docpull 2.2.0__tar.gz → 2.3.0__tar.gz

docpull-2.3.0/PKG-INFO

@@ -0,0 +1,331 @@
+Metadata-Version: 2.4
+Name: docpull
+Version: 2.3.0
+Summary: Pull documentation from the web and convert to clean markdown
+Author-email: Zachary Roth <support@raintree.technology>
+Maintainer-email: Raintree Technology <support@raintree.technology>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/raintree-technology/docpull
+Project-URL: Documentation, https://github.com/raintree-technology/docpull#readme
+Project-URL: Repository, https://github.com/raintree-technology/docpull
+Project-URL: Source Code, https://github.com/raintree-technology/docpull
+Project-URL: Bug Tracker, https://github.com/raintree-technology/docpull/issues
+Project-URL: Releases, https://github.com/raintree-technology/docpull/releases
+Keywords: python,markdown,documentation,web-scraping,developer-tools,claude,ai-training-data
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Education
+Classifier: Environment :: Console
+Classifier: Topic :: Documentation
+Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
+Classifier: Topic :: Software Development :: Documentation
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Classifier: Topic :: Utilities
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: beautifulsoup4>=4.12.0
+Requires-Dist: html2text>=2020.1.16
+Requires-Dist: defusedxml>=0.7.1
+Requires-Dist: extruct>=0.15.0
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: pydantic>=2.0
+Provides-Extra: proxy
+Requires-Dist: aiohttp-socks>=0.8.0; extra == "proxy"
+Provides-Extra: normalize
+Requires-Dist: url-normalize>=1.4.0; extra == "normalize"
+Provides-Extra: trafilatura
+Requires-Dist: trafilatura>=1.12.0; extra == "trafilatura"
+Provides-Extra: tokens
+Requires-Dist: tiktoken>=0.7.0; extra == "tokens"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0.0; extra == "mcp"
+Provides-Extra: llm
+Requires-Dist: tiktoken>=0.7.0; extra == "llm"
+Provides-Extra: all
+Requires-Dist: aiohttp-socks>=0.8.0; extra == "all"
+Requires-Dist: url-normalize>=1.4.0; extra == "all"
+Requires-Dist: trafilatura>=1.12.0; extra == "all"
+Requires-Dist: tiktoken>=0.7.0; extra == "all"
+Requires-Dist: mcp>=1.0.0; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: bandit>=1.7.0; extra == "dev"
+Requires-Dist: pip-audit>=2.0.0; extra == "dev"
+Requires-Dist: pre-commit>=3.0.0; extra == "dev"
+Requires-Dist: types-requests>=2.31.0; extra == "dev"
+Requires-Dist: types-beautifulsoup4>=4.12.0; extra == "dev"
+Requires-Dist: types-defusedxml>=0.7.0; extra == "dev"
+Requires-Dist: types-pyyaml>=6.0.0; extra == "dev"
+Dynamic: license-file
+
+# docpull
+
+**Security-hardened, browser-free crawler that turns static documentation sites into clean, AI-ready Markdown — fast.**
+
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![PyPI version](https://badge.fury.io/py/docpull.svg)](https://badge.fury.io/py/docpull)
+[![Downloads](https://pepy.tech/badge/docpull)](https://pepy.tech/project/docpull)
+[![License: MIT](https://img.shields.io/github/license/raintree-technology/docpull)](https://github.com/raintree-technology/docpull/blob/main/LICENSE)
+
+<p align="center">
+  <a href="https://docpull.raintree.technology">
+    <img src="https://pub-e85a1abca36f4fd8b4300a6ec2d6f45f.r2.dev/marketing/docpull/1768954147343-iaiziy-docpull-terminal-hero.gif" alt="docpull demo" width="600">
+  </a>
+</p>
+
+docpull uses async HTTP (not Playwright) to fetch server-rendered pages,
+extracts main content, and writes clean Markdown with source-URL frontmatter —
+in seconds, with a small install footprint. It won't render JavaScript, but for
+the large class of docs that don't need it (API references, Python/Go stdlib,
+most dev-tool docs, OpenAPI specs, Next.js and Docusaurus builds), it is a
+fast, auditable, sandbox-friendly way to pipe documentation into an LLM context,
+a RAG index, or an offline archive. SSRF, XXE, DNS-rebinding, and
+CRLF-injection protections are on by default — a necessity when an AI agent
+is choosing the URLs.
+
+## Install
+
+```bash
+pip install docpull
+
+# Optional extras
+pip install 'docpull[llm]'           # tiktoken for token-accurate chunking
+pip install 'docpull[trafilatura]'   # alternative extractor for noisy pages
+pip install 'docpull[mcp]'           # run as an MCP server for AI agents
+pip install 'docpull[all]'           # everything above
+```
+
+## Quick start
+
+```bash
+# Crawl and save Markdown
+docpull https://docs.example.com
+
+# One page, no crawl — the fast path for agents
+docpull https://docs.example.com/guide --single
+
+# LLM-ready NDJSON with 4k-token chunks streamed to stdout
+docpull https://docs.example.com --profile llm --stream | jq .
+
+# Mirror a site for offline use
+docpull https://docs.example.com --profile mirror --cache
+```
+
+## Framework-aware extraction
+
+docpull inspects each page before running the generic extractor and can pull
+content directly from framework data feeds:
+
+| Framework | Strategy |
+|-----------|----------|
+| Next.js   | Parses `__NEXT_DATA__` JSON |
+| Mintlify  | `__NEXT_DATA__` with Mintlify tagging |
+| OpenAPI   | Renders `openapi.json` / `swagger.json` into Markdown |
