colin
/
gosint-sitecrawl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat(report): add metadata/params/stats + URL normalization; docs: schema; chore: update TODO; test: fresh reports

This commit is contained in:
colin 2025-08-31 09:44:04 -04:00
parent e7b4d33971
commit 3eb9ab48bf
7 changed files with 6256 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
TODO.md
View File

@ -3,10 +3,10 @@
Prioritized from easiest/low-risk to more involved work. Check off as we ship.
### Quick wins (target v0.0.2)
- [ ] Add crawl metadata (startedAt, finishedAt, durationMs)
- [ ] Include run parameters in report (maxDepth, concurrency, timeout, userAgent, sameHostOnly)
- [ ] Status histogram (2xx/3xx/4xx/5xx totals) in summary
- [ ] Normalize and dedupe trailing `/.` URL variants in output
- [x] Add crawl metadata (startedAt, finishedAt, durationMs)
- [x] Include run parameters in report (maxDepth, concurrency, timeout, userAgent, sameHostOnly)
- [x] Status histogram (2xx/3xx/4xx/5xx totals) in summary
- [x] Normalize and dedupe trailing `/.` URL variants in output
- [ ] Add compact `reportSummary` text block to JSON
- [ ] Top external domains with counts
- [ ] Broken links sample (first N) + per-domain broken counts

81
internal/report/report.go
View File

@ -18,31 +18,80 @@ type Report struct {
LinkSources map[string][]string `json:"linkSources"`
MissingInSitemap []string `json:"missingInSitemap,omitempty"`
InSitemapNotCrawled []string `json:"inSitemapNotCrawled,omitempty"`
Metadata Metadata `json:"metadata"`
Params Params `json:"params"`
Stats Stats `json:"stats"`
}
func Build(target string, crawled map[string]struct{}, sitemap map[string]struct{}, crawlErrs map[string]error, check linkcheck.Results, outlinks map[string]map[string]struct{}) Report {
crawledList := keys(crawled)
sitemapList := keys(sitemap)
type Metadata struct {
StartedAt string `json:"startedAt"` // RFC3339
FinishedAt string `json:"finishedAt"` // RFC3339
DurationMs int64 `json:"durationMs"`
}
type Params struct {
MaxDepth int `json:"maxDepth"`
Concurrency int `json:"concurrency"`
TimeoutMs int64 `json:"timeoutMs"`
UserAgent string `json:"userAgent"`
SameHostOnly bool `json:"sameHostOnly"`
}
type Stats struct {
OK int `json:"ok"`
Broken int `json:"broken"`
Status2xx int `json:"status2xx"`
Status3xx int `json:"status3xx"`
Status4xx int `json:"status4xx"`
Status5xx int `json:"status5xx"`
StatusOther int `json:"statusOther"`
}
func Build(target string, crawled map[string]struct{}, sitemap map[string]struct{}, crawlErrs map[string]error, check linkcheck.Results, outlinks map[string]map[string]struct{}, meta Metadata, params Params) Report {
crawledList := sanitizeURLs(keys(crawled))
sitemapList := sanitizeURLs(keys(sitemap))
crawlErrMap := make(map[string]string, len(crawlErrs))
for k, v := range crawlErrs {
crawlErrMap[k] = v.Error()
}
missing := difference(crawled, sitemap)
missingList := keys(missing)
missingList := sanitizeURLs(keys(missing))
inSmNotCrawled := difference(sitemap, crawled)
inSmNotCrawledList := keys(inSmNotCrawled)
inSmNotCrawledList := sanitizeURLs(keys(inSmNotCrawled))
pageOut := make(map[string][]string, len(outlinks))
linkSrc := make(map[string][]string)
for page, set := range outlinks {
lst := keys(set)
lst := sanitizeURLs(keys(set))
pageOut[page] = lst
for _, u := range lst {
linkSrc[u] = append(linkSrc[u], page)
}
}
// Compute simple status histogram
var st Stats
for _, ls := range check.Statuses {
if ls.OK {
st.OK++
} else {
st.Broken++
}
switch {
case ls.StatusCode >= 200 && ls.StatusCode < 300:
st.Status2xx++
case ls.StatusCode >= 300 && ls.StatusCode < 400:
st.Status3xx++
case ls.StatusCode >= 400 && ls.StatusCode < 500:
st.Status4xx++
case ls.StatusCode >= 500 && ls.StatusCode < 600:
st.Status5xx++
default:
st.StatusOther++
}
}
return Report{
Target: target,
CrawledURLs: crawledList,
@ -53,6 +102,9 @@ func Build(target string, crawled map[string]struct{}, sitemap map[string]struct
LinkSources: linkSrc,
MissingInSitemap: missingList,
InSitemapNotCrawled: inSmNotCrawledList,
Metadata: meta,
Params: params,
Stats: st,
}
}
@ -94,3 +146,20 @@ func difference(a, b map[string]struct{}) map[string]struct{} {
}
return res
}
// sanitizeURLs normalizes small variants like trailing "/." to "/" for consistency.
