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

--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>

CHANGELOG.md

@@ -3,6 +3,13 @@
 All notable changes to webclaw are documented here.
 Format follows [Keep a Changelog](https://keepachangelog.com/).
 
+## [0.1.7] — 2026-03-26
+
+### Fixed
+- `--only-main-content`, `--include`, and `--exclude` now work in batch mode (#3)
+
+---
+
 ## [0.1.6] — 2026-03-26
 
 ### Added

Cargo.lock

@@ -2881,7 +2881,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-cli"
-version = "0.1.6"
+version = "0.1.7"
 dependencies = [
  "clap",
  "dotenvy",
@@ -2901,7 +2901,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-core"
-version = "0.1.6"
+version = "0.1.7"
 dependencies = [
  "ego-tree",
  "once_cell",
@@ -2919,7 +2919,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-fetch"
-version = "0.1.6"
+version = "0.1.7"
 dependencies = [
  "primp",
  "quick-xml",
@@ -2937,7 +2937,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-llm"
-version = "0.1.6"
+version = "0.1.7"
 dependencies = [
  "async-trait",
  "reqwest",
@@ -2950,7 +2950,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-mcp"
-version = "0.1.6"
+version = "0.1.7"
 dependencies = [
  "dotenvy",
  "reqwest",
@@ -2970,7 +2970,7 @@ dependencies = [
 
 [[package]]
 name = "webclaw-pdf"
-version = "0.1.6"
+version = "0.1.7"
 dependencies = [
  "pdf-extract",
  "thiserror",

Cargo.toml

@@ -3,7 +3,7 @@ resolver = "2"
 members = ["crates/*"]
 
 [workspace.package]
-version = "0.1.6"
+version = "0.1.7"
 edition = "2024"
 license = "MIT"
 repository = "https://github.com/0xMassi/webclaw"

crates/webclaw-cli/src/main.rs

@@ -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;

crates/webclaw-fetch/src/client.rs

@@ -465,6 +465,24 @@ impl FetchClient {
         self: &Arc<Self>,
         urls: &[&str],
         concurrency: usize,
+    ) -> Vec<BatchExtractResult> {
+        self.fetch_and_extract_batch_with_options(
+            urls,
+            concurrency,
+            &webclaw_core::ExtractionOptions::default(),
+        )
+        .await
+    }
+
+    /// Fetch and extract multiple URLs concurrently with custom extraction options.
+    ///
+    /// Same as [`fetch_and_extract_batch`] but applies the given options
+    /// (include/exclude selectors, only-main-content, etc.) to each extraction.
+    pub async fn fetch_and_extract_batch_with_options(
+        self: &Arc<Self>,
+        urls: &[&str],
+        concurrency: usize,
+        options: &webclaw_core::ExtractionOptions,
     ) -> Vec<BatchExtractResult> {
         let semaphore = Arc::new(Semaphore::new(concurrency));
         let mut handles = Vec::with_capacity(urls.len());
@@ -473,10 +491,11 @@ impl FetchClient {
             let permit = Arc::clone(&semaphore);
             let client = Arc::clone(self);
             let url = url.to_string();
+            let opts = options.clone();
 
             handles.push(tokio::spawn(async move {
                 let _permit = permit.acquire().await.expect("semaphore closed");
-                let result = client.fetch_and_extract(&url).await;
+                let result = client.fetch_and_extract_with_options(&url, &opts).await;
                 (idx, BatchExtractResult { url, result })
             }));
         }