ -139,0 +159,0 @@ that.push = function (uriObj) {

lib/domCrawler.js

@@ -14,4 +14,4 @@ "use strict";
 var request = require('request');
-var jsdom = require('jsdom');
-//var request = require('http').request;
+//var jsdom = require('jsdom');
+var cheerio = require('cheerio');
 var iconv = require('iconv-lite');
@@ -23,2 +23,3 @@ var charset = require('charset');
 var utilBox = require('./utilbox.js');
+var jsdomCount = 0;
 
@@ -28,2 +29,3 @@ //Load jQuery source code to string.
 
+var resourceParser = config.crawlOptions.resourceParser;
 //prepare working path
@@ -37,3 +39,3 @@ var ROOT_PATH = config.crawlOptions.working_root_path;
 var getFilename = function (uriObj) {
-  return config.crawlOptions.resourceParser.getFileName(ROOT_PATH, uriObj);
+  return resourceParser.getFileName(uriObj);
 };
@@ -51,9 +53,8 @@
 
-var getBaseURI = function (window) {
+var getBaseURI = function ($base, locationHref) {
 //get baseURI, document.baseURI is not working in jsdom.
-  var $base = window.$('base');
-  var urlObj = url.parse(window.location.href);
+  var urlObj = url.parse(locationHref);
   var basePath = $base.length === 1 ? $base.attr('href') : path.dirname(urlObj.pathname);
   if (!url.parse(basePath).host) {
-    basePath = url.resolve(window.location.href, basePath);
+    basePath = url.resolve(locationHref, basePath);
   }
@@ -69,7 +70,12 @@ return basePath;
   var uri = uriObj['uri'];
-  console.log("Crawl   :", uriObj.type, uri);
+  console.log("Crawl :", uriObj.type, uri);
 
   console.debug('File', uriObj.filename);
+  Object.defineProperty(uriObj, 'distFilename', {
+    value: path.join(ROOT_PATH, url.parse(uriObj.uri).hostname, uriObj.filename),
+    writable: true,
+    numerable: false,
+    configurable: true});
 
-  utilBox.preparePath(path.dirname(uriObj.filename));
+  utilBox.preparePath(path.dirname(uriObj.distFilename));
 
@@ -103,3 +109,3 @@ /**
       }
-    }).pipe(fs.createWriteStream(uriObj.filename));
+    }).pipe(fs.createWriteStream(uriObj.distFilename));
   } else {
@@ -135,60 +141,67 @@ request.get({uri: uri, jar: true, encoding: null, headers: requestOptions}, function (err, res, body) {
       //2. Remove absolute path to relative path
-      var regexp = new RegExp('http:\/\/' + config.crawlOptions.host.replace(/\./g, '\.'), 'g');
-      var outputCrawled = body.replace(regexp, '');
       //3. save to disk
-      fs.writeFile(uriObj.filename, outputCrawled, function (err) {
-        if (err) {
-          return crawlEnd(err, uriObj);
-        }
-        outputCrawled = null;
-        console.info('Save to:', uriObj.filename);
-      });
+      var saveCrawledUri = function (output) {
+        var regexp = new RegExp('http:\/\/' + config.crawlOptions.host.replace(/\./g, '\.'), 'g');
+        var outputCrawled = output || body;
+        outputCrawled = outputCrawled.replace(regexp, '');
 
+        //console.warn(outputCrawled);
+
+        fs.writeFile(uriObj.distFilename, outputCrawled, function (err) {
+          if (err) {
+            return crawlEnd(err, uriObj);
+          }
+          outputCrawled = null;
+          console.info('Save to:', uriObj.filename);
+        });
+      };
+      if (!resourceParser.modify) {
+        saveCrawledUri();
+      }
+
       //4. Remove all script for parsing HTML DOM.
       body = body.replace(/<script.*?>.*?<\/script>/ig, '');
       //5. parse links
-      jsdom.env({ html: body, src: [jQuerySrc],
-        done: function (err, window) {
-          body = null; //release memory
+      var $ =  cheerio.load(body, { normalizeWhitespace: true, xmlMode: false });
 