func sanitizeURLs(urls []string) []string {
out := make([]string, 0, len(urls))
for _, u := range urls {
out = append(out, sanitizeURL(u))
}
sort.Strings(out)
return out
}
func sanitizeURL(u string) string {
if len(u) >= 2 && u[len(u)-2:] == "/." {
return u[:len(u)-1]
}
return u
}

17
main.go
View File

@ -47,6 +47,17 @@ func main() {
client := &http.Client{Timeout: timeout}
ctx := context.Background()
// Report metadata
started := time.Now()
meta := report.Metadata{StartedAt: started.UTC().Format(time.RFC3339)}
params := report.Params{
MaxDepth: maxDepth,
Concurrency: concurrency,
TimeoutMs: timeout.Milliseconds(),
UserAgent: userAgent,
SameHostOnly: sameHostOnly,
}
fmt.Fprintf(os.Stderr, "Starting crawl of %s (depth: %d)...\n", target, maxDepth)
// Setup progress counters
@ -137,8 +148,12 @@ func main() {
urlsVisited.Load(), urlsErrored.Load())
}
finished := time.Now()
meta.FinishedAt = finished.UTC().Format(time.RFC3339)
meta.DurationMs = finished.Sub(started).Milliseconds()
fmt.Fprintf(os.Stderr, "Building report...\n")
reports := report.Build(target, visited, smURLs, crawlErrs, checkResults, outlinks)
reports := report.Build(target, visited, smURLs, crawlErrs, checkResults, outlinks, meta, params)
switch output {
case "json":

46
reports/REPORT_SCHEMA.md
View File

@ -21,7 +21,28 @@ This document describes the structure of the JSON reports produced by `urlcrawle
"https://example.com/about": ["https://example.com"]
},
"missingInSitemap": ["https://example.com/page-not-in-sitemap"],
"inSitemapNotCrawled": ["https://example.com/deferred"]
"inSitemapNotCrawled": ["https://example.com/deferred"],
"metadata": {
"startedAt": "2025-08-31T12:34:56Z",
"finishedAt": "2025-08-31T12:35:57Z",
"durationMs": 61000
},
"params": {
"maxDepth": 1,
"concurrency": 5,
"timeoutMs": 5000,
"userAgent": "urlcrawler/1.0",
"sameHostOnly": true
},
"stats": {
"ok": 12,
"broken": 1,
"status2xx": 12,
"status3xx": 0,
"status4xx": 1,
"status5xx": 0,
"statusOther": 0
}
}
```
@ -49,9 +70,30 @@ This document describes the structure of the JSON reports produced by `urlcrawle
- **inSitemapNotCrawled** (string[]; optional): URLs present in the sitemap that were not crawled (e.g., due to depth limits or off-host rules).
- **metadata** (object): Crawl timing information.
- **startedAt** (string, RFC3339)
- **finishedAt** (string, RFC3339)
- **durationMs** (number)
- **params** (object): Parameters used for the run.
- **maxDepth** (number)
- **concurrency** (number)
- **timeoutMs** (number)
- **userAgent** (string)
- **sameHostOnly** (boolean)
- **stats** (object): Summary of link status results.
- **ok** (number)
- **broken** (number)
- **status2xx** (number)
- **status3xx** (number)
- **status4xx** (number)
- **status5xx** (number)
- **statusOther** (number)
### Notes
- URLs are normalized and deduplicated during crawl.
- URLs are normalized and deduplicated during crawl. Minor variants like trailing `/.` are normalized in output.
- Content-type filtering: only `text/html` pages are parsed for outlinks.
- Sitemap fetching is best-effort; absence is not treated as an error.
- The JSON lists are sorted to produce stable outputs across runs.

