diff --git a/.release-please-manifest.json b/.release-please-manifest.json index 47582228..53ecb865 100644 --- a/.release-please-manifest.json +++ b/.release-please-manifest.json @@ -1,3 +1,3 @@ { - ".": "0.32.0" + ".": "0.33.0" } diff --git a/CHANGELOG.md b/CHANGELOG.md index b905b9cb..a338b00e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,23 @@ All notable changes to CRW are documented here. +## [0.33.0](https://github.com/us/crw/compare/v0.32.0...v0.33.0) (2026-09-02) + + +### Features + +* enhance crawl error diagnostics and configurable headers ([93b4c11](https://github.com/us/crw/commit/93b4c117dd7dd569f1f0b9abce8d3416cf162e75)) + + +### Bug Fixes + +* **crawl:** report unreadable pages and honour per-request headers ([c58a8f6](https://github.com/us/crw/commit/c58a8f6e4d09bff7c5686b1db093f1571fa47988)) +* **deps:** move PDF parsing to lopdf 0.42, clearing RUSTSEC-2026-0187 ([10f4341](https://github.com/us/crw/commit/10f4341eaa9bb957e5b2bcfb7424fdb131e844b1)) +* **extract:** enforce structured output on the chat transports ([aeb55ca](https://github.com/us/crw/commit/aeb55ca844b32197859252679d9a28290aab31d7)) +* **renderer:** don't feed binary bodies to the HTML extractor ([ab5e93e](https://github.com/us/crw/commit/ab5e93e6d116ed1aa5a17c5a4193122fb18b035e)) +* **renderer:** keep the binary-body check off real pages ([4f741d5](https://github.com/us/crw/commit/4f741d57d03170617b30e6dbbc4e83e7af6afbff)) +* **scrape:** classify a wall and an empty result as failures ([96a4b43](https://github.com/us/crw/commit/96a4b4395366cafcd1a6314b7a0af8fb6db82cab)) + ## [0.32.0](https://github.com/us/crw/compare/v0.31.0...v0.32.0) (2026-08-24) diff --git a/Cargo.toml b/Cargo.toml index 5e6ab471..198592e7 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -16,7 +16,7 @@ exclude = ["fuzz"] resolver = "2" [workspace.package] -version = "0.32.0" +version = "0.33.0" edition = "2024" license = "AGPL-3.0" repository = "https://github.com/us/crw" @@ -136,15 +136,15 @@ insta = { version = "1", features = ["json"] } # and layer their own `features` / `optional` on top. `path` is resolved # relative to THIS (root) manifest. Only crates that are depended upon by # another crate appear here; leaf binaries (crw-mcp, crw-cli) just consume. -crw-mcp-proto = { path = "crates/crw-mcp-proto", version = "0.32.0" } -crw-core = { path = "crates/crw-core", version = "0.32.0" } -crw-extract = { path = "crates/crw-extract", version = "0.32.0" } -crw-renderer = { path = "crates/crw-renderer", version = "0.32.0" } -crw-search = { path = "crates/crw-search", version = "0.32.0" } -crw-diff = { path = "crates/crw-diff", version = "0.32.0" } -crw-crawl = { path = "crates/crw-crawl", version = "0.32.0" } -crw-server = { path = "crates/crw-server", version = "0.32.0" } -crw-browse = { path = "crates/crw-browse", version = "0.32.0" } +crw-mcp-proto = { path = "crates/crw-mcp-proto", version = "0.33.0" } +crw-core = { path = "crates/crw-core", version = "0.33.0" } +crw-extract = { path = "crates/crw-extract", version = "0.33.0" } +crw-renderer = { path = "crates/crw-renderer", version = "0.33.0" } +crw-search = { path = "crates/crw-search", version = "0.33.0" } +crw-diff = { path = "crates/crw-diff", version = "0.33.0" } +crw-crawl = { path = "crates/crw-crawl", version = "0.33.0" } +crw-server = { path = "crates/crw-server", version = "0.33.0" } +crw-browse = { path = "crates/crw-browse", version = "0.33.0" } [profile.release] lto = true diff --git a/crates/crw-server/openapi/openapi.json b/crates/crw-server/openapi/openapi.json index b1ca0226..127ba6bb 100644 --- a/crates/crw-server/openapi/openapi.json +++ b/crates/crw-server/openapi/openapi.json @@ -2,7 +2,7 @@ "openapi": "3.1.0", "info": { "title": "CRW REST API", - "version": "0.32.0", + "version": "0.33.0", "description": "Firecrawl-compatible web scraping, crawling, mapping, search, and extraction API. Hosted at https://api.fastcrw.com; self-host with `docker run -p 3000:3000 