-          if (err) {
-            window && window.close && window.close();
-            return crawlEnd(err, uriObj);
+      console.debug('Parse HTML :', uri);
+      var baseURI = getBaseURI($('base'), uriObj.uri);
+
+      //todo move linkStacks into resourcePraser.
+      var linkStacks = [];
+      var handler = {
+        parse: function (jQuerySelector, resourceType, callback) {
+          var resources = jQuerySelector;
+          if (resources) {
+            //todo use Object[key] to count;
+            linkStacks.push(resourceType + ': ' + resources.length);
+            resources.each(function (index, link) {
+              callback($(link));
+            });
+          } else {
+            linkStacks.push(resourceType, 0);
           }
+        },
+        push: function (uriObj) {
+          var host2 = url.parse(uriObj.uri).host;
+          if (!host2) {
+            uriObj.uri = getAbsUrlPath(baseURI, uriObj.uri);
+          }
+          uriObj.filename = getFilename(uriObj);
+          crawler.push(uriObj);
+        }};
 
-          console.debug('Parse HTML :', uri);
-          var baseURI = getBaseURI(window);
 
-          var linkStacks = [];
-          var handler = {
-            parse: function (jQuerySelector, resourceType, callback) {
-              var resources = window.$(jQuerySelector);
-              if (resources) {
-                linkStacks.push(resourceType + ': ' + resources.length);
-                resources.each(function (index, link) {
-                  callback(link);
-                });
-              } else {
-                linkStacks.push(resourceType, 0);
-              }
-            },
-            push: function (uriObj) {
-              var host2 = url.parse(uriObj.uri).host;
-              if (!host2) {
-                uriObj.uri = getAbsUrlPath(baseURI, uriObj.uri);
-              }
-              uriObj.filename = getFilename(uriObj);
-              crawler.push(uriObj);
-            }};
+      resourceParser.parseLinks($, handler);
+      if (resourceParser.modify) {
+        saveCrawledUri(resourceParser.modify($, handler));
+      } else {
+        //TODO change rules then move parseLines method downside.
+        //resourceParser.parseLinks($, handler);
+      }
 
-          config.crawlOptions.resourceParser.parseLinks(window.$, handler);
-
-          window.close();//Call window.close(); for memory leak.
-          window = null;
-          handler = null;
-          console.info('Resource count in page:', uriObj.uri, linkStacks);
-          linkStacks = null;
-          crawlEnd(null, uriObj);
-        }
-      });
+      handler = null;
+      console.info('Resource count in page:', uriObj.uri, linkStacks);
+      linkStacks = null;
+      crawlEnd(null, uriObj);
     });
@@ -195,0 +208,0 @@ }

lib/plugins/discuz/attachment.js

@@ -25,2 +25,4 @@ "use strict";
 var utilBox = require('../../utilbox.js');
+var console = require('../../logger.js').getLogger('info');
+console.log = console.debug;
 
@@ -38,8 +40,10 @@ var finishedStack = {};
 
-var attachmentFilePath = function (baseDir, uriObj) {
+var attachmentFilePath = function (uriObj) {
   //path name = __dirname/hostname/attachment/tid/uid-paramnames-n
   var realIdArray = decode(uriObj.query.aid).split('|');
+  console.log('realId.array: ', realIdArray);
+  console.log('16num to 10', parseInt(realIdArray[1], 16));
 
   var filename = Object.keys(uriObj.query).reduce(function (pre, current, index) {
-    //console.log(index, 'pre:', pre, 'current:', current);
+    console.log(index, 'current:', current, 'pre:', pre);
     //Add other param to filenameArray
@@ -52,3 +56,6 @@ if (!/(mod|aid)/i.test(current)) {
 
-  return path.join(baseDir, uriObj.hostname, 'attachment', realIdArray.pop(), filename.join('-'));
+  console.log('realId.array: ', realIdArray);
+  console.log('filename:', filename);
+
+  return path.join('attachment', realIdArray.pop(), filename.join('-'));
 };
@@ -129,18 +136,7 @@
 
-exports.getAttFilePath = function (dir, uri) {
+exports.getAttFilePath = function (uri) {
   var urlObj = url.parse(uri, true);
-  return attachmentFilePath(dir, urlObj);
+  return attachmentFilePath(urlObj);
 };
 
