rawfy 0.1.0__tar.gz

rawfy-0.1.0/PKG-INFO

@@ -0,0 +1,98 @@
+Metadata-Version: 2.4
+Name: rawfy
+Version: 0.1.0
+Summary: Python wrapper for the Rawfy AI agent skill — converts any URL into structured, agent-readable content
+Author: rishiiicreates
+License: MIT
+Project-URL: Homepage, https://github.com/rishiiicreates/rawfy
+Project-URL: Repository, https://github.com/rishiiicreates/rawfy
+Project-URL: Issues, https://github.