v8.0.9

- Stop using purified HTML to extract content (#388)
extractus · May 7, 2024 · b68c8db · b68c8db
1 parent 32a17a2
commit b68c8db
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 5 deletions.
diff --git a/examples/pupperteer/README.md b/examples/pupperteer/README.md
@@ -14,6 +14,6 @@ Start server:
 npm start
 ```
 
-Open `http://localhost:3100/?url=https://www.techradar.com/televisions/samsungs-new-cheaper-oled-tvs-are-now-available-to-buy` to see the result.
+Open `http://localhost:3100/?url=https://client-side-rendering.pages.dev/lorem-ipsum` to see the result.
 
 ---
diff --git a/src/utils/parseFromHtml.js b/src/utils/parseFromHtml.js
@@ -30,8 +30,8 @@ const summarize = (desc, txt, threshold, maxlen) => { // eslint-disable-line
 }
 
 export default async (inputHtml, inputUrl = '', parserOptions = {}) => {
-  const html = purify(inputHtml)
-  const meta = extractMetaData(html)
+  const pureHtml = purify(inputHtml)
+  const meta = extractMetaData(pureHtml)
 
   let title = meta.title
 
@@ -57,7 +57,7 @@ export default async (inputHtml, inputUrl = '', parserOptions = {}) => {
 
   // gather title
   if (!title) {
-    title = extractTitleWithReadability(html, inputUrl)
+    title = extractTitleWithReadability(pureHtml, inputUrl)
   }
   if (!title) {
     return null
@@ -95,7 +95,7 @@ export default async (inputHtml, inputUrl = '', parserOptions = {}) => {
     }
   )
 
-  const content = fns(html)
+  const content = fns(inputHtml)
 
   if (!content) {
     return null