-exports.exists = function (uri) {
-  var uriObj = url.parse(uri, true);
-  if (isAttach(uriObj)) {
-    var filePath = attachmentFilePath(uriObj);
-    //console.log('filePath:', filePath, ' exist:', fs.existsSync(filePath));
-    return fs.existsSync(filePath);
-  } else {
-    return false;
-  }
-};
-
 exports.clear = function () {
@@ -147,0 +143,0 @@ clearFishied.call(null, cleanAttFiles);

lib/plugins/discuz/index.js

@@ -19,25 +19,25 @@ "use strict";
 //pipe images
-  handler.parse('img[file^="forum.php?mod=attachment"]', "images", function (img) {
-    handler.push({uri: img.getAttribute('file'), type: 'attachment'});
-    handler.push({uri: img.getAttribute('zoomfile'), type: 'attachment'});
+  handler.parse($('img[file^="forum.php?mod=attachment"]'), "images", function (img) {
+    handler.push({uri: img.attr('file'), type: 'attachment'});
+    handler.push({uri: img.attr('zoomfile'), type: 'attachment'});
   });
 
   //pipe attachments and not need JB
-  handler.parse('a[href^="forum.php?mod=attachment"]', 'attachments', function (attachment) {
-    var needJB = $('#' + (attachment.parentNode.id || attachment.id) + '_menu').text().indexOf('金币') > 0;
+  handler.parse($('a[href^="forum.php?mod=attachment"]'), 'attachments', function (attachment) {
+    var needJB = $('#' + (attachment.parent.attr('id') || attachment.attr('id')) + '_menu').text().indexOf('金币') > 0;
     if (!needJB) {
       //console.log('attachment:', attachment.href, $('#' + $(attachment).parent().id + '_menu').text());
-      handler.push({uri: (attachment.href), type: 'attachment'});
+      handler.push({uri: (attachment.attr('href')), type: 'attachment'});
     }
   });
 
-  handler.parse('img', 'image', function (link) {
-    handler.push({uri: link.src, type: 'img'});
+  handler.parse($('img'), 'image', function (link) {
+    handler.push({uri: link.attr('src'), type: 'img'});
   });
 
-  handler.parse('link[rel="stylesheet"]', 'css', function (link) {
-    handler.push({uri: link.href, type: 'css'});
+  handler.parse($('link[rel="stylesheet"]'), 'css', function (link) {
+    handler.push({uri: link.attr('href'), type: 'css'});
   });
 
-  handler.parse('sscript[src^="static/"]', 'js', function (link) {
+  handler.parse($('sscript[src^="static/"]'), 'js', function (link) {
     handler.push({uri: $(link).attr('src'), type: 'js'});
@@ -50,43 +50,41 @@ });
     //thread links
-    handler.parse('a[href$=".html"][href^="forum"]', 'forum', function (link) {
-      handler.push({uri: link.href, type: 'link'});
+    handler.parse($('a[href$=".html"][href^="forum"]'), 'forum', function (link) {
+      handler.push({uri: link.attr('href'), type: 'link'});
     });
 
-    handler.parse('a[href$=".html"][href^="thread"]', 'thread', function (link) {
-      handler.push({uri: link.href, type: 'link'});
+    handler.parse($('a[href$=".html"][href^="thread"]'), 'thread', function (link) {
+      handler.push({uri: link.attr('href'), type: 'link'});
     });
 
     //archive links
-    handler.parse('a[href^="archiver/"],a[href^="?tid-"]', 'Archive', function (a) {
-      handler.push({uri: a.href, type: 'link'});
+    handler.parse($('a[href^="archiver/"],a[href^="?tid-"]'), 'Archive', function (a) {
+      handler.push({uri: a.attr('href'), type: 'link'});
     });
 
     //forum links
-    handler.parse('a[href^="forum.php?gid="] ', 'forum', function (a) {
-      handler.push({uri: a.href, type: 'link'});
+    handler.parse($('a[href^="forum.php?gid="] '), 'forum', function (a) {
+      handler.push({uri: a.attr('href'), type: 'link'});
     });
 