5724
reports/engagewr.ca.json Normal file
View File

File diff suppressed because it is too large Load Diff

330
reports/lilsgym.ca.json Normal file
View File

@ -0,0 +1,330 @@
{
"target": "https://lilsgym.ca",
"crawledUrls": [
"https://lilsgym.ca",
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/contact.html?type=group-training",
"https://lilsgym.ca/contact.html?type=membership",
"https://lilsgym.ca/facility.html",
"https://lilsgym.ca/grouptraining.html",
"https://lilsgym.ca/personaltraining.html"
],
"sitemapUrls": [
"https://lilsgym.ca/",
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/facility.html",
"https://lilsgym.ca/grouptraining.html",
"https://lilsgym.ca/personaltraining.html",
"https://lilsgym.ca/policies.html",
"https://lilsgym.ca/privacy.html"
],
"linkStatuses": [
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0313_00-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/facility.html",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0333_00-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/facility-new/IMG_6741.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/personaltraining.html",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/contact.html",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0335_00-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0314_00-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/facility-new/IMG_6731.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_9115.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/contact.html?type=membership",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0332_00-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/facility-new/IMG_6739.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/grouptraining.html",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0339_00-1-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/contact.html?type=group-training",
"statusCode": 200,
"ok": true
},
{
"url": "https://titan-training.ca/",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0331_00-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://maps.google.com/?q=32+Weber+St+W,+Kitchener,+ON+N2H+3Z2",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0306_00-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/facility-new/rotated/IMG_6738_rotated.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://lilsgym.ca/assets/img/webp/IMG_0323_00-1024x768.webp",
"statusCode": 200,
"ok": true
},
{
"url": "https://www.blackswanstrength.com/",
"statusCode": 200,
"ok": true
},
{
"url": "https://www.mutantfrogfitness.ca/",
"statusCode": 200,
"ok": true
},
{
"url": "https://booking.setmore.com/scheduleappointment/0b712222-be8d-4521-afc7-afbed7d7a4b4?lang=",
"statusCode": 200,
"ok": true
}
],
"pageOutlinks": {
"https://lilsgym.ca": [
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/grouptraining.html",
"https://lilsgym.ca/personaltraining.html"
],
"https://lilsgym.ca/contact.html": [
"https://booking.setmore.com/scheduleappointment/0b712222-be8d-4521-afc7-afbed7d7a4b4?lang=",
"https://lilsgym.ca/contact.html",
"https://maps.google.com/?q=32+Weber+St+W,+Kitchener,+ON+N2H+3Z2"
],
"https://lilsgym.ca/contact.html?type=group-training": [
"https://booking.setmore.com/scheduleappointment/0b712222-be8d-4521-afc7-afbed7d7a4b4?lang=",
"https://lilsgym.ca/contact.html?type=group-training",
"https://maps.google.com/?q=32+Weber+St+W,+Kitchener,+ON+N2H+3Z2"
],
"https://lilsgym.ca/contact.html?type=membership": [
"https://booking.setmore.com/scheduleappointment/0b712222-be8d-4521-afc7-afbed7d7a4b4?lang=",
"https://lilsgym.ca/contact.html?type=membership",
"https://maps.google.com/?q=32+Weber+St+W,+Kitchener,+ON+N2H+3Z2"
],
"https://lilsgym.ca/facility.html": [
"https://lilsgym.ca/assets/img/facility-new/IMG_6731.webp",
"https://lilsgym.ca/assets/img/facility-new/IMG_6739.webp",
"https://lilsgym.ca/assets/img/facility-new/IMG_6741.webp",
"https://lilsgym.ca/assets/img/facility-new/rotated/IMG_6738_rotated.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0306_00-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0313_00-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0314_00-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0323_00-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0331_00-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0332_00-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0333_00-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0335_00-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_0339_00-1-1024x768.webp",
"https://lilsgym.ca/assets/img/webp/IMG_9115.webp",
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/facility.html",
"https://lilsgym.ca/grouptraining.html"
],
"https://lilsgym.ca/grouptraining.html": [
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/contact.html?type=group-training",
"https://lilsgym.ca/contact.html?type=membership",
