Merge 26a13e4 into 0e80ba3

.github/workflows/ci-test.yml

@@ -8,11 +8,11 @@ on: [push, pull_request]
 jobs:
   test:
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
 
     strategy:
       matrix:
-        node_version: [14.x, 15.x, 16.x, 17.x, 18.x]
+        node_version: [14.x, 15.x, 16.x, 17.x, 18.x, 19.x]
 
     steps:
     - uses: actions/checkout@v2
@@ -24,7 +24,6 @@ jobs:
 
     - name: run npm scripts
       run: |
-        npm i -g standard
         npm install
         npm run lint
         npm run build --if-present

README.md

@@ -10,11 +10,35 @@ Extract main article, main image and meta data from URL.
 
 [![Deploy](https://button.deta.dev/1/svg)](https://go.deta.dev/deploy?repo=https://github.com/ndaidong/article-parser-deta)
 
+
+## Intro
+
+*article-parser* is a part of tool sets for content builder:
+
+- [feed-reader](https://github.com/ndaidong/feed-reader): extract & normalize RSS/ATOM/JSON feed
+- [article-parser](https://github.com/ndaidong/article-parser): extract main article from given URL
+- [oembed-parser](https://github.com/ndaidong/oembed-parser): extract oEmbed data from supported providers
+
+You can use one or combination of these tools to build news sites, create automated content systems for marketing campaign or gather dataset for NLP projects...
+
+```
+                                    ┌────────────────┐
+                            ┌───────► article-parser ├──────────┐
+                            │       └────────────────┘          │
+┌─────────────┐   ┌─────────┴────┐                     ┌────────▼─────────┐   ┌─────────────┐
+│ feed-reader ├───► feed entries │                     │ content database ├───► public APIs │
+└─────────────┘   └─────────┬────┘                     └────────▲─────────┘   └─────────────┘
+                            │       ┌────────────────┐          │
+                            └───────► oembed-parser  ├──────────┘
+                                    └────────────────┘
+```
+
 ## Demo
 
 - [Give it a try!](https://demos.pwshub.com/article-parser)
 - [Example FaaS](https://extract-article.deta.dev/?url=https://www.freethink.com/technology/virtual-world)
 
+
 ## Install & Usage
 
 ### Node.js
@@ -215,7 +239,7 @@ Basically, the meaning of `transformation` can be interpreted like this:
 
 Here is an example transformation:
 
-```ts
+```js
 {
   patterns: [
     /([\w]+.)?domain.tld\/*/,

SECURITY.md

@@ -0,0 +1,17 @@
+# Security Policy
+
+## Supported Versions
+
+Due to resource limitations, only the latest stable minor release is getting bugfixes (including security ones).
+
+So e.g. if the latest stable version is 7.2.5, then 7.2.x line will still get security fixes but older versions (like 7.1.x) won't get any fixes.
+
+Description above is a general rule and may be altered on case by case basis.
+
+## Reporting a Vulnerability
+
+You can report low severity vulnerabilities as GitHub issues.
+
+More severe vulnerabilities should be reported to the email ndaidong@pwshub.com.
+
+---

dist/cjs/package.json

@@ -1,5 +1,5 @@
 {
   "name": "article-parser",
-  "version": "7.2.4",
+  "version": "7.2.5",
   "main": "./article-parser.js"
 }

package.json

@@ -1,5 +1,5 @@
 {
-  "version": "7.2.4",
+  "version": "7.2.5",
   "name": "article-parser",
   "description": "To extract main article from given URL",
   "homepage": "https://demos.pwshub.com/article-parser",
@@ -33,10 +33,10 @@
   },
   "dependencies": {
     "@mozilla/readability": "^0.4.2",
-    "bellajs": "^11.0.7",
+    "bellajs": "^11.1.1",
     "cross-fetch": "^3.1.5",
-    "linkedom": "^0.14.16",
-    "sanitize-html": "^2.7.2",
+    "linkedom": "^0.14.19",
+    "sanitize-html": "^2.7.3",
     "string-similarity": "^4.0.4"
   },
   "standard": {
@@ -47,9 +47,10 @@
   },
   "devDependencies": {
     "@types/sanitize-html": "^2.6.2",
-    "esbuild": "^0.15.9",
-    "jest": "^29.0.3",
-    "nock": "^13.2.9"
+    "esbuild": "^0.15.13",
+    "jest": "^29.3.1",
+    "nock": "^13.2.9",
+    "standard": "^17.0.0"
   },
   "keywords": [
     "article",

src/utils/extractMetaData.js

@@ -41,7 +41,10 @@ export default (html) => {
     'twitter:description'
   ]
   const imageAttrs = [
+    'image',
     'og:image',
+    'og:image:url',
+    'og:image:secure_url',
     'twitter:image',
     'twitter:image:src'
   ]
@@ -57,7 +60,18 @@ export default (html) => {
     'article:published_time',
     'article:modified_time',
     'og:updated_time',
-    'datepublished'
+    'dc.date',
+    'dc.date.issued',
+    'dc.date.created',
+    'dc:created',
+    'dcterms.date',
+    'datepublished',
+    'datemodified',
+    'updated_time',
+    'modified_time',
+    'published_time',
+    'release_date',
+    'date'
   ]
 
   const document = new DOMParser().parseFromString(html, 'text/html')