+| Docusaurus| Detected and tagged; generic extractor produces Markdown |
+| Sphinx    | Detected and tagged; generic extractor produces Markdown |
+
+JS-only SPAs with no server-rendered content are detected and skipped with a
+clear reason (or, with `--strict-js-required`, reported as an error so agents
+can route elsewhere).
+
+## Agent-friendly features
+
+- **`--single`** — fetch a single URL without discovery. Designed for tool loops.
+- **`--stream`** — NDJSON one-record-per-line, flushed on every page, pipeable.
+- **`--max-tokens-per-file N`** — split each page into token-bounded chunks on
+  heading boundaries (exact counts with tiktoken, estimate without).
+- **`--emit-chunks`** — write one file or record per chunk instead of per page.
+- **`--strict-js-required`** — hard-fail on JS-only pages instead of silently
+  skipping.
+- **`--extractor trafilatura`** — swap in [trafilatura](https://trafilatura.readthedocs.io/)
+  for sites where the default heuristics struggle.
+
+## Python API
+
+```python
+from docpull import fetch_one
+
+ctx = fetch_one("https://docs.python.org/3/library/asyncio.html")
+print(ctx.title, ctx.source_type)
+print(ctx.markdown[:500])
+```
+
+Async streaming:
+
+```python
+import asyncio
+from docpull import Fetcher, DocpullConfig, ProfileName, EventType
+
+async def main():
+    cfg = DocpullConfig(
+        url="https://docs.example.com",
+        profile=ProfileName.LLM,  # chunked NDJSON output
+    )
+    async with Fetcher(cfg) as fetcher:
+        async for event in fetcher.run():
+            if event.type == EventType.FETCH_PROGRESS:
+                print(f"{event.current}/{event.total}: {event.url}")
+        print(f"Done: {fetcher.stats.pages_fetched} pages")
+
+asyncio.run(main())
+```
+
+Single-page from an agent tool:
+
+```python
+from docpull import Fetcher, DocpullConfig
+
+async def tool_call(url: str) -> str:
+    async with Fetcher(DocpullConfig(url=url)) as f:
+        ctx = await f.fetch_one(url, save=False)
+        return ctx.markdown or ctx.error or ""
+```
+
+## Profiles
+
+```bash
+docpull https://site.com --profile rag      # Default. Dedup, rich metadata.
+docpull https://site.com --profile llm      # NDJSON + chunks + metadata.
+docpull https://site.com --profile mirror   # Full archive, polite, cached.
+docpull https://site.com --profile quick    # Sampling: 50 pages, depth 2.
+```
+
+## MCP server
+
+docpull ships an MCP (Model Context Protocol) server so AI agents can call it
+directly over stdio:
+
+```bash
+pip install 'docpull[mcp]'
+docpull mcp  # starts the stdio server
+```
+
+Add to Claude Desktop or Claude Code:
+
+```json
+{
+  "mcpServers": {
+    "docpull": {
+      "command": "docpull",
+      "args": ["mcp"]
+    }
+  }
+}
+```
+
+Tools exposed:
+
+- `fetch_url(url, max_tokens?)` — one-shot fetch, no crawl
+- `ensure_docs(source, force?)` — fetch a named library (cached 7 days)
+- `list_sources(category?)` — show available aliases (react, nextjs, fastapi, …)
+- `list_indexed()` — what has been fetched locally
+- `grep_docs(pattern, library?)` — regex search across fetched Markdown
+
+User-defined sources live in `~/.config/docpull-mcp/sources.yaml`:
+
+```yaml
+sources:
+  mydocs:
+    url: https://docs.example.com
+    description: My internal docs
+    category: internal
+    maxPages: 200
+```
+
+## Output
+
+Markdown files with YAML frontmatter:
+
+```markdown
+---
+title: "Getting Started"
+source: https://docs.example.com/guide
+source_type: "nextjs"
+---
+
+# Getting Started
+…
+```
+
+NDJSON (one record per page or chunk):
+
+```json
+{"url": "...", "title": "...", "content": "...", "hash": "...", "token_count": 842, "chunk_index": 0}
+```
+
+## Security
+
+- HTTPS-only, mandatory robots.txt compliance
+- SSRF protection: blocks private/internal network IPs, DNS rebinding
+- XXE protection via `defusedxml` on sitemaps
+- Path traversal and CRLF header injection guards
+- Auth headers stripped on cross-origin redirects
+
+## Options
+
+Run `docpull --help` for the full list. Highlights:
+
+```
+Core:
+  --profile {rag,mirror,quick,llm,custom}
+  --single                Fetch one URL (no crawl)
+  --format {markdown,json,ndjson,sqlite}
+  --stream                Stream NDJSON to stdout
+
+LLM / chunking:
+  --max-tokens-per-file N
+  --tokenizer NAME        tiktoken encoding (default cl100k_base)
+  --emit-chunks           One file/record per chunk
+
+Content extraction:
+  --extractor {default,trafilatura}
+  --no-special-cases      Disable framework extractors
+  --strict-js-required    Error on JS-only pages
+
+Cache:
+  --cache                 Enable incremental updates
+  --cache-dir DIR
+  --cache-ttl DAYS
+```
+
+## Troubleshooting
+
+```bash
+docpull --doctor              # Check installation
+docpull URL --verbose         # Verbose output
+docpull URL --dry-run         # Test without downloading
+docpull URL --preview-urls    # List URLs without fetching
+```
+
+## Links
+
+- [Website](https://docpull.raintree.technology)
+- [PyPI](https://pypi.org/project/docpull/)
+- [GitHub](https://github.com/raintree-technology/docpull)
+- [Changelog](https://github.com/raintree-technology/docpull/blob/main/docs/CHANGELOG.md)
+
+## License
+
+MIT

