Skip to content

fix: using GET for candidate checks - sitemaps #3464

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nikitachapovskii-dev merged 5 commits into from
Mar 10, 2026
+20 −15
Merged

fix: using GET for candidate checks - sitemaps #3464

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1fb27c2
fix: using GET for candidate checks - sitemaps
nikitachapovskii-dev Mar 4, 2026
5856195
tests
nikitachapovskii-dev Mar 4, 2026
0086010
fix: parallelize sitemap candidate checks while keeping HEAD
nikitachapovskii-dev Mar 9, 2026
e62cd5f
Update packages/utils/src/internals/sitemap.ts
nikitachapovskii-dev Mar 10, 2026
faec49e
format
nikitachapovskii-dev Mar 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion packages/utils/src/internals/sitemap.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -507,7 +507,7 @@ export async function* discoverValidSitemaps(
const urlExists = async (url: string) => {
const response = await gotScraping({
url,
method: 'HEAD',
method: 'GET',
proxyUrl,
timeout: {
request: requestTimeoutMillis,
Expand Down
44 changes: 22 additions & 22 deletions packages/utils/test/sitemap.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -464,13 +464,13 @@ describe('discoverValidSitemaps', () => {
nock('http://sitemap-discovery.com')
.get('/robots.txt')
.reply(200, 'Sitemap: http://sitemap-discovery.com/some-sitemap.xml')
.head('/some-sitemap.xml')
.get('/some-sitemap.xml')
.reply(200, '')
.head('/sitemap.xml')
.get('/sitemap.xml')
.reply(404, '')
.head('/sitemap.txt')
.get('/sitemap.txt')
.reply(404, '')
.head('/sitemap_index.xml')
.get('/sitemap_index.xml')
.reply(404, '');

const urls = [];
Expand All @@ -485,11 +485,11 @@ describe('discoverValidSitemaps', () => {
nock('http://sitemap-discovery.com')
.get('/robots.txt')
.reply(404)
.head('/sitemap.xml')
.get('/sitemap.xml')
.reply(200, '')
.head('/sitemap.txt')
.get('/sitemap.txt')
.reply(404, '')
.head('/sitemap_index.xml')
.get('/sitemap_index.xml')
.reply(404, '');

const urls = [];
Expand All @@ -504,11 +504,11 @@ describe('discoverValidSitemaps', () => {
nock('http://sitemap-discovery.com')
.get('/robots.txt')
.reply(404)
.head('/sitemap.xml')
.get('/sitemap.xml')
.reply(404, '')
.head('/sitemap.txt')
.get('/sitemap.txt')
.reply(200, '')
.head('/sitemap_index.xml')
.get('/sitemap_index.xml')
.reply(404, '');

const urls = [];
Expand All @@ -523,11 +523,11 @@ describe('discoverValidSitemaps', () => {
nock('http://sitemap-discovery.com')
.get('/robots.txt')
.reply(404)
.head('/sitemap.xml')
.get('/sitemap.xml')
.reply(404, '')
.head('/sitemap.txt')
.get('/sitemap.txt')
.reply(404, '')
.head('/sitemap_index.xml')
.get('/sitemap_index.xml')
.reply(200, '');

const urls = [];
Expand All @@ -554,26 +554,26 @@ describe('discoverValidSitemaps', () => {
.get('/robots.txt')
.delay(10)
.reply(404)
.head('/sitemap.xml')
.get('/sitemap.xml')
.delay(30)
.reply(200, '')
.head('/sitemap.txt')
.get('/sitemap.txt')
.delay(50)
.reply(200, '')
.head('/sitemap_index.xml')
.get('/sitemap_index.xml')
.reply(404);

nock('http://domain-b.com')
.get('/robots.txt')
.delay(20)
.reply(404)
.head('/sitemap.xml')
.get('/sitemap.xml')
.delay(40)
.reply(200, '')
.head('/sitemap.txt')
.get('/sitemap.txt')
.delay(60)
.reply(200, '')
.head('/sitemap_index.xml')
.get('/sitemap_index.xml')
.reply(404);

const urls = [];
Expand Down Expand Up @@ -654,11 +654,11 @@ describe('discoverValidSitemaps', () => {
.get('/robots.txt')
.delay(5_000)
.reply(200, 'Sitemap: http://slow-site.com/sitemap.xml')
.head('/sitemap.xml')
.get('/sitemap.xml')
.reply(200, '')
.head('/sitemap.txt')
.get('/sitemap.txt')
.reply(404, '')
.head('/sitemap_index.xml')
.get('/sitemap_index.xml')
.reply(404, '');

const start = Date.now();
Expand Down