-    handler.parse('a[href="group.php"],a[href="portal.php"],a[href="home.php"]', 'p&f&g', function (link) {
+    handler.parse($('a[href="group.php"],a[href="portal.php"],a[href="home.php"]'), 'p&f&g', function (link) {
       //console.log('group:', link.href);
-      if (/\.php$/.test(link.href)) {
+      if (/\.php$/.test(link.attr('href'))) {
         //console.log('push:', link.href, crawler.push({uri:link.href, type:'link'}));
-        handler.push({uri: link.href, type: 'link'});
+        handler.push({uri: link.attr('href'), type: 'link'});
       }
     });
 
-    handler.parse('a[href^="group.php?gid="]', 'group', function (link) {
+    handler.parse($('a[href^="group.php?gid="]'), 'group', function (link) {
       //console.log('group:', link.href);
-      if (/group\.php\?gid=\(d{1,3}$/.test(link.href)) {
-        handler.push({uri: link.href, type: 'link'});
+      if (/group\.php\?gid=\(d{1,3}$/.test(link.attr('href'))) {
+        handler.push({uri: link.attr('href'), type: 'link'});
       }
     });
 
-    handler.parse('a[href^="home.php?mod=space&uid="]', 'space', function (link) {
-      if (/home\.php\?mod=space&uid=\d{1,6}$/.test(link.href)) {
-        handler.push({uri: link.href, type: 'link'});
+    handler.parse($('a[href^="home.php?mod=space&uid="]'), 'space', function (link) {
+      if (/home\.php\?mod=space&uid=\d{1,6}$/.test(link.attr('href'))) {
+        handler.push({uri: link.attr('href'), type: 'link'});
       }
     });
   }
-
-  handler.callback && handler.callback();
 };
@@ -93,0 +91,0 @@

lib/plugins/qicai/index.js

@@ -8,3 +8,7 @@ /**
 var attachment = require('../discuz/attachment');
+var fs = require('fs');
+var assert = require('assert');
 
+var template = fs.readFileSync(path.join(__dirname, '../../../template/index.html')).toString();
+
 exports.parseLinks = function ($, handler) {
@@ -14,40 +18,63 @@ "use strict";
   //pipe images
-  handler.parse('img[file*="forum.php?mod=attachment"]', "images", function (img) {
-    handler.push({uri: img.getAttribute('file'), type: 'attachment'});
-    handler.push({uri: img.getAttribute('src'), type: 'attachment'});
+  handler.parse($('img[file*="forum.php?mod=attachment"]'), "images", function (img) {
+    //discuz default src is a blank image, use file attribute.
+    assert(img);
+    img = $(img);
+    assert(img.attr('file'));
+    handler.push({uri: img.attr('file'), type: 'attachment'});
   });
 
   /*//pipe attachments and not need JB
-  handler.parse('a[href*="forum.php?mod=attachment"]', 'attachments', function (attachment) {
-    var needJB = $('#' + (attachment.parentNode.id || attachment.id) + '_menu').text().indexOf('金币') > 0;
-    if (!needJB) {
-      //console.log('attachment:', attachment.href, $('#' + $(attachment).parent().id + '_menu').text());
-      handler.push({uri: (attachment.href), type: 'attachment'});
-    }
-  });*/
+   handler.parse($('a[href*="forum.php?mod=attachment"]'), 'attachments', function (attachment) {
+   var needJB = $('#' + (attachment.parentNode.id || attachment.id) + '_menu').text().indexOf('金币') > 0;
+   if (!needJB) {
+   //console.log('attachment:', attachment.href, $('#' + $(attachment).parent().id + '_menu').text());
+   handler.push({uri: (attachment.href), type: 'attachment'});
+   }
+   });*/
 
-  /*handler.parse('img', 'image', function (link) {
-    handler.push({uri: link.src, type: 'img'});
+  handler.parse($('img[src$=gif]', '#postlist'), 'image', function (link) {
+    link = $(link);
+    var attr = link.attr('src');
+    assert(attr);
+    if (/\.gif$/.test(attr))
+      handler.push({uri: attr, type: 'img'});
   });
 
