Zengtudor/Nuxt
1
0
Fork 0
mirror of https://github.com/nuxt/nuxt.git synced 2024-11-21 21:25:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

ci(crawl): ignore <a> links without hrefs (#7925)

Browse Source 
Co-authored-by: Alexander Lichter <github@lichter.io>
This commit is contained in:
Daniel Roe 2022-10-03 14:38:06 +01:00 committed by GitHub
parent d25dafef49
commit c11630328d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
scripts/crawl.mjs
View File

@ -32,6 +32,13 @@ const erroredUrls = new Set()
* @param {string | undefined} referrer The referring page
*/
function queue (path, referrer) {
if (!path) {
const message = chalk.red(`${chalk.bold('✗')} ${referrer} linked to empty href`)
if (isCI) { actions.error(message) }
logger.log(message)
return
}
if (urlsToOmit.some(url => path.startsWith(url))) { return }
const { pathname, origin } = new URL(path, referrer)
@ -80,7 +87,11 @@ const crawler = new Crawler({
return done()
}
$('a:not([href*=mailto])').each((_, el) => 'attribs' in el && queue(el.attribs.href, uri))
$('a:not([href*=mailto]):not([href*=tel])').each((_, el) => {
if ('attribs' in el && 'href' in el.attribs) {
queue(el.attribs.href, uri)
}
})
logger.success(chalk.green(uri))
logger.debug(uri, `[${crawler.queueSize} / ${urls.size}]`)