Merge pull request #275 from ndaidong/6.0.5

6.0.5
extractus · Jul 4, 2022 · 0a70987 · 0a70987
2 parents fb32038 + 5074746
commit 0a70987
Show file tree

Hide file tree

Showing 10 changed files with 28 additions and 16 deletions.
diff --git a/README.md b/README.md
@@ -121,7 +121,7 @@ extract('https://bad-website.domain/page/article')
 addQueryRules([
   {
     patterns: [
-      { hostname: 'bad-website.domain' }
+      '*://bad-website.domain/*'
     ],
     selector: '#noop_article_locates_here',
     unwanted: [
@@ -137,11 +137,16 @@ addQueryRules([
 extract('https://bad-website.domain/page/article')
 ````
 
-Regarding pattern structure, please refer [URL Pattern API](https://developer.mozilla.org/en-US/docs/Web/API/URL_Pattern_API).
+#### Query Rule
+
+A query rule is an object with the following properties:
 
-While adding rules, you can specify a `transform()` function to fine-tune article content more thoroughly.
+- `patterns`: required, list of [URLPattern](https://developer.mozilla.org/en-US/docs/Web/API/URLPattern) objects. See [the syntax for patterns](https://developer.mozilla.org/en-US/docs/Web/API/URL_Pattern_API).
+- `selector`: optional, where to find the HTMLElement which contains main article content
+- `unwanted`: optional, list of selectors to filter unwanted HTML elements from the last result
+- `transform`, optional, function to fine-tune article content more thoroughly
 
-Example rule with transformation:
+Here is an example using rule with transformation:
 
 ```js
 import { addQueryRules } from 'article-parser'

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": "6.0.4",
+  "version": "6.0.5",
   "main": "./article-parser.js"
 }
diff --git a/package.json b/package.json
@@ -1,5 +1,5 @@
 {
-  "version": "6.0.4",
+  "version": "6.0.5",
   "name": "article-parser",
   "description": "To extract main article from given URL",
   "homepage": "https://ndaidong.github.io/article-parser-demo/",

diff --git a/src/rules.js b/src/rules.js
@@ -73,7 +73,7 @@ export const rules = [
   },
   {
     patterns: [
-      '*://zingnews.vn/*'
+      { hostname: 'zingnews.vn' }
     ],
     unwanted: [
       '.the-article-category',

diff --git a/src/utils/findRulesByUrl.js b/src/utils/findRulesByUrl.js
@@ -12,7 +12,7 @@ export default (urls = []) => {
   const rules = getQueryRules()
   for (const rule of rules) {
     const { patterns } = rule
-    const matched = urls.some((url) => patterns.some((pattern) => new URLPattern(pattern).exec(url)))
+    const matched = urls.some((url) => patterns.some((pattern) => new URLPattern(pattern).test(url)))
     if (matched) {
       return rule
     }

diff --git a/src/utils/findRulesByUrl.test.js b/src/utils/findRulesByUrl.test.js
@@ -11,6 +11,13 @@ describe('test findRulesByUrl()', () => {
       urls: [{}, ''],
       expectation: {}
     },
+    {
+      urls: ['https://zingnews.vn/article-slug.html'],
+      expectation: (result, expect) => {
+        expect(result).toBeTruthy()
+        expect(result.unwanted).toContain('.the-article-category')
+      }
+    },
     {
       urls: [1209, 'https://vietnamnet.vn/path/to/article'],
       expectation: (result, expect) => {