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
54 lines
2.4 KiB
YAML
54 lines
2.4 KiB
YAML
# golem15.seo defaults, read as golem15.seo.<key>.
|
|
#
|
|
# site_url is the public origin of the site (for example
|
|
# https://example.com). Canonical, og:url and every other absolute URL the
|
|
# resolver answers start with it; when it is empty, app.url is used. The
|
|
# request's Host header is never used.
|
|
site_url: ""
|
|
#
|
|
# unprefixed_locale names the locale whose public URLs carry no locale
|
|
# prefix (for example pl on a site whose English pages start with /en).
|
|
# Empty leaves the choice to each content type.
|
|
unprefixed_locale: ""
|
|
#
|
|
# notfound_token is the shared secret the frontend server sends as
|
|
# "Authorization: Bearer <token>" with each 404 report to
|
|
# POST /_seo/api/v1/notfound. Empty turns the endpoint off (it answers 404).
|
|
notfound_token: ""
|
|
#
|
|
# notfound_max_rows caps the 404 log; new addresses beyond it are dropped,
|
|
# with one warning an hour.
|
|
notfound_max_rows: 10000
|
|
#
|
|
# robots_sitemaps lists the sitemap addresses robots.txt names, one
|
|
# "Sitemap:" line each, made absolute on the site URL. Unset, robots.txt
|
|
# names the sitemap plugin's index (its site address plus /sitemap.xml);
|
|
# the per-type files are never listed, the index names them. Set it only
|
|
# to name other sitemaps:
|
|
# robots_sitemaps: ["/sitemap.xml"]
|
|
#
|
|
# route_report_token is the shared secret the frontend server sends as
|
|
# "Authorization: Bearer <token>" with its route report to
|
|
# POST /_seo/api/v1/registry/routes (the page registry). Empty uses
|
|
# notfound_token; both empty turn the report off (it answers 404).
|
|
route_report_token: ""
|
|
#
|
|
# og_locales maps locale codes to their og:locale values (the resolve
|
|
# answer's seo.og.locale and locale_alternates). Codes not listed use
|
|
# pl_PL, en_US and de_DE for pl, en and de, else the language with its
|
|
# region (pt-BR: pt_BR) or the language doubled (fr: fr_FR):
|
|
# og_locales: {pl: pl_PL, en: en_GB}
|
|
#
|
|
# search_url is the site search address with the {search_term_string}
|
|
# placeholder, for example /szukaj?q={search_term_string}. When set, the
|
|
# WebSite node of the JSON-LD graph carries a SearchAction. Empty means no
|
|
# SearchAction:
|
|
# search_url: "/szukaj?q={search_term_string}"
|
|
#
|
|
# crawl_trusted lets the site audit's crawler fetch plain http addresses
|
|
# and addresses inside the network (a staging or local site). Without it
|
|
# the crawler fetches only https addresses of the site host and its www
|
|
# twin, and refuses private addresses. Only config (or the environment,
|
|
# SUMMER_GOLEM15__SEO__CRAWL_TRUSTED) sets it, never a setting or MCP.
|
|
crawl_trusted: false
|