apunkt/webclaw
1
0
Fork 0
mirror of https://github.com/0xMassi/webclaw.git synced 2026-05-12 16:32:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix: v0.1.7 — extraction options now work in batch mode (#3)

Browse source 
--only-main-content, --include, and --exclude were ignored in batch
mode because run_batch used default ExtractionOptions. Added
fetch_and_extract_batch_with_options to pass CLI options through.

Closes #3

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Valerio 2026-03-26 13:30:20 +01:00
parent 1b8dfb77a6
commit 0e4128782a
5 changed files with 38 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

5
crates/webclaw-cli/src/main.rs
View file

@ -1248,7 +1248,10 @@ async fn run_batch(cli: &Cli, entries: &[(String, Option<String>)]) -> Result<()
);
let urls: Vec<&str> = entries.iter().map(|(u, _)| u.as_str()).collect();
let results = client.fetch_and_extract_batch(&urls, cli.concurrency).await;
let options = build_extraction_options(cli);
let results = client
.fetch_and_extract_batch_with_options(&urls, cli.concurrency, &options)
.await;
let ok = results.iter().filter(|r| r.result.is_ok()).count();
let errors = results.len() - ok;