-  handler.parse('link[rel="stylesheet"]', 'css', function (link) {
-    handler.push({uri: link.href, type: 'css'});
-  });
-*/
-  handler.parse('a[href*="thread-50247-"]', 'link', function (link) {
-    handler.push({uri: link.href, type: 'link'});
-  });
+
+  /*handler.parse('link[rel="stylesheet"]', 'css', function (link) {
+   handler.push({uri: link.href, type: 'css'});
+   });
+   */
+  if (config.crawlOptions.recursive) {
+    handler.parse($('a[href*="thread-50247-"]'), 'link', function (link) {
+      link = $(link);
+      handler.push({uri: link.attr('href'), type: 'link'});
+    });
+  }
 };
 
+var attachmentFilePath = function (uriObj) {
+  //path name = __dirname/hostname/attachment/tid/uid-paramnames-n
+  //new Buffer(str, 'base64')).toString()
+  var realIdArray = new Buffer(uriObj.query.aid, 'base64').toString().split('|');
+  //console.log('realId.array: ', realIdArray);
+  //console.log('16num to 10', parseInt(realIdArray[1], 16));
 
+
+  var filename = realIdArray.shift() + '.jpg';
+  //console.log('filename:', filename);
+
+  return path.join('attachment', filename);
+};
+
+
 //Get file path of url
-exports.getFileName = function (baseDir, uriObj) {
+exports.getFileName = function (uriObj) {
   var filename, uri = uriObj.uri;
-  var urlObj = url.parse(uri);
+  var urlObj = url.parse(uri, true);
 
   if (uriObj.type === "attachment" && /\.php$/.test(urlObj.pathname)) {
-    return attachment.getAttFilePath(baseDir, uri);
-  }
-
-  if (/(css)|(js)/.test(uriObj.type)) {
+    filename = path.join(path.dirname(urlObj.pathname), attachmentFilePath(urlObj));
+  } else if (/(css)|(js)/.test(uriObj.type)) {
     filename = urlObj.pathname;
@@ -58,5 +85,57 @@ } else {
   if (/\/$/.test(filename)) {
-    filename = 'index.html';
+    filename = path.join(filename, 'index.html');
   }
-  return path.join(baseDir, urlObj.hostname, filename);
+  return filename;
 };
+
+exports.modify = function ($, handler) {
+  "use strict";
+  var attaches = $('img[file]');
+  attaches.each(function (index, attach) {
+    attach = $(attach);
+    attach.attr('src', attachmentFilePath(url.parse(attach.attr('file'), true)));
+  });
+
+  var $ul = $('<ul id="postList"></ul>');
+  var posts = $('#postlist').children('div[id^=post_]');
+
+  //console.log('get posts length:', posts.length);
+
+  posts.each(function (index, post) {
+    var $post = $(post);
+    //console.dir(post);
+    console.assert($post.attr('id'));
+    var postContent = $('<div class="postContent"></div>');
+    var postMessage = $('<div class="postMessage"></div>')
+        .append($post.find('div.pct div.pcb div.t_fsz td[id^=postmessage]').html());
+    postContent.append(postMessage);
+    var postImage = $post.find('div.pct div.pcb div.t_fsz div.pattl')
+        .attr('class', 'postImage');
+    postImage.find('em').remove();
+    postImage.find('div.attp').remove();
+    postImage.find('dl dt').remove();
+    postImage.find('a').each(function (index, a) {
+      a = $(a);
+      a.parent().text(a.text());
+    });
+    //postImage.find('p.mbn').each(function(index,p){
+    //});
+
+    if (postImage.length) {
+      postContent.append(postImage);
+    }
+
+    $ul.append($('<li id="' + $post.attr('id') + '"></li>')
+        .append('<div class="uname"><strong>' + $post.find('div.authi a.xw1').text() + '</strong></div>')
+        .append('<div class="postTime">' + $post.find('div.pi em[id^=authorposton]').text() + '</div>')
+        .append(postContent));
+  });
+
+  $ul.find('*').removeAttr('onclick').removeAttr('onmouseover').removeAttr('file');
+
+  var result = template.replace(/\{\{content\}\}/ig, $ul.toString())
+      .replace(/\{\{pageNav\}\}/ig, $('div.pgt').html());
+
+  //exports.parseLinks($, handler);
+  return result;
+};