ghcr.io/us/crw:latest`.", "license": { "name": "AGPL-3.0", diff --git a/docs/openapi.json b/docs/openapi.json index b1ca0226..127ba6bb 100644 --- a/docs/openapi.json +++ b/docs/openapi.json @@ -2,7 +2,7 @@ "openapi": "3.1.0", "info": { "title": "CRW REST API", - "version": "0.32.0", + "version": "0.33.0", "description": "Firecrawl-compatible web scraping, crawling, mapping, search, and extraction API. Hosted at https://api.fastcrw.com; self-host with `docker run -p 3000:3000 ghcr.io/us/crw:latest`.", "license": { "name": "AGPL-3.0", diff --git a/mcp/crw-mcp-darwin-arm64/package.json b/mcp/crw-mcp-darwin-arm64/package.json index 90a5bddc..68345b77 100644 --- a/mcp/crw-mcp-darwin-arm64/package.json +++ b/mcp/crw-mcp-darwin-arm64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-darwin-arm64", - "version": "0.32.0", + "version": "0.33.0", "description": "CRW MCP server binary for darwin arm64", "license": "AGPL-3.0", "author": "fastCRW ", diff --git a/mcp/crw-mcp-darwin-x64/package.json b/mcp/crw-mcp-darwin-x64/package.json index 3f74935b..b97cd0a0 100644 --- a/mcp/crw-mcp-darwin-x64/package.json +++ b/mcp/crw-mcp-darwin-x64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-darwin-x64", - "version": "0.32.0", + "version": "0.33.0", "description": "CRW MCP server binary for darwin x64", "license": "AGPL-3.0", "author": "fastCRW ", diff --git a/mcp/crw-mcp-linux-arm64/package.json b/mcp/crw-mcp-linux-arm64/package.json index b875d37d..eda20dad 100644 --- a/mcp/crw-mcp-linux-arm64/package.json +++ b/mcp/crw-mcp-linux-arm64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-linux-arm64", - "version": "0.32.0", + "version": "0.33.0", "description": "CRW MCP server binary for linux arm64", "license": "AGPL-3.0", "author": "fastCRW ", diff --git a/mcp/crw-mcp-linux-x64/package.json b/mcp/crw-mcp-linux-x64/package.json index 54227b6d..8eb7d0f7 100644 --- a/mcp/crw-mcp-linux-x64/package.json +++ b/mcp/crw-mcp-linux-x64/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp-linux-x64", - "version": "0.32.0", + "version": "0.33.0", "description": "CRW MCP server binary for linux x64", "license": "AGPL-3.0", "author": "fastCRW ", diff --git a/mcp/crw-mcp/package.json b/mcp/crw-mcp/package.json index 465ba054..b4d2e0b2 100644 --- a/mcp/crw-mcp/package.json +++ b/mcp/crw-mcp/package.json @@ -1,6 +1,6 @@ { "name": "crw-mcp", - "version": "0.32.0", + "version": "0.33.0", "description": "MCP server for CRW web scraper — scrape, crawl, map, extract, search, and PDF-parse tools for AI agents", "license": "AGPL-3.0", "author": "fastCRW ", @@ -38,9 +38,9 @@ "skills/SKILL.md" ], "optionalDependencies": { - "crw-mcp-darwin-x64": "0.32.0", - "crw-mcp-darwin-arm64": "0.32.0", - "crw-mcp-linux-x64": "0.32.0", - "crw-mcp-linux-arm64": "0.32.0" + "crw-mcp-darwin-x64": "0.33.0", + "crw-mcp-darwin-arm64": "0.33.0", + "crw-mcp-linux-x64": "0.33.0", + "crw-mcp-linux-arm64": "0.33.0" } } diff --git a/sdks/python/pyproject.toml b/sdks/python/pyproject.toml index 0c847439..15d9727d 100644 --- a/sdks/python/pyproject.toml +++ b/sdks/python/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "hatchling.build" [project] name = "crw" -version = "0.32.0" +version = "0.33.0" description = "Python SDK for CRW web scraper — scrape, crawl, and map any website from Python" readme = "README.md" requires-python = ">=3.10" diff --git a/sdks/typescript/package.json b/sdks/typescript/package.json index fd1485e6..f1a82853 100644 --- a/sdks/typescript/package.json +++ b/sdks/typescript/package.json @@ -1,6 +1,6 @@ { "name": "crw-sdk", - "version": "0.32.0", + "version": "0.33.0", "description": "TypeScript/JavaScript SDK for CRW — scrape, crawl, map, search, parse, and extract any website", "license": "MIT", "author": "fastCRW ", diff --git a/server.json b/server.json index 75cbbd34..9c9e3454 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": "0.32.0", + "version": "0.33.0", "websiteUrl": "https://fastcrw.com", "repository": { "url": "https://github.com/us/crw",