"https://lilsgym.ca/grouptraining.html"
],
"https://lilsgym.ca/personaltraining.html": [
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/facility.html",
"https://lilsgym.ca/personaltraining.html",
"https://titan-training.ca/",
"https://www.blackswanstrength.com/",
"https://www.mutantfrogfitness.ca/"
]
},
"linkSources": {
"https://booking.setmore.com/scheduleappointment/0b712222-be8d-4521-afc7-afbed7d7a4b4?lang=": [
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/contact.html?type=membership",
"https://lilsgym.ca/contact.html?type=group-training"
],
"https://lilsgym.ca/assets/img/facility-new/IMG_6731.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/facility-new/IMG_6739.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/facility-new/IMG_6741.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/facility-new/rotated/IMG_6738_rotated.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0306_00-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0313_00-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0314_00-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0323_00-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0331_00-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0332_00-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0333_00-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0335_00-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_0339_00-1-1024x768.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/assets/img/webp/IMG_9115.webp": [
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/contact.html": [
"https://lilsgym.ca/grouptraining.html",
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/personaltraining.html",
"https://lilsgym.ca/facility.html",
"https://lilsgym.ca"
],
"https://lilsgym.ca/contact.html?type=group-training": [
"https://lilsgym.ca/grouptraining.html",
"https://lilsgym.ca/contact.html?type=group-training"
],
"https://lilsgym.ca/contact.html?type=membership": [
"https://lilsgym.ca/grouptraining.html",
"https://lilsgym.ca/contact.html?type=membership"
],
"https://lilsgym.ca/facility.html": [
"https://lilsgym.ca/personaltraining.html",
"https://lilsgym.ca/facility.html"
],
"https://lilsgym.ca/grouptraining.html": [
"https://lilsgym.ca/grouptraining.html",
"https://lilsgym.ca/facility.html",
"https://lilsgym.ca"
],
"https://lilsgym.ca/personaltraining.html": [
"https://lilsgym.ca/personaltraining.html",
"https://lilsgym.ca"
],
"https://maps.google.com/?q=32+Weber+St+W,+Kitchener,+ON+N2H+3Z2": [
"https://lilsgym.ca/contact.html",
"https://lilsgym.ca/contact.html?type=membership",
"https://lilsgym.ca/contact.html?type=group-training"
],
"https://titan-training.ca/": [
"https://lilsgym.ca/personaltraining.html"
],
"https://www.blackswanstrength.com/": [
"https://lilsgym.ca/personaltraining.html"
],
"https://www.mutantfrogfitness.ca/": [
"https://lilsgym.ca/personaltraining.html"
]
},
"missingInSitemap": [
"https://lilsgym.ca",
"https://lilsgym.ca/contact.html?type=group-training",
"https://lilsgym.ca/contact.html?type=membership"
],
"inSitemapNotCrawled": [
"https://lilsgym.ca/",
"https://lilsgym.ca/policies.html",
"https://lilsgym.ca/privacy.html"
],
"metadata": {
"startedAt": "2025-08-31T13:31:06Z",
"finishedAt": "2025-08-31T13:31:08Z",
"durationMs": 1610
},
"params": {
"maxDepth": 2,
"concurrency": 5,
"timeoutMs": 5000,
"userAgent": "urlcrawler/1.0",
"sameHostOnly": true
},
"stats": {
"ok": 26,
"broken": 0,
"status2xx": 26,
"status3xx": 0,
"status4xx": 0,
"status5xx": 0,
"statusOther": 0
}
}

107
reports/titan-training.ca.json
View File

@ -3,7 +3,7 @@
"crawledUrls": [
"https://titan-training.ca",
"https://titan-training.ca/",
"https://titan-training.ca/.",
"https://titan-training.ca/",
"https://titan-training.ca/cdn-cgi/l/email-protection",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/product-details/product/681331db52e2115c63435275",
@ -16,7 +16,27 @@
],
"linkStatuses": [
{
"url": "https://titan-training.ca/products-list",
"url": "https://titan-training.ca",
"statusCode": 200,
"ok": true
},
{
"url": "https://titan-training.ca/titan-training.ca",
"statusCode": 200,
"ok": true
},
{
"url": "https://www.google.com/maps/search?api=1\u0026query=Google\u0026query_place_id=ChIJwzSnW430K4gRU8zOBshqKAg",
"statusCode": 404,
"ok": false
},
{
"url": "https://titan-training.ca/.",
"statusCode": 200,
"ok": true
},
{
"url": "https://titan-training.ca/product-details/product/titan-training.ca",
"statusCode": 200,
"ok": true
},
@ -26,12 +46,7 @@
"ok": true
},
{
"url": "https://www.cloudflare.com/5xx-error-landing",
"statusCode": 200,
"ok": true
},
{
"url": "https://titan-training.ca",
"url": "https://www.youtube.com/channel/UCOtL1D3s3fBxHJLAyF5kNRA/featured?view_as=public",
"statusCode": 200,
"ok": true
},
@ -41,17 +56,7 @@
"ok": true
},
{
"url": "https://www.youtube.com/channel/UCOtL1D3s3fBxHJLAyF5kNRA/featured?view_as=public",
