patchtroy 0.4.6__tar.gz → 0.5.0__tar.gz

{patchtroy-0.4.6 → patchtroy-0.5.0}/Dockerfile

@@ -1,62 +1,66 @@
-# ==============================================================================
-# Patchtroy Production Dockerfile
-# Undetected stealth web scraper & markdown extractor microservice for LLMs
-# ==============================================================================
-
-FROM python:3.11-slim
-
-LABEL maintainer="Marcus Zou <marcus.zou@icloud.com>"
-LABEL org.opencontainers.image.title="Patchtroy"
-LABEL org.opencontainers.image.description="Undetected stealth web scraper & markdown extractor microservice"
-LABEL org.opencontainers.image.version="0.4.6"
-
-# Python and environment settings
-ENV PYTHONUNBUFFERED=1 \
-    PYTHONDONTWRITEBYTECODE=1 \
-    PIP_NO_CACHE_DIR=1 \
-    PATCHRIGHT_BROWSERS_PATH=/ms-playwright
-
-# Install minimal OS dependencies for headless Chromium
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    curl \
-    ca-certificates \
-    libnss3 \
-    libnspr4 \
-    libatk1.0-0 \
-    libatk-bridge2.0-0 \
-    libcups2 \
-    libdrm2 \
-    libxkbcommon0 \
-    libxcomposite1 \
-    libxdamage1 \
-    libxfixes3 \
-    libxrandr2 \
-    libgbm1 \
-    libpango-1.0-0 \
-    libcairo2 \
-    libasound2 \
-    && rm -rf /var/lib/apt/lists/*
-
-WORKDIR /app
-
-# Copy dependency definition and source code
-COPY pyproject.toml README.md /app/
-COPY src/ /app/src/
-
-# Install patchtroy with REST microservice extras and download Chromium
-RUN pip install --no-cache-dir ".[server]" \
-    && patchright install chromium
-
-# Create unprivileged user
-RUN useradd -m -u 1000 patchtroy \
-    && chown -R patchtroy:patchtroy /app /ms-playwright
-
-USER patchtroy
-
-EXPOSE 4013
-
-HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
-    CMD curl -f http://localhost:4013/health || exit 1
-
-ENTRYPOINT ["patchtroy"]
-CMD ["--serve", "--host", "0.0.0.0", "--port", "4013"]
+# ==============================================================================
+# Patchtroy Production Dockerfile
+# Undetected stealth web scraper & markdown extractor microservice for LLMs
+# ==============================================================================
+
+FROM python:3.11-slim
+
+LABEL maintainer="Marcus Zou <marcus.zou@icloud.com>"
+LABEL org.opencontainers.image.title="Patchtroy"
+LABEL org.opencontainers.image.description="Undetected stealth web scraper & markdown extractor microservice"
+LABEL org.opencontainers.image.version="0.5.0"
+
+# Python and environment settings
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PLAYWRIGHT_BROWSERS_PATH=/ms-playwright \
+    PATCHRIGHT_BROWSERS_PATH=/ms-playwright
+
+# Install minimal OS dependencies for headless Chromium
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    ca-certificates \
+    libnss3 \
+    libnspr4 \
+    libatk1.0-0 \
+    libatk-bridge2.0-0 \
+    libcups2 \
+    libdrm2 \
+    libxkbcommon0 \
+    libxcomposite1 \
+    libxdamage1 \
+    libxfixes3 \
+    libxrandr2 \
+    libgbm1 \
+    libpango-1.0-0 \
+    libcairo2 \
+    libasound2 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create unprivileged user and ensure browser directories exist
+RUN useradd -m -u 1000 patchtroy \
+    && mkdir -p /ms-playwright /app /home/patchtroy/.cache \
+    && ln -s /ms-playwright /home/patchtroy/.cache/ms-playwright \
+    && chown -R patchtroy:patchtroy /ms-playwright /app /home/patchtroy
+
+WORKDIR /app
+
+# Copy dependency definition and source code
+COPY pyproject.toml README.md /app/
+COPY src/ /app/src/
+
+# Install patchtroy with REST microservice extras and download Chromium
+RUN pip install --no-cache-dir ".[server]" \
+    && patchright install chromium \
+    && chown -R patchtroy:patchtroy /app /ms-playwright
+
+USER patchtroy
+
+EXPOSE 4013
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
+    CMD curl -f http://localhost:4013/health || exit 1
+
+ENTRYPOINT ["patchtroy"]
+CMD ["serve", "--host", "0.0.0.0", "--port", "4013"]

{patchtroy-0.4.6 → patchtroy-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: patchtroy
-Version: 0.4.6
+Version: 0.5.0
 Summary: Undetected stealth web scraper & markdown extractor for LLMs, pairing Patchright with Trafilatura.
 Project-URL: Homepage, https://github.com/marcuz-apl/patchtroy
 Project-URL: Repository, https://github.com/marcuz-apl/patchtroy

{patchtroy-0.4.6 → patchtroy-0.5.0}/PRD.md

@@ -152,7 +152,7 @@ Patchtroy occupies the unoccupied **"Lightweight Stealth Sweet Spot"**:
 - [x] Token counter & LLM chunking utility (`result.chunk(max_tokens=2048)`).
 - [x] Full test suite (32 tests passing).
 
