patchtroy 0.4.0__tar.gz → 0.4.4__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {patchtroy-0.4.0 → patchtroy-0.4.4}/Dockerfile +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/PKG-INFO +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/PRD.md +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/benchmarks/BENCHMARKS.md +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/benchmarks.md +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/rest-api.md +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/pyproject.toml +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/__init__.py +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/cli.py +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/server.py +2 -2
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_server.py +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/uv.lock +1 -1
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.dockerignore +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.gitattributes +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.githooks/pre-commit +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.githooks/prepare-commit-msg +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.githooks/versionlib.sh +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.github/workflows/ci.yml +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.github/workflows/docs.yml +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.github/workflows/release.yml +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/.gitignore +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/LICENSE +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/README.md +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/VERSION +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/benchmarks/benchmark_results.json +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/benchmarks/run_benchmark.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docker-compose.yml +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/context-pool.md +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/getting-started.md +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/index.md +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/llm-chunking.md +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/media-capture.md +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/proxy-rotation.md +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/docs/stealth-architecture.md +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/mkdocs.yml +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/chunker.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/crawler.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/extractors.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/models.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/pool.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/proxy.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/src/patchtroy/utils.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_chunker.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_cli.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_crawler.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_extractors.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_media_capture.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_models.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_pool.py +0 -0
- {patchtroy-0.4.0 → patchtroy-0.4.4}/tests/test_proxy.py +0 -0
|
@@ -8,7 +8,7 @@ FROM python:3.11-slim
|
|
|
8
8
|
LABEL maintainer="Marcus Zou <marcus.zou@icloud.com>"
|
|
9
9
|
LABEL org.opencontainers.image.title="Patchtroy"
|
|
10
10
|
LABEL org.opencontainers.image.description="Undetected stealth web scraper & markdown extractor microservice"
|
|
11
|
-
LABEL org.opencontainers.image.version="0.4.
|
|
11
|
+
LABEL org.opencontainers.image.version="0.4.4"
|
|
12
12
|
|
|
13
13
|
# Python and environment settings
|
|
14
14
|
ENV PYTHONUNBUFFERED=1 \
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: patchtroy
|
|
3
|
-
Version: 0.4.
|
|
3
|
+
Version: 0.4.4
|
|
4
4
|
Summary: Undetected stealth web scraper & markdown extractor for LLMs, pairing Patchright with Trafilatura.
|
|
5
5
|
Project-URL: Homepage, https://github.com/marcuz-apl/patchtroy
|
|
6
6
|
Project-URL: Repository, https://github.com/marcuz-apl/patchtroy
|
|
@@ -152,7 +152,7 @@ Patchtroy occupies the unoccupied **"Lightweight Stealth Sweet Spot"**:
|
|
|
152
152
|
- [x] Token counter & LLM chunking utility (`result.chunk(max_tokens=2048)`).
|
|
153
153
|
- [x] Full test suite (32 tests passing).
|
|
154
154
|
|
|
155
|
-
### Phase 4 (v0.4.
|
|
155
|
+
### Phase 4 (v0.4.4 — Current)
|
|
156
156
|
- [x] PyPI public release workflows & multi-OS matrix CI (`.github/workflows/`).
|
|
157
157
|
- [x] Comprehensive benchmark publication vs Crawl4AI and Firecrawl (`benchmarks/BENCHMARKS.md`).
|
|
158
158
|
- [x] Official documentation portal (Material for MkDocs).
|
|
@@ -19,7 +19,7 @@ Existing open-source solutions force developers to choose between:
|
|
|
19
19
|
|
|
20
20
|
## 2. Feature & Architecture Matrix
|
|
21
21
|
|
|
22
|
-
| Dimension | **Patchtroy** (v0.4.
|
|
22
|
+
| Dimension | **Patchtroy** (v0.4.4) | **Crawl4AI** (v0.9.3) | **Firecrawl** (Self-Hosted) |
|
|
23
23
|
| :--- | :---: | :---: | :---: |
|
|
24
24
|
| **Stealth Engine** | **✅ Native Patchright (C++ CDP masked)** | ❌ Standard Playwright (CDP leaked) | ⚠️ Standard Playwright / Puppeteer |
|
|
25
25
|
| **Dynamic Challenge Resilience** | **✅ Native driver protection** | ❌ Frequently flagged on automated checks | ❌ Blocked unless using paid SaaS proxy |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# 📊 Benchmarks vs Crawl4AI and Firecrawl
|
|
2
2
|
|
|
3
|
-
A quantitative, reproducible benchmark comparing **Patchtroy (v0.4.
|
|
3
|
+
A quantitative, reproducible benchmark comparing **Patchtroy (v0.4.4)** against **Crawl4AI (v0.9.3)** and **Firecrawl (Self-Hosted)**.
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "patchtroy"
|
|
7
|
-
version = "0.4.
|
|
7
|
+
version = "0.4.4"
|
|
8
8
|
description = "Undetected stealth web scraper & markdown extractor for LLMs, pairing Patchright with Trafilatura."
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
license = "Apache-2.0"
|
|
@@ -6,7 +6,7 @@ from patchtroy.models import LinkItem, PatchtroyConfig, ScrapeResult
|
|
|
6
6
|
from patchtroy.pool import BrowserContextPool
|
|
7
7
|
from patchtroy.proxy import ProxyItem, ProxyManager
|
|
8
8
|
|
|
9
|
-
__version__ = "0.4.
|
|
9
|
+
__version__ = "0.4.4"
|
|
10
10
|
__author__ = "Marcus Zou"
|
|
11
11
|
__license__ = "Apache-2.0"
|
|
12
12
|
__copyright__ = "Copyright 2026 Alfazen Inc."
|
|
@@ -90,7 +90,7 @@ def create_app() -> FastAPI:
|
|
|
90
90
|
app = FastAPI(
|
|
91
91
|
title="Patchtroy REST Microservice",
|
|
92
92
|
description="Undetected stealth web scraper & clean Markdown extractor for LLMs.",
|
|
93
|
-
version="0.4.
|
|
93
|
+
version="0.4.4",
|
|
94
94
|
lifespan=lifespan,
|
|
95
95
|
)
|
|
96
96
|
|
|
@@ -99,7 +99,7 @@ def create_app() -> FastAPI:
|
|
|
99
99
|
"""Microservice health and status check."""
|
|
100
100
|
return {
|
|
101
101
|
"status": "healthy",
|
|
102
|
-
"version": "0.4.
|
|
102
|
+
"version": "0.4.4",
|
|
103
103
|
"engine": "patchright",
|
|
104
104
|
"active": crawler_instance is not None and crawler_instance._pool.is_running,
|
|
105
105
|
}
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|