v8.0.8

- Merge pr extractus#374 by @andremacola (issue extractus#373)
- Update dependencies
- Update CI config
- Fix function call in eval.js

.github/workflows/ci-test.yml

@@ -12,13 +12,13 @@ jobs:
 
     strategy:
       matrix:
-        node_version: [18.x, 20.x]
+        node_version: [18.x, 20.x, 21.x]
 
     steps:
     - uses: actions/checkout@v3
 
     - name: setup Node.js v${{ matrix.node_version }}
-      uses: actions/setup-node@v3
+      uses: actions/setup-node@v4
       with:
         node-version: ${{ matrix.node_version }}
 
@@ -31,8 +31,8 @@ jobs:
         npm run build --if-present
         npm run test
 
-    - name: Coveralls GitHub Action
-      uses: coverallsapp/github-action@1.1.3
+    - name: Report Coveralls
+      uses: coverallsapp/github-action@v2
       with:
         github-token: ${{ secrets.GITHUB_TOKEN }}
 
@@ -43,6 +43,3 @@ jobs:
         key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
         restore-keys: |
           ${{ runner.os }}-node-
-
-
-

.github/workflows/codeql-analysis.yml

@@ -38,7 +38,7 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

README.md

@@ -105,6 +105,7 @@ The result - `article` - can be `null` or an object with the following structure
   favicon: String,
   content: String,
   published: Date String,
+  type: String, // page type
   source: String, // original publisher
   links: Array, // list of alternative links
   ttr: Number, // time to read in second, 0 = unknown

eval.js

@@ -6,7 +6,7 @@ import { readFileSync, writeFileSync, existsSync } from 'node:fs'
 import { slugify } from 'bellajs'
 
 import { isValid as isValidUrl } from './src/utils/linker.js'
-import { extract } from './src/main.js'
+import { extractFromHtml } from './src/main.js'
 
 if (!existsSync('evaluation')) {
   execSync('mkdir evaluation')
@@ -15,7 +15,12 @@ if (!existsSync('evaluation')) {
 const extractFromUrl = async (url) => {
   try {
     console.time('extraction')
-    const art = await extract(url)
+    const res = await fetch(url)
+    const buffer = await res.arrayBuffer()
+    const decoder = new TextDecoder('iso-8859-1')
+    const html = decoder.decode(buffer)
+
+    const art = await extractFromHtml(html)
     console.log(art)
     const slug = slugify(art.title)
     writeFileSync(`evaluation/${slug}.html`, art.content, 'utf8')
@@ -28,7 +33,7 @@ const extractFromUrl = async (url) => {
 const extractFromFile = async (fpath) => {
   try {
     const html = readFileSync(fpath, 'utf8')
-    const art = await extract(html)
+    const art = await extractFromHtml(html)
     console.log(art)
   } catch (err) {
     console.trace(err)

package.json

@@ -1,5 +1,5 @@
 {
-  "version": "8.0.3",
+  "version": "8.0.4",
   "name": "@extractus/article-extractor",
   "description": "To extract main article from given URL",
   "homepage": "https://github.com/extractus/article-extractor",
@@ -33,15 +33,15 @@
     "@mozilla/readability": "^0.4.4",
     "bellajs": "^11.1.2",
     "cross-fetch": "^4.0.0",
-    "linkedom": "^0.15.1",
+    "linkedom": "^0.16.4",
     "sanitize-html": "2.11.0"
   },
   "devDependencies": {
-    "@types/sanitize-html": "^2.9.0",
-    "eslint": "^8.47.0",
-    "https-proxy-agent": "^7.0.1",
-    "jest": "^29.6.2",
-    "nock": "^13.3.2"
+    "@types/sanitize-html": "^2.9.5",
+    "eslint": "^8.55.0",
+    "https-proxy-agent": "^7.0.2",
+    "jest": "^29.7.0",
+    "nock": "^13.4.0"
   },
   "keywords": [
     "article",