-### Phase 4 (v0.4.6 — Current)
+### Phase 4 (v0.5.0 — Current)
 - [x] PyPI public release workflows & multi-OS matrix CI (`.github/workflows/`).
 - [x] Comprehensive benchmark publication vs Crawl4AI and Firecrawl (`benchmarks/BENCHMARKS.md`).
 - [x] Official documentation portal (Material for MkDocs).

patchtroy-0.5.0/VERSION

@@ -0,0 +1 @@
+v0.5.0-2609031

{patchtroy-0.4.6 → patchtroy-0.5.0}/benchmarks/BENCHMARKS.md

@@ -19,7 +19,7 @@ Existing open-source solutions force developers to choose between:
 
 ## 2. Feature & Architecture Matrix
 
-| Dimension | **Patchtroy** (v0.4.6) | **Crawl4AI** (v0.9.3) | **Firecrawl** (Self-Hosted) |
+| Dimension | **Patchtroy** (v0.5.0) | **Crawl4AI** (v0.9.3) | **Firecrawl** (Self-Hosted) |
 | :--- | :---: | :---: | :---: |
 | **Stealth Engine** | **✅ Native Patchright (C++ CDP masked)** | ❌ Standard Playwright (CDP leaked) | ⚠️ Standard Playwright / Puppeteer |
 | **Dynamic Challenge Resilience** | **✅ Native driver protection** | ❌ Frequently flagged on automated checks | ❌ Blocked unless using paid SaaS proxy |

{patchtroy-0.4.6 → patchtroy-0.5.0}/docs/benchmarks.md

@@ -1,6 +1,6 @@
 # 📊 Benchmarks vs Crawl4AI and Firecrawl
 
-A quantitative, reproducible benchmark comparing **Patchtroy (v0.4.6)** against **Crawl4AI (v0.9.3)** and **Firecrawl (Self-Hosted)**.
+A quantitative, reproducible benchmark comparing **Patchtroy (v0.5.0)** against **Crawl4AI (v0.9.3)** and **Firecrawl (Self-Hosted)**.
 
 ---
 

{patchtroy-0.4.6 → patchtroy-0.5.0}/docs/rest-api.md

@@ -53,7 +53,7 @@ curl http://localhost:4013/health
 ```json
 {
   "status": "healthy",
-  "version": "0.4.6",
+  "version": "0.5.0",
   "engine": "patchright",
   "active": true
 }

{patchtroy-0.4.6 → patchtroy-0.5.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "patchtroy"
-version = "0.4.6"
+version = "0.5.0"
 description = "Undetected stealth web scraper & markdown extractor for LLMs, pairing Patchright with Trafilatura."
 readme = "README.md"
 license = "Apache-2.0"

{patchtroy-0.4.6 → patchtroy-0.5.0}/src/patchtroy/__init__.py

@@ -6,7 +6,7 @@ from patchtroy.models import LinkItem, PatchtroyConfig, ScrapeResult
 from patchtroy.pool import BrowserContextPool
 from patchtroy.proxy import ProxyItem, ProxyManager
 
-__version__ = "0.4.6"
+__version__ = "0.5.0"
 __author__ = "Marcus Zou"
 __license__ = "Apache-2.0"
 __copyright__ = "Copyright 2026 Alfazen Inc."

{patchtroy-0.4.6 → patchtroy-0.5.0}/src/patchtroy/cli.py

@@ -11,7 +11,7 @@ from patchtroy.crawler import Patchtroy
 from patchtroy.models import PatchtroyConfig
 from patchtroy.utils import silence_windows_proactor_bug
 
-__version__ = "0.4.6"
+__version__ = "0.5.0"
 
 
 def main(argv: list[str] | None = None) -> int:

{patchtroy-0.4.6 → patchtroy-0.5.0}/src/patchtroy/server.py

@@ -90,7 +90,7 @@ def create_app() -> FastAPI:
     app = FastAPI(
         title="Patchtroy REST Microservice",
         description="Undetected stealth web scraper & clean Markdown extractor for LLMs.",
-        version="0.4.6",
+        version="0.5.0",
         lifespan=lifespan,
     )
 
@@ -99,7 +99,7 @@ def create_app() -> FastAPI:
         """Microservice health and status check."""
         return {
             "status": "healthy",
-            "version": "0.4.6",
+            "version": "0.5.0",
             "engine": "patchright",
             "active": crawler_instance is not None and crawler_instance._pool.is_running,
         }

{patchtroy-0.4.6 → patchtroy-0.5.0}/tests/test_server.py

@@ -17,7 +17,7 @@ async def test_health_check_endpoint():
         assert resp.status_code == 200
         data = resp.json()
         assert data["status"] == "healthy"
-        assert data["version"] == "0.4.6"
+        assert data["version"] == "0.5.0"
         assert data["engine"] == "patchright"
 
 

{patchtroy-0.4.6 → patchtroy-0.5.0}/uv.lock

@@ -900,7 +900,7 @@ wheels = [
 
 [[package]]
 name = "patchtroy"
-version = "0.4.6"
+version = "0.5.0"
 source = { editable = "." }
 dependencies = [
     { name = "beautifulsoup4" },

patchtroy-0.4.6/VERSION

@@ -1 +0,0 @@
-v0.4.7-260902d