package.json

 {
   "name": "crawlit",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": " A node.js crawler support custom crawl rules for special site with thirdpart plugin.",
@@ -11,3 +11,2 @@ "main": "lib/index.js",
   "dependencies": {
-    "cookies.txt": "*",
     "iconv-lite": "*",
@@ -17,5 +16,8 @@ "request": "*",
     "charset": "*",
-    "jsdom": "*"
+    "cheerio": "*"
   },
-  "devDependencies": { },
+  "devDependencies": {
+    "connect":"~2.x",
+    "cookies.txt": "*"
+  },
   "scripts": {},
@@ -22,0 +24,0 @@ "repository": {

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Wildcard dependency

Quality

Package has a dependency with a floating version range. This can cause issues if the dependency publishes a new major version.

Found 1 instance in 1 package

No README

Quality

Package does not have a README. This may indicate a failed publish or a low quality package.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Wildcard dependency

Quality

Package has a dependency with a floating version range. This can cause issues if the dependency publishes a new major version.

Found 2 instances in 1 package

Improved metrics

Total package byte prevSize

37413

increased by18.51%

Dependency count

5

decreased by-16.67%

Number of package files

15

increased by15.38%

Lines of code

1045

increased by24.85%

Worsened metrics

Dev dependency count

2

increased byInfinity%

Number of lines in readme file

0

decreased by-100%

Number of low supply chain risk alerts

6

increased by20%

Dependency changes

• + Addedcheerio@*

• + Addedboolbase@1.0.0(transitive)

• + Addedcheerio@1.0.0(transitive)

• + Addedcheerio-select@2.1.0(transitive)

• + Addedcss-select@5.1.0(transitive)

• + Addedcss-what@6.1.0(transitive)

• + Addeddom-serializer@2.0.0(transitive)

• + Addeddomelementtype@2.3.0(transitive)

• + Addeddomhandler@5.0.3(transitive)

• + Addeddomutils@3.1.0(transitive)

• + Addedencoding-sniffer@0.2.0(transitive)

• + Addedhtmlparser2@9.1.0(transitive)

• + Addednth-check@2.1.1(transitive)

• + Addedparse5-htmlparser2-tree-adapter@7.1.0(transitive)

• + Addedparse5-parser-stream@7.1.2(transitive)

• + Addedundici@6.20.1(transitive)

• - Removedcookies.txt@*

• - Removedjsdom@*

• - Removedagent-base@7.1.1(transitive)

• - Removedcookies.txt@0.1.2(transitive)

• - Removedcssstyle@4.1.0(transitive)

• - Removeddata-urls@5.0.0(transitive)

• - Removeddebug@4.3.7(transitive)

• - Removeddecimal.js@10.4.3(transitive)

• - Removedform-data@4.0.1(transitive)

• - Removedhtml-encoding-sniffer@4.0.0(transitive)

• - Removedhttp-proxy-agent@7.0.2(transitive)

• - Removedhttps-proxy-agent@7.0.5(transitive)

• - Removedis-potential-custom-element-name@1.0.1(transitive)

• - Removedjsdom@25.0.1(transitive)

• - Removedms@2.1.3(transitive)

• - Removednwsapi@2.2.13(transitive)

• - Removedrrweb-cssom@0.7.1(transitive)

• - Removedsaxes@6.0.0(transitive)

• - Removedsymbol-tree@3.2.4(transitive)

• - Removedtldts@6.1.59(transitive)

• - Removedtldts-core@6.1.59(transitive)

• - Removedtough-cookie@5.0.0(transitive)

• - Removedtr46@5.0.0(transitive)

• - Removedw3c-xmlserializer@5.0.0(transitive)

• - Removedwebidl-conversions@7.0.0(transitive)

• - Removedwhatwg-url@14.0.0(transitive)

• - Removedws@8.18.0(transitive)

• - Removedxml-name-validator@5.0.0(transitive)

• - Removedxmlchars@2.2.0(transitive)