From 9d1c90066dcd22897c9ab21546bc1ab74308ec06 Mon Sep 17 00:00:00 2001
From: Ming Di Leom <2809763-curben@users.noreply.gitlab.com>
Date: Sat, 22 Mar 2025 01:53:32 +0000
Subject: [PATCH] refactor: test url with URL.canParse()

supported by Nodejs >=19.9
---
 package.json  |  2 +-
 src/script.js | 44 ++++++++++++++++++++++++--------------------
 2 files changed, 25 insertions(+), 21 deletions(-)

diff --git a/package.json b/package.json
index eba1852..a51b298 100644
--- a/package.json
+++ b/package.json
@@ -8,7 +8,7 @@
     "unzipper": "^0.12.3"
   },
   "engines": {
-    "node": ">= 18.12.0"
+    "node": ">= 20.9.0"
   },
   "type": "module"
 }
diff --git a/src/script.js b/src/script.js
index 3596917..e3c052f 100644
--- a/src/script.js
+++ b/src/script.js
@@ -7,29 +7,33 @@ import { fileURLToPath } from 'node:url'
 const __dirname = dirname(fileURLToPath(import.meta.url))
 const { parse } = JSON
 
-const f = async () => {
-  // __dirname is src/
-  const outputFile = join(__dirname, '../tmp/domains-raw.txt')
-  await rm(outputFile, { force: true })
-  const domainsPath = join(__dirname, '../tmp/blacklistdomains.json')
+// __dirname is src/
+const outputFile = join(__dirname, '../tmp/domains-raw.txt')
+await rm(outputFile, { force: true })
+const domainsPath = join(__dirname, '../tmp/blacklistdomains.json')
 
-  const domainsStr = await readFile(domainsPath)
-  const domainsArray = parse(domainsStr)
+const domainsStr = await readFile(domainsPath)
+const domainsArray = parse(domainsStr)
 
-  const domains = new Set()
+const domains = new Set()
 
-  for (const { url } of domainsArray) {
-    let parsedUrl = new URL('http://example.com')
-    try {
-      parsedUrl = new URL(url.replace(/\*\./g, ''))
-    } catch {
-      continue
-    }
-    const domain = parsedUrl.hostname.replace(/\\/g, '').replace(/^www\./, '')
-    domains.add(domain)
+for (const { url } of domainsArray) {
+  let domain = ''
+  if (URL.canParse(url)) {
+    const urlObj = new URL(url)
+
+    domain = urlObj.hostname
+  } else {
+    const urlArray = url.split('/')
+    if (urlArray.length >= 3) domain = urlArray[2]
+  }
+  if (domain.length >= 1) {
+    domains.add(domain
+      .replace(/^\*\./, '')
+      .replace(/\\/g, '')
+      .replace(/^www\./, '')
+    )
   }
-
-  await writeFile(outputFile, Array.from(domains).join('\n'))
 }
 
-f()
+await writeFile(outputFile, Array.from(domains).join('\n'))