"statusCode": 200,
"ok": true
},
{
"url": "https://developers.cloudflare.com/waf/tools/scrape-shield/email-address-obfuscation",
"statusCode": 200,
"ok": true
},
{
"url": "https://developers.cloudflare.com/fundamentals/setup/account/create-account",
"url": "https://titan-training.ca/products-list",
"statusCode": 200,
"ok": true
},
@ -60,6 +65,11 @@
"statusCode": 200,
"ok": true
},
{
"url": "https://titan-training.ca/product-details/product/681331db52e2115c63435275",
"statusCode": 200,
"ok": true
},
{
"url": "https://www.cloudflare.com/sign-up?utm_source=email_protection",
"statusCode": 403,
@ -71,39 +81,29 @@
"ok": true
},
{
"url": "https://titan-training.ca/titan-training.ca",
"url": "https://developers.cloudflare.com/waf/tools/scrape-shield/email-address-obfuscation",
"statusCode": 200,
"ok": true
},
{
"url": "https://titan-training.ca/product-details/product/681331db52e2115c63435275",
"url": "https://www.cloudflare.com/5xx-error-landing",
"statusCode": 200,
"ok": true
},
{
"url": "https://titan-training.ca/.",
"url": "https://developers.cloudflare.com/fundamentals/setup/account/create-account",
"statusCode": 200,
"ok": true
},
{
"url": "https://www.google.com/maps/search?api=1\u0026query=Google\u0026query_place_id=ChIJwzSnW430K4gRU8zOBshqKAg",
"statusCode": 404,
"ok": false
},
{
"url": "https://www.instagram.com/titan__training",
"statusCode": 200,
"ok": true
},
{
"url": "https://titan-training.ca/product-details/product/titan-training.ca",
"statusCode": 200,
"ok": true
}
],
"pageOutlinks": {
"https://titan-training.ca": [
"https://titan-training.ca/.",
"https://titan-training.ca/",
"https://titan-training.ca/cdn-cgi/l/email-protection",
"https://titan-training.ca/products-list",
"https://titan-training.ca/titan-training.ca",
@ -188,19 +188,17 @@
],
"https://titan-training.ca/": [
"https://titan-training.ca/",
"https://titan-training.ca/.",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/.",
"https://titan-training.ca/product-details/product/681331db52e2115c63435275",
"https://titan-training.ca",
"https://titan-training.ca/products-list"
],
"https://titan-training.ca/.": [
"https://titan-training.ca"
],
"https://titan-training.ca/cdn-cgi/l/email-protection": [
"https://titan-training.ca/",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/.",
"https://titan-training.ca/titan-training.ca",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/product-details/product/681331db52e2115c63435275",
"https://titan-training.ca",
"https://titan-training.ca/products-list"
@ -219,9 +217,9 @@
],
"https://titan-training.ca/products-list": [
"https://titan-training.ca/",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/.",
"https://titan-training.ca/titan-training.ca",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/product-details/product/681331db52e2115c63435275",
"https://titan-training.ca",
"https://titan-training.ca/products-list"
@ -241,9 +239,9 @@
],
"https://www.facebook.com/titantrainingkw": [
"https://titan-training.ca/",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/.",
"https://titan-training.ca/titan-training.ca",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/product-details/product/681331db52e2115c63435275",
"https://titan-training.ca",
"https://titan-training.ca/products-list"
@ -256,18 +254,18 @@
],
"https://www.instagram.com/titan__training": [
"https://titan-training.ca/",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/.",
"https://titan-training.ca/titan-training.ca",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/product-details/product/681331db52e2115c63435275",
"https://titan-training.ca",
"https://titan-training.ca/products-list"
],
"https://www.youtube.com/channel/UCOtL1D3s3fBxHJLAyF5kNRA/featured?view_as=public": [
"https://titan-training.ca/",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/.",
"https://titan-training.ca/titan-training.ca",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/product-details/product/681331db52e2115c63435275",
"https://titan-training.ca",
"https://titan-training.ca/products-list"
@ -276,7 +274,7 @@
"missingInSitemap": [
"https://titan-training.ca",
"https://titan-training.ca/",
"https://titan-training.ca/.",
"https://titan-training.ca/",
"https://titan-training.ca/cdn-cgi/l/email-protection",
"https://titan-training.ca/product-details/product/681330e25a7661691fe205c8",
"https://titan-training.ca/product-details/product/681331db52e2115c63435275",
@ -286,5 +284,26 @@
"inSitemapNotCrawled": [
"https://titan-training.ca/home",
"https://titan-training.ca/test_path?item=123"
]
],
"metadata": {
"startedAt": "2025-08-31T13:41:55Z",
"finishedAt": "2025-08-31T13:41:58Z",
"durationMs": 2547
},
"params": {
"maxDepth": 2,
"concurrency": 5,
"timeoutMs": 5000,
"userAgent": "urlcrawler/1.0",
"sameHostOnly": true
},
"stats": {
"ok": 15,
"broken": 2,
"status2xx": 15,
"status3xx": 0,
"status4xx": 2,
"status5xx": 0,
"statusOther": 0
}
}