apunkt/webclaw
1
0
Fork 0
mirror of https://github.com/0xMassi/webclaw.git synced 2026-04-25 00:06:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add fallback sitemap paths for broader discovery

Browse source 
Try /sitemap_index.xml, /wp-sitemap.xml, and /sitemap/sitemap-index.xml
after the standard /sitemap.xml. WordPress 5.5+ and many CMS platforms
use non-standard paths that were previously missed. Paths found via
robots.txt are deduplicated to avoid double-fetching.

Bump to 0.3.11.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Valerio 2026-04-10 18:22:57 +02:00
parent 25b6282d5f
commit a4c351d5ae
4 changed files with 39 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

12
Cargo.lock generated
View file

@ -3102,7 +3102,7 @@ dependencies = [
[[package]]
name = "webclaw-cli"
version = "0.3.9"
version = "0.3.11"
dependencies = [
"clap",
"dotenvy",
@ -3122,7 +3122,7 @@ dependencies = [
[[package]]
name = "webclaw-core"
version = "0.3.9"
version = "0.3.11"
dependencies = [
"ego-tree",
"once_cell",
@ -3140,7 +3140,7 @@ dependencies = [
[[package]]
name = "webclaw-fetch"
version = "0.3.9"
version = "0.3.11"
dependencies = [
"bytes",
"calamine",
@ -3162,7 +3162,7 @@ dependencies = [
[[package]]
name = "webclaw-llm"
version = "0.3.9"
version = "0.3.11"
dependencies = [
"async-trait",
"reqwest",
@ -3175,7 +3175,7 @@ dependencies = [
[[package]]
name = "webclaw-mcp"
version = "0.3.9"
version = "0.3.11"
dependencies = [
"dirs",
"dotenvy",
@ -3196,7 +3196,7 @@ dependencies = [
[[package]]
name = "webclaw-pdf"
version = "0.3.9"
version = "0.3.11"
dependencies = [
"pdf-extract",
"thiserror",