c2b61bf8e9
- golem15_seo_crawls, crawl pages, links, issues and ignores (P33-37) - classes/crawl: fetchguard client on the site host and its www twin, sitemap index and robots.txt seeds, two workers with a delay, limits - h1_missing and h1_multiple with the P33-38 fix route - POST /_seo/api/v1/crawls queues the golem15.seo.crawl job; GET /issues answers the stored issues with id, severity, source, fix, found_at, ignored and crawl_id
49 lines
1.9 KiB
Go
49 lines
1.9 KiB
Go
package seo_test
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"git.golem15.com/golem15/summercms/modules/pact"
|
|
)
|
|
|
|
// TestCrawlerTracer is the end-to-end path (D-14): an administrator
|
|
// starts a crawl through the API, the crawl job fetches the site with the
|
|
// crawler's User-Agent, and GET /issues lists the page with two H1
|
|
// headings as an error with how to fix it: code for H1 headings of the
|
|
// template, the record type's headings tool for an H1 inside the record's
|
|
// own content.
|
|
func TestCrawlerTracer(t *testing.T) {
|
|
env := bootCrawlEnv(t)
|
|
token := env.admin(t, true)
|
|
setCrawlRecords(t, map[string][]crawlRecord{
|
|
crawlPostType: {{id: "1", path: "/c/two-h1", title: "Post title", headings: []pact.ContentHeading{{Level: 1, Text: "Inside the body"}}}},
|
|
})
|
|
site := newFakeSite()
|
|
site.sitemap("/", "/p/two-h1", "/c/two-h1")
|
|
site.plant(
|
|
doc{path: "/", title: "Home", links: []string{"/p/two-h1", "/c/two-h1"}},
|
|
doc{path: "/p/two-h1", title: "Template page", h1: []string{"Template page", "Another H1"}},
|
|
doc{path: "/c/two-h1", title: "Post title", h1: []string{"Post title", "Inside the body"}},
|
|
)
|
|
|
|
env.crawlOnce(t, token, siteCtx(t, site))
|
|
|
|
list := env.issues(t, token, "")
|
|
tpl := findIssue(t, list, "h1_multiple", "/p/two-h1")
|
|
if tpl.Severity != "error" || tpl.Fix != "code" || tpl.Tool != "" || tpl.Source != "crawl" || tpl.Details["what"] == nil || tpl.Details["count"] != float64(2) {
|
|
t.Fatalf("template h1_multiple = %+v", tpl)
|
|
}
|
|
content := findIssue(t, list, "h1_multiple", "/c/two-h1")
|
|
if content.Fix != "tool" || content.Tool != "acme_fix_headings" || content.CrawlID == nil || content.ID == 0 {
|
|
t.Fatalf("content h1_multiple = %+v", content)
|
|
}
|
|
if !site.requested("/sitemap-pages-1.xml") || !site.requested("/c/two-h1") {
|
|
t.Fatalf("crawler requests = %v", site.requests)
|
|
}
|
|
for _, ua := range site.agents {
|
|
if ua != "SummerCMS-SEO-Crawler/1 (+https://www.example.test)" {
|
|
t.Fatalf("User-Agent = %q", ua)
|
|
}
|
|
}
|
|
}
|