docpull-2.3.0/README.md

@@ -0,0 +1,249 @@
+# docpull
+
+**Security-hardened, browser-free crawler that turns static documentation sites into clean, AI-ready Markdown — fast.**
+
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![PyPI version](https://badge.fury.io/py/docpull.svg)](https://badge.fury.io/py/docpull)
+[![Downloads](https://pepy.tech/badge/docpull)](https://pepy.tech/project/docpull)
+[![License: MIT](https://img.shields.io/github/license/raintree-technology/docpull)](https://github.com/raintree-technology/docpull/blob/main/LICENSE)
+
+<p align="center">
+  <a href="https://docpull.raintree.technology">
+    <img src="https://pub-e85a1abca36f4fd8b4300a6ec2d6f45f.r2.dev/marketing/docpull/1768954147343-iaiziy-docpull-terminal-hero.gif" alt="docpull demo" width="600">
+  </a>
+</p>
+
+docpull uses async HTTP (not Playwright) to fetch server-rendered pages,
+extracts main content, and writes clean Markdown with source-URL frontmatter —
+in seconds, with a small install footprint. It won't render JavaScript, but for
+the large class of docs that don't need it (API references, Python/Go stdlib,
+most dev-tool docs, OpenAPI specs, Next.js and Docusaurus builds), it is a
+fast, auditable, sandbox-friendly way to pipe documentation into an LLM context,
+a RAG index, or an offline archive. SSRF, XXE, DNS-rebinding, and
+CRLF-injection protections are on by default — a necessity when an AI agent
+is choosing the URLs.
+
+## Install
+
+```bash
+pip install docpull
+
+# Optional extras
+pip install 'docpull[llm]'           # tiktoken for token-accurate chunking
+pip install 'docpull[trafilatura]'   # alternative extractor for noisy pages
+pip install 'docpull[mcp]'           # run as an MCP server for AI agents
+pip install 'docpull[all]'           # everything above
+```
+
+## Quick start
+
+```bash
+# Crawl and save Markdown
+docpull https://docs.example.com
+
+# One page, no crawl — the fast path for agents
+docpull https://docs.example.com/guide --single
+
+# LLM-ready NDJSON with 4k-token chunks streamed to stdout
+docpull https://docs.example.com --profile llm --stream | jq .
+
+# Mirror a site for offline use
+docpull https://docs.example.com --profile mirror --cache
+```
+
+## Framework-aware extraction
+
+docpull inspects each page before running the generic extractor and can pull
+content directly from framework data feeds:
+
+| Framework | Strategy |
+|-----------|----------|
+| Next.js   | Parses `__NEXT_DATA__` JSON |
+| Mintlify  | `__NEXT_DATA__` with Mintlify tagging |
+| OpenAPI   | Renders `openapi.json` / `swagger.json` into Markdown |
+| Docusaurus| Detected and tagged; generic extractor produces Markdown |
+| Sphinx    | Detected and tagged; generic extractor produces Markdown |
+
+JS-only SPAs with no server-rendered content are detected and skipped with a
+clear reason (or, with `--strict-js-required`, reported as an error so agents
+can route elsewhere).
+
+## Agent-friendly features
+
+- **`--single`** — fetch a single URL without discovery. Designed for tool loops.
+- **`--stream`** — NDJSON one-record-per-line, flushed on every page, pipeable.
+- **`--max-tokens-per-file N`** — split each page into token-bounded chunks on
+  heading boundaries (exact counts with tiktoken, estimate without).
+- **`--emit-chunks`** — write one file or record per chunk instead of per page.
+- **`--strict-js-required`** — hard-fail on JS-only pages instead of silently
+  skipping.
+- **`--extractor trafilatura`** — swap in [trafilatura](https://trafilatura.readthedocs.io/)
+  for sites where the default heuristics struggle.
+
+## Python API
+
+```python
+from docpull import fetch_one
+
+ctx = fetch_one("https://docs.python.org/3/library/asyncio.html")
+print(ctx.title, ctx.source_type)
+print(ctx.markdown[:500])
+```
+
+Async streaming:
+
+```python
+import asyncio
+from docpull import Fetcher, DocpullConfig, ProfileName, EventType
+
