patchtroy 0.5.1__tar.gz → 0.5.2__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.
Files changed (51) hide show
  1. {patchtroy-0.5.1 → patchtroy-0.5.2}/Dockerfile +2 -2
  2. {patchtroy-0.5.1 → patchtroy-0.5.2}/PKG-INFO +4 -4
  3. {patchtroy-0.5.1 → patchtroy-0.5.2}/PRD.md +2 -2
  4. {patchtroy-0.5.1 → patchtroy-0.5.2}/README.md +1 -1
  5. patchtroy-0.5.2/VERSION +1 -0
  6. {patchtroy-0.5.1 → patchtroy-0.5.2}/benchmarks/BENCHMARKS.md +1 -1
  7. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/benchmarks.md +1 -1
  8. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/rest-api.md +1 -1
  9. {patchtroy-0.5.1 → patchtroy-0.5.2}/pyproject.toml +3 -3
  10. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/__init__.py +2 -2
  11. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/cli.py +1 -1
  12. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/server.py +2 -2
  13. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_server.py +1 -1
  14. {patchtroy-0.5.1 → patchtroy-0.5.2}/uv.lock +1 -1
  15. patchtroy-0.5.1/VERSION +0 -1
  16. {patchtroy-0.5.1 → patchtroy-0.5.2}/.dockerignore +0 -0
  17. {patchtroy-0.5.1 → patchtroy-0.5.2}/.gitattributes +0 -0
  18. {patchtroy-0.5.1 → patchtroy-0.5.2}/.githooks/pre-commit +0 -0
  19. {patchtroy-0.5.1 → patchtroy-0.5.2}/.githooks/prepare-commit-msg +0 -0
  20. {patchtroy-0.5.1 → patchtroy-0.5.2}/.githooks/versionlib.sh +0 -0
  21. {patchtroy-0.5.1 → patchtroy-0.5.2}/.github/workflows/ci.yml +0 -0
  22. {patchtroy-0.5.1 → patchtroy-0.5.2}/.github/workflows/docs.yml +0 -0
  23. {patchtroy-0.5.1 → patchtroy-0.5.2}/.github/workflows/release.yml +0 -0
  24. {patchtroy-0.5.1 → patchtroy-0.5.2}/.gitignore +0 -0
  25. {patchtroy-0.5.1 → patchtroy-0.5.2}/LICENSE +0 -0
  26. {patchtroy-0.5.1 → patchtroy-0.5.2}/benchmarks/benchmark_results.json +0 -0
  27. {patchtroy-0.5.1 → patchtroy-0.5.2}/benchmarks/run_benchmark.py +0 -0
  28. {patchtroy-0.5.1 → patchtroy-0.5.2}/docker-compose.yml +0 -0
  29. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/context-pool.md +0 -0
  30. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/getting-started.md +0 -0
  31. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/index.md +0 -0
  32. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/llm-chunking.md +0 -0
  33. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/media-capture.md +0 -0
  34. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/proxy-rotation.md +0 -0
  35. {patchtroy-0.5.1 → patchtroy-0.5.2}/docs/stealth-architecture.md +0 -0
  36. {patchtroy-0.5.1 → patchtroy-0.5.2}/mkdocs.yml +0 -0
  37. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/chunker.py +0 -0
  38. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/crawler.py +0 -0
  39. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/extractors.py +0 -0
  40. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/models.py +0 -0
  41. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/pool.py +0 -0
  42. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/proxy.py +0 -0
  43. {patchtroy-0.5.1 → patchtroy-0.5.2}/src/patchtroy/utils.py +0 -0
  44. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_chunker.py +0 -0
  45. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_cli.py +0 -0
  46. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_crawler.py +0 -0
  47. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_extractors.py +0 -0
  48. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_media_capture.py +0 -0
  49. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_models.py +0 -0
  50. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_pool.py +0 -0
  51. {patchtroy-0.5.1 → patchtroy-0.5.2}/tests/test_proxy.py +0 -0
@@ -5,10 +5,10 @@
5
5
 
6
6
  FROM python:3.11-slim
7
7
 
8
- LABEL maintainer="Marcus Zou <marcus.zou@icloud.com>"
8
+ LABEL maintainer="marcuz-apl <support@alfazen.org>"
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="0.5.1"
11
+ LABEL org.opencontainers.image.version="0.5.2"
12
12
 
13
13
  # Python and environment settings
14
14
  ENV PYTHONUNBUFFERED=1 \
@@ -1,12 +1,12 @@
1
1
  Metadata-Version: 2.5
2
2
  Name: patchtroy
3
- Version: 0.5.1
3
+ Version: 0.5.2
4
4
  Summary: 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
7
7
  Project-URL: Issues, https://github.com/marcuz-apl/patchtroy/issues
8
- Author-email: Marcus Zou <marcus.zou@icloud.com>
9
- Maintainer-email: "Alfazen Inc." <support@alfazen.io>
8
+ Author-email: marcuz-apl <support@alfazen.org>
9
+ Maintainer-email: "Alfazen Inc." <support@alfazen.org>
10
10
  License-Expression: Apache-2.0
11
11
  License-File: LICENSE
12
12
  Keywords: crawler,llm,markdown,patchright,playwright,rag,scraper,stealth,trafilatura,web-scraping
@@ -152,4 +152,4 @@ Full documentation, API references, architecture guides, and benchmarks are avai
152
152
 
