Merge pull request #285 from ndaidong/v7.x.x

v7.0.1
extractus · Aug 12, 2022 · bc25c16 · bc25c16
2 parents d415e55 + fb45060
commit bc25c16
Show file tree

Hide file tree

Showing 9 changed files with 134 additions and 151 deletions.
diff --git a/README.md b/README.md
@@ -45,12 +45,6 @@ extract(url).then((article) => {
 })
 ```
 
-##### Note:
-
-> Since Node.js v14, ECMAScript modules [have became the official standard format](https://nodejs.org/docs/latest-v14.x/api/esm.html#esm_modules_ecmascript_modules).
-> Just ensure that you are [using module system](https://nodejs.org/api/packages.html#determining-module-system) and enjoy with ES6 import/export syntax.
-
-
 ## APIs
 
 - [.extract(String url | String html)](#extractstring-url--string-html)

diff --git a/dist/article-parser.browser.js b/dist/article-parser.browser.js
diff --git a/dist/article-parser.browser.js.map b/dist/article-parser.browser.js.map
diff --git a/dist/cjs/article-parser.js b/dist/cjs/article-parser.js
diff --git a/dist/cjs/article-parser.js.map b/dist/cjs/article-parser.js.map
diff --git a/dist/cjs/package.json b/dist/cjs/package.json
@@ -1,5 +1,5 @@
 {
   "name": "article-parser-cjs",
-  "version": "7.0.0",
+  "version": "7.0.1",
   "main": "./article-parser.js"
 }
diff --git a/package.json b/package.json
@@ -1,5 +1,5 @@
 {
-  "version": "7.0.0",
+  "version": "7.0.1",
   "name": "article-parser",
   "description": "To extract main article from given URL",
   "homepage": "https://ndaidong.github.io/article-parser-demo/",
@@ -21,7 +21,7 @@
   "scripts": {
     "lint": "standard .",
     "pretest": "npm run lint",
-    "test": "cross-env NODE_ENV=test NODE_OPTIONS=--experimental-vm-modules jest --unhandled-rejections=strict",
+    "test": "cross-env NODE_ENV=test NODE_OPTIONS=--experimental-vm-modules jest --coverage=true",
     "build": "node build",
     "eval": "cross-env node eval",
     "eval:cjs": "cross-env node eval.cjs",
@@ -30,13 +30,13 @@
   "dependencies": {
     "@mozilla/readability": "^0.4.2",
     "axios": "^0.27.2",
-    "bellajs": "^11.0.3",
-    "html-crush": "^5.0.20",
+    "bellajs": "^11.0.4",
+    "html-crush": "^5.0.22",
     "linkedom": "^0.14.12",
     "sanitize-html": "^2.7.1",
     "string-comparison": "^1.1.0",
-    "tldts": "^5.7.84",
-    "urlpattern-polyfill": "^5.0.5"
+    "tldts": "^5.7.89",
+    "urlpattern-polyfill": "^5.0.6"
   },
   "standard": {
     "ignore": [
@@ -46,7 +46,7 @@
   "devDependencies": {
     "@types/sanitize-html": "^2.6.2",
     "cross-env": "^7.0.3",
-    "esbuild": "^0.14.50",
+    "esbuild": "^0.15.1",
     "jest": "^28.1.3",
     "nock": "^13.2.9",
     "standard": "^17.0.0"

diff --git a/src/config.js b/src/config.js
@@ -42,7 +42,7 @@ const htmlCrushOptions = {
 const parserOptions = {
   wordsPerMinute: 300, // to estimate "time to read"
   urlsCompareAlgorithm: 'levenshtein', // to find the best url from list
-  descriptionLengthThreshold: 210, // min num of chars required for description
+  descriptionLengthThreshold: 180, // min num of chars required for description
   descriptionTruncateLen: 210, // max num of chars generated for description
   contentLengthThreshold: 200 // content must have at least 200 chars
 }

diff --git a/src/utils/parseFromHtml.js b/src/utils/parseFromHtml.js
@@ -26,20 +26,9 @@ import getTimeToRead from './getTimeToRead.js'
 import { getParserOptions } from '../config.js'
 
 const summarize = (desc, txt, threshold, maxlen) => {
-  const removeFirstParts = (str) => {
-    const arr = str.split(' - ')
-    if (arr.length > 1) {
-      arr.shift()
-      return arr.join(' ')
-    }
-    return str
-  }
-  const metadesc = removeFirstParts(desc)
-  if (metadesc.length > threshold) {
-    return metadesc
-  }
-  const extradesc = truncate(txt, maxlen).replace(/\n/g, ' ')
-  return removeFirstParts(extradesc)
+  return desc.length > threshold
+    ? desc
+    : truncate(txt, maxlen).replace(/\n/g, ' ')
 }
 
 export default async (inputHtml, inputUrl = '') => {