diff --git a/.release-please-manifest.json b/.release-please-manifest.json index 5d02000..bf5f1fb 100644 --- a/.release-please-manifest.json +++ b/.release-please-manifest.json @@ -1,3 +1,3 @@ { - ".": "0.6.1" + ".": "0.6.2" } diff --git a/CHANGELOG.md b/CHANGELOG.md index 8120afd..3e59239 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,25 @@ All notable changes to CRW are documented here. +## [0.6.2](https://github.com/us/crw/compare/v0.6.1...v0.6.2) (2026-05-10) + + +### Features + +* **search:** add /v1/search endpoint backed by bundled SearXNG sidecar ([f4bd7f4](https://github.com/us/crw/commit/f4bd7f46db9f286e3c49be95a968951802a90710)) + + +### Bug Fixes + +* **antibot:** drop bare 'captcha'/'access denied' markers — false positives ([fae6c09](https://github.com/us/crw/commit/fae6c09537cf286bfb08cb9ebefab0c723c4160f)) +* **crawl:** drop redundant `.into_iter()` for clippy 1.95 ([#39](https://github.com/us/crw/issues/39)) ([fb4032b](https://github.com/us/crw/commit/fb4032b86a5c0095e7e69b198ac2017aa7003000)) +* **map:** WordPress sitemap-index timeout (closes [#33](https://github.com/us/crw/issues/33)) ([c3dfd6c](https://github.com/us/crw/commit/c3dfd6c66ff6bdbbaf3d2ce1646dbb9d7ac6dd5a)) +* **release:** register crw-search crate in release manifest ([9074761](https://github.com/us/crw/commit/907476163c69c5fd8e421e5063686a750c10ce24)) +* **search:** codex iteration-1 hardening — error mapping, resource bounds, container ([5acba7b](https://github.com/us/crw/commit/5acba7bbf1be2cc147e5c25ad9fca80e9bce757d)) +* **search:** codex iteration-2 — error-body cap, per-source row budget, doc ([a440d6e](https://github.com/us/crw/commit/a440d6e4ae3b6ac0dc8decdead3efe04ad33bc43)) +* **search:** codex iteration-3 — predicate-based well-formed filter ([4b4df3a](https://github.com/us/crw/commit/4b4df3a521cba31cd2a82f2d3595d726cb4b2c16)) +* **search:** use real SearXNG image tag and add fallback secret_key ([be1f403](https://github.com/us/crw/commit/be1f403648d352bc68037b0c5ba208729b96d1fa)) + ## [0.6.1](https://github.com/us/crw/compare/v0.6.0...v0.6.1) (2026-05-09) diff --git a/Cargo.toml b/Cargo.toml index 3029465..137551a 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -14,7 +14,7 @@ members = [ resolver = "2" [workspace.package] -version = "0.6.1" +version = "0.6.2" edition = "2024" license = "AGPL-3.0" repository = "https://github.com/us/crw" diff --git a/crates/crw-browse/Cargo.toml b/crates/crw-browse/Cargo.toml index 2d5d1e1..9da9cb9 100644 --- a/crates/crw-browse/Cargo.toml +++ b/crates/crw-browse/Cargo.toml @@ -11,8 +11,8 @@ description = "MCP server for interactive browser automation over CDP" publish = false [dependencies] -crw-core = { path = "../crw-core", version = "0.6.1" } -crw-renderer = { path = "../crw-renderer", version = "0.6.1", features = ["cdp"] } +crw-core = { path = "../crw-core", version = "0.6.2" } +crw-renderer = { path = "../crw-renderer", version = "0.6.2", features = ["cdp"] } rmcp = { version = "1.5", features = ["server", "macros", "transport-io"] } clap = { workspace = true } diff --git a/crates/crw-cli/Cargo.toml b/crates/crw-cli/Cargo.toml index 7d4c460..1f0001c 100644 --- a/crates/crw-cli/Cargo.toml +++ b/crates/crw-cli/Cargo.toml @@ -14,10 +14,10 @@ name = "crw" path = "src/main.rs" [dependencies] -crw-core = { path = "../crw-core", version = "0.6.1" } -crw-renderer = { path = "../crw-renderer", version = "0.6.1", features = ["auto-browser", "cdp"] } -crw-extract = { path = "../crw-extract", version = "0.6.1" } -crw-crawl = { path = "../crw-crawl", version = "0.6.1" } +crw-core = { path = "../crw-core", version = "0.6.2" } +crw-renderer = { path = "../crw-renderer", version = "0.6.2", features = ["auto-browser", "cdp"] } +crw-extract = { path = "../crw-extract", version = "0.6.2" } +crw-crawl = { path = "../crw-crawl", version = "0.6.2" } tokio = { workspace = true } clap = { workspace = true } diff --git a/crates/crw-core/Cargo.toml b/crates/crw-core/Cargo.toml index 2beeb69..c913059 100644 --- a/crates/crw-core/Cargo.toml +++ b/crates/crw-core/Cargo.toml @@ -19,7 +19,7 @@ description = "Core types, config, and error handling