153
153
  ## 📄 License
154
154
 
155
- Patchtroy is open-source software created by **Marcus Zou** and maintained by **Alfazen Inc.**, released under the **[Apache 2.0 License](LICENSE)**.
155
+ Patchtroy is open-source software created by [@marcuz-apl](https://github.com/marcuz-apl) and maintained by **Alfazen Inc.**, released under the **[Apache 2.0 License](LICENSE)**.
@@ -2,7 +2,7 @@
2
2
 
3
3
  **Document Version**: 1.0.0
4
4
  **Status**: Active / Approved
5
- **Author**: Marcus Zou / Patchtroy Project
5
+ **Author**: marcuz-apl / Patchtroy Project
6
6
  **Target Category**: Developer Tools / AI & LLM Data Engineering
7
7
 
8
8
  ---
@@ -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 (v0.5.1 — Current)
155
+ ### Phase 4 (v0.5.2 — 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).
@@ -107,4 +107,4 @@ Full documentation, API references, architecture guides, and benchmarks are avai
107
107
 
108
108
  ## 📄 License
109
109
 
110
- Patchtroy is open-source software created by **Marcus Zou** and maintained by **Alfazen Inc.**, released under the **[Apache 2.0 License](LICENSE)**.
110
+ Patchtroy is open-source software created by [@marcuz-apl](https://github.com/marcuz-apl) and maintained by **Alfazen Inc.**, released under the **[Apache 2.0 License](LICENSE)**.
@@ -0,0 +1 @@
1
+ v0.5.2-2609033
@@ -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** (v0.5.1) | **Crawl4AI** (v0.9.3) | **Firecrawl** (Self-Hosted) |
22
+ | Dimension | **Patchtroy** (v0.5.2) | **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 (v0.5.1)** against **Crawl4AI (v0.9.3)** and **Firecrawl (Self-Hosted)**.
3
+ A quantitative, reproducible benchmark comparing **Patchtroy (v0.5.2)** against **Crawl4AI (v0.9.3)** and **Firecrawl (Self-Hosted)**.
4
4
 
5
5
  ---
6
6
 
@@ -53,7 +53,7 @@ curl http://localhost:4013/health
53
53
  ```json
54
54
  {
55
55
  "status": "healthy",
56
- "version": "0.5.1",
56
+ "version": "0.5.2",
57
57
  "engine": "patchright",
58
58
  "active": true
59
59
  }
@@ -4,16 +4,16 @@ build-backend = "hatchling.build"
4
4
 
5
5
  [project]
6
6
  name = "patchtroy"
7
- version = "0.5.1"
7
+ version = "0.5.2"
8
8
  description = "Stealth web scraper & markdown extractor for LLMs, pairing Patchright with Trafilatura."
9
9
  readme = "README.md"
10
10
  license = "Apache-2.0"
11
11
  requires-python = ">=3.10"
12
12
  authors = [
13
- { name = "Marcus Zou", email = "marcus.zou@icloud.com" }
13
+ { name = "marcuz-apl", email = "support@alfazen.org" }
14
14
  ]
15
15
  maintainers = [
16
- { name = "Alfazen Inc.", email = "support@alfazen.io" }
16
+ { name = "Alfazen Inc.", email = "support@alfazen.org" }
17
17
  ]
18
18
  keywords = [
19
19
  "crawler",
@@ -6,8 +6,8 @@ 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__ = "0.5.1"
10
- __author__ = "Marcus Zou"
9
+ __version__ = "0.5.2"
10
+ __author__ = "marcuz-apl"
11
11
  __license__ = "Apache-2.0"
12
12
  __copyright__ = "Copyright 2026 Alfazen Inc."
13
13
 
@@ -11,7 +11,7 @@ from patchtroy.crawler import Patchtroy
11
11
  from patchtroy.models import PatchtroyConfig
12
12
  from patchtroy.utils import silence_windows_proactor_bug
13
13
 
14
- __version__ = "0.5.1"
14
+ __version__ = "0.5.2"
15
15
 
16
16
 
17
17
  def main(argv: list[str] | None = None) -> int:
@@ -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="0.5.1",
93
+ version="0.5.2",
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": "0.5.1",
102
+ "version": "0.5.2",
103
103
  "engine": "patchright",
104
104
  "active": crawler_instance is not None and crawler_instance._pool.is_running,
105
105
  }
@@ -17,7 +17,7 @@ async def test_health_check_endpoint():
17
17
  assert resp.status_code == 200
18
18
  data = resp.json()
19
19
  assert data["status"] == "healthy"
20
- assert data["version"] == "0.5.1"
20
+ assert data["version"] == "0.5.2"
21
21
  assert data["engine"] == "patchright"
22
22
 
23
23
 
@@ -900,7 +900,7 @@ wheels = [
900
900
 
901
901
  [[package]]
902
902
  name = "patchtroy"
903
- version = "0.5.1"
903
+ version = "0.5.2"
904
904
  source = { editable = "." }
905
905
  dependencies = [
906
906
  { name = "beautifulsoup4" },
patchtroy-0.5.1/VERSION DELETED
@@ -1 +0,0 @@
1
- v0.5.1-2609032
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