+async def main():
+    cfg = DocpullConfig(
+        url="https://docs.example.com",
+        profile=ProfileName.LLM,  # chunked NDJSON output
+    )
+    async with Fetcher(cfg) as fetcher:
+        async for event in fetcher.run():
+            if event.type == EventType.FETCH_PROGRESS:
+                print(f"{event.current}/{event.total}: {event.url}")
+        print(f"Done: {fetcher.stats.pages_fetched} pages")
+
+asyncio.run(main())
+```
+
+Single-page from an agent tool:
+
+```python
+from docpull import Fetcher, DocpullConfig
+
+async def tool_call(url: str) -> str:
+    async with Fetcher(DocpullConfig(url=url)) as f:
+        ctx = await f.fetch_one(url, save=False)
+        return ctx.markdown or ctx.error or ""
+```
+
+## Profiles
+
+```bash
+docpull https://site.com --profile rag      # Default. Dedup, rich metadata.
+docpull https://site.com --profile llm      # NDJSON + chunks + metadata.
+docpull https://site.com --profile mirror   # Full archive, polite, cached.
+docpull https://site.com --profile quick    # Sampling: 50 pages, depth 2.
+```
+
+## MCP server
+
+docpull ships an MCP (Model Context Protocol) server so AI agents can call it
+directly over stdio:
+
+```bash
+pip install 'docpull[mcp]'
+docpull mcp  # starts the stdio server
+```
+
+Add to Claude Desktop or Claude Code:
+
+```json
+{
+  "mcpServers": {
+    "docpull": {
+      "command": "docpull",
+      "args": ["mcp"]
+    }
+  }
+}
+```
+
+Tools exposed:
+
+- `fetch_url(url, max_tokens?)` — one-shot fetch, no crawl
+- `ensure_docs(source, force?)` — fetch a named library (cached 7 days)
+- `list_sources(category?)` — show available aliases (react, nextjs, fastapi, …)
+- `list_indexed()` — what has been fetched locally
+- `grep_docs(pattern, library?)` — regex search across fetched Markdown
+
+User-defined sources live in `~/.config/docpull-mcp/sources.yaml`:
+
+```yaml
+sources:
+  mydocs:
+    url: https://docs.example.com
+    description: My internal docs
+    category: internal
+    maxPages: 200
+```
+
+## Output
+
+Markdown files with YAML frontmatter:
+
+```markdown
+---
+title: "Getting Started"
+source: https://docs.example.com/guide
+source_type: "nextjs"
+---
+
+# Getting Started
+…
+```
+
+NDJSON (one record per page or chunk):
+
+```json
+{"url": "...", "title": "...", "content": "...", "hash": "...", "token_count": 842, "chunk_index": 0}
+```
+
+## Security
+
+- HTTPS-only, mandatory robots.txt compliance
+- SSRF protection: blocks private/internal network IPs, DNS rebinding
+- XXE protection via `defusedxml` on sitemaps
+- Path traversal and CRLF header injection guards
+- Auth headers stripped on cross-origin redirects
+
+## Options
+
+Run `docpull --help` for the full list. Highlights:
+
+```
+Core:
+  --profile {rag,mirror,quick,llm,custom}
+  --single                Fetch one URL (no crawl)
+  --format {markdown,json,ndjson,sqlite}
+  --stream                Stream NDJSON to stdout
+
+LLM / chunking:
+  --max-tokens-per-file N
+  --tokenizer NAME        tiktoken encoding (default cl100k_base)
+  --emit-chunks           One file/record per chunk
+
+Content extraction:
+  --extractor {default,trafilatura}
+  --no-special-cases      Disable framework extractors
+  --strict-js-required    Error on JS-only pages
+
+Cache:
+  --cache                 Enable incremental updates
+  --cache-dir DIR
+  --cache-ttl DAYS
+```
+
+## Troubleshooting
+
+```bash
+docpull --doctor              # Check installation
+docpull URL --verbose         # Verbose output
+docpull URL --dry-run         # Test without downloading
+docpull URL --preview-urls    # List URLs without fetching
+```
+
+## Links
+
+- [Website](https://docpull.raintree.technology)
+- [PyPI](https://pypi.org/project/docpull/)
+- [GitHub](https://github.com/raintree-technology/docpull)
+- [Changelog](https://github.com/raintree-technology/docpull/blob/main/docs/CHANGELOG.md)
+
+## License
+
+MIT