for the CRW web scraper" cdp = [] [dependencies] -crw-mcp-proto = { path = "../crw-mcp-proto", version = "0.6.1" } +crw-mcp-proto = { path = "../crw-mcp-proto", version = "0.6.2" } serde = { workspace = true } serde_json = { workspace = true } toml = { workspace = true } diff --git a/crates/crw-crawl/Cargo.toml b/crates/crw-crawl/Cargo.toml index 91d88f5..2d7efd6 100644 --- a/crates/crw-crawl/Cargo.toml +++ b/crates/crw-crawl/Cargo.toml @@ -10,9 +10,9 @@ categories.workspace = true description = "Async BFS web crawler with rate limiting and robots.txt support for CRW" [dependencies] -crw-core = { path = "../crw-core", version = "0.6.1" } -crw-renderer = { path = "../crw-renderer", version = "0.6.1" } -crw-extract = { path = "../crw-extract", version = "0.6.1" } +crw-core = { path = "../crw-core", version = "0.6.2" } +crw-renderer = { path = "../crw-renderer", version = "0.6.2" } +crw-extract = { path = "../crw-extract", version = "0.6.2" } reqwest = { workspace = true } scraper = { workspace = true } tokio = { workspace = true } diff --git a/crates/crw-extract/Cargo.toml b/crates/crw-extract/Cargo.toml index 8e50cb6..c4a1b85 100644 --- a/crates/crw-extract/Cargo.toml +++ b/crates/crw-extract/Cargo.toml @@ -10,7 +10,7 @@ categories.workspace = true description = "HTML extraction and markdown conversion engine for the CRW web scraper" [dependencies] -crw-core = { path = "../crw-core", version = "0.6.1" } +crw-core = { path = "../crw-core", version = "0.6.2" } lol_html = { workspace = true } scraper = { workspace = true } htmd = { workspace = true } diff --git a/crates/crw-mcp/Cargo.toml b/crates/crw-mcp/Cargo.toml index ea20704..6227a22 100644 --- a/crates/crw-mcp/Cargo.toml +++ b/crates/crw-mcp/Cargo.toml @@ -18,8 +18,8 @@ default = ["embedded"] embedded = ["dep:crw-server"] [dependencies] -crw-core = { path = "../crw-core", version = "0.6.1" } -crw-renderer = { path = "../crw-renderer", version = "0.6.1", features = ["auto-browser"] } +crw-core = { path = "../crw-core", version = "0.6.2" } +crw-renderer = { path = "../crw-renderer", version = "0.6.2", features = ["auto-browser"] } serde_json = { workspace = true } tokio = { workspace = true } reqwest = { workspace = true } @@ -28,4 +28,4 @@ tracing-subscriber = { workspace = true } clap = { workspace = true } # Embedded mode: pulls in full scraping engine -crw-server = { path = "../crw-server", version = "0.6.1", optional = true, features = ["cdp"] } +crw-server = { path = "../crw-server", version = "0.6.2", optional = true, features = ["cdp"] } diff --git a/crates/crw-renderer/Cargo.toml b/crates/crw-renderer/Cargo.toml index fb3afd5..5bc3b70 100644 --- a/crates/crw-renderer/Cargo.toml +++ b/crates/crw-renderer/Cargo.toml @@ -15,7 +15,7 @@ cdp = ["tokio-tungstenite", "crw-core/cdp"] auto-browser = ["dep:dirs"] [dependencies] -crw-core = { path = "../crw-core", version = "0.6.1" } +crw-core = { path = "../crw-core", version = "0.6.2" } reqwest = { workspace = true } tokio = { workspace = true } tokio-tungstenite = { version = "0.28", features = ["rustls-tls-native-roots"], optional = true } diff --git a/crates/crw-server/Cargo.toml b/crates/crw-server/Cargo.toml index b8f866a..65f7471 100644 --- a/crates/crw-server/Cargo.toml +++ b/crates/crw-server/Cargo.toml @@ -15,10 +15,10 @@ cdp = ["crw-renderer/cdp"] test-utils = [] [dependencies] -crw-core = { path = "../crw-core", version = "0.6.1" } -crw-renderer = { path = "../crw-renderer", version = "0.6.1" } -crw-extract = { path = "../crw-extract", version = "0.6.1" } -crw-crawl = { path = "../crw-crawl", version = "0.6.1" } +crw-core = { path = "../crw-core", version = "0.6.2" } +crw-renderer = { path = "../crw-renderer", version = "0.6.2" } +crw-extract = { path = "../crw-extract", version = "0.6.2" } +crw-crawl = { path = "../crw-crawl", version = "0.6.2" } crw-search = { path = "../crw-search", version = "0.6.1" } axum = { workspace = true } tower = { workspace = true } diff --git a/npm/crw-mcp-darwin-arm64/package.json b/npm/crw-mcp-darwin-arm64/package.json index bcf99e6..cfdd1a6 100644 --- a/npm/crw-mcp-darwin-arm64/package.json +++ b/npm/crw-mcp-darwin-arm64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-darwin-arm64", - "version": "0.6.1", + "version": "0.6.2", "description": "CRW MCP server binary for darwin arm64", "license": "AGPL-3.0", "homepage": "https://github.com/us/crw", diff --git a/npm/crw-mcp-darwin-x64/package.json b/npm/crw-mcp-darwin-x64/package.json index b9733bb..0628f30 100644 --- a/npm/crw-mcp-darwin-x64/package.json +++ b/npm/crw-mcp-darwin-x64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-darwin-x64", - "version": "0.6.1", + "version": "0.6.2", "description": "CRW MCP server binary for darwin x64", "license": "AGPL-3.0", "homepage": "https://github.com/us/crw", diff --git a/npm/crw-mcp-linux-arm64/package.json b/npm/crw-mcp-linux-arm64/package.json index 5a1cb20..866661d 100644 --- a/npm/crw-mcp-linux-arm64/package.json +++ b/npm/crw-mcp-linux-arm64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-linux-arm64", - "version": "0.6.1", + "version": "0.6.2", "description": "CRW MCP server binary for linux arm64", "license": "AGPL-3.0", "homepage": "https://github.com/us/crw", diff --git a/npm/crw-mcp-linux-x64/package.json b/npm/crw-mcp-linux-x64/package.json index 3a97f16..95c93f0 100644 --- a/npm/crw-mcp-linux-x64/package.json +++ b/npm/crw-mcp-linux-x64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-linux-x64", - "version": "0.6.1", + "version": "0.6.2", "description": "CRW MCP server binary for linux x64", "license": "AGPL-3.0", "homepage": "https://github.com/us/crw", diff --git a/npm/crw-mcp-win32-arm64/package.json b/npm/crw-mcp-win32-arm64/package.json index 8e4b9e2..321278e 100644 --- a/npm/crw-mcp-win32-arm64/package.json +++ b/npm/crw-mcp-win32-arm64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-win32-arm64", - "version": "0.6.1", + "version": "0.6.2", "description": "CRW MCP server binary for win32 arm64", "license": "AGPL-3.0", "homepage": "https://github.com/us/crw", diff --git a/npm/crw-mcp-win32-x64/package.json b/npm/crw-mcp-win32-x64/package.json index a080a78..3f6774a 100644 --- a/npm/crw-mcp-win32-x64/package.json +++ b/npm/crw-mcp-win32-x64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-win32-x64", - "version": "0.6.1", + "version": "0.6.2", "description": "CRW MCP server binary for win32 x64", "license": "AGPL-3.0", "homepage": "https://github.com/us/crw", diff --git a/npm/crw-mcp/package.json b/npm/crw-mcp/package.json index d9e580f..c5c7597 100644 --- a/npm/crw-mcp/package.json +++ b/npm/crw-mcp/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp", - "version": "0.6.1", + "version": "0.6.2", "description": "MCP server for CRW web scraper — scrape, crawl, and map tools for AI agents", "license": "AGPL-3.0", "homepage": "https://github.com/us/crw", @@ -27,11 +27,11 @@ "skills/SKILL.md" ], "optionalDependencies": { - "crw-mcp-darwin-x64": "0.6.1", - "crw-mcp-darwin-arm64": "0.6.1", - "crw-mcp-linux-x64": "0.6.1", - "crw-mcp-linux-arm64": "0.6.1", - "crw-mcp-win32-x64": "0.6.1", - "crw-mcp-win32-arm64": "0.6.1" + "crw-mcp-darwin-x64": "0.6.2", + "crw-mcp-darwin-arm64": "0.6.2", + "crw-mcp-linux-x64": "0.6.2", + "crw-mcp-linux-arm64": "0.6.2", + "crw-mcp-win32-x64": "0.6.2", + "crw-mcp-win32-arm64": "0.6.2" } } diff --git a/python/pyproject.toml b/python/pyproject.toml index 08c8ef6..2f5fbba 100644 --- a/python/pyproject.toml +++ b/python/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "hatchling.build" [project] name = "crw" -version = "0.6.1" +version = "0.6.2" description = "Python SDK for CRW web scraper — scrape, crawl, and map any website from Python" readme = "README.md" requires-python = ">=3.9" diff --git a/server.json b/server.json index 0d1c323..cbc483c 100644 --- a/server.json +++ b/server.json @@ -3,7 +3,7 @@ "name": "io.github.us/crw", "title": "CRW Web Scraper", "description": "Open-source web scraper for AI agents with scrape, crawl, and map tools", - "version": "0.6.1", + "version": "0.6.2", "websiteUrl": "https://us.github.io/crw", "repository": { "url": "https://github.com/us/crw", diff --git a/version.txt b/version.txt index ee6cdce..b616048 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -0.6.1 +0.6.2