{docpull-2.2.0 → docpull-2.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "docpull"
-version = "2.2.0"
+version = "2.3.0"
 dynamic = []
 description = "Pull documentation from the web and convert to clean markdown"
 readme = {file = "README.md", content-type = "text/markdown"}
@@ -51,7 +51,6 @@ classifiers = [
 
     # Programming Language
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
@@ -63,7 +62,6 @@ classifiers = [
     "Typing :: Typed",
 ]
 dependencies = [
-    "requests>=2.31.0",
     "beautifulsoup4>=4.12.0",
     "html2text>=2020.1.16",
     "defusedxml>=0.7.1",
@@ -71,24 +69,34 @@ dependencies = [
     "aiohttp>=3.9.0",
     "rich>=13.0.0",
     "pyyaml>=6.0",
-    "gitpython>=3.1.40",
     "pydantic>=2.0",
 ]
 
 [project.optional-dependencies]
-js = [
-    "playwright>=1.40.0",
-]
 proxy = [
     "aiohttp-socks>=0.8.0",
 ]
 normalize = [
     "url-normalize>=1.4.0",
 ]
+trafilatura = [
+    "trafilatura>=1.12.0",
+]
+tokens = [
+    "tiktoken>=0.7.0",
+]
+mcp = [
+    "mcp>=1.0.0",
+]
+llm = [
+    "tiktoken>=0.7.0",
+]
 all = [
-    "playwright>=1.40.0",
     "aiohttp-socks>=0.8.0",
     "url-normalize>=1.4.0",
+    "trafilatura>=1.12.0",
+    "tiktoken>=0.7.0",
+    "mcp>=1.0.0",
 ]
 dev = [
     "pytest>=7.0.0",
@@ -126,11 +134,11 @@ docpull = ["py.typed"]
 
 [tool.black]
 line-length = 110
-target-version = ["py39", "py310", "py311", "py312", "py313", "py314"]
+target-version = ["py310", "py311", "py312", "py313", "py314"]
 
 [tool.ruff]
 line-length = 110
-target-version = "py39"
+target-version = "py310"
 
 [tool.ruff.lint]
 select = ["E", "F", "W", "I", "N", "UP", "B", "A", "C4", "SIM"]
@@ -154,10 +162,6 @@ init_forbid_extra = true
 init_typed = true
 warn_required_dynamic_aliases = true
 
-[[tool.mypy.overrides]]
-module = "playwright.*"
-ignore_missing_imports = true
-
 [[tool.mypy.overrides]]
 module = "extruct.*"
 ignore_missing_imports = true
@@ -171,11 +175,6 @@ module = "docpull.models.*"
 disallow_any_unimported = false
 warn_return_any = false
 
-[[tool.mypy.overrides]]
-module = "docpull.concurrency.browser_pool"
-disallow_any_unimported = false
-warn_return_any = false
-
 [[tool.mypy.overrides]]
 module = "tests.*"
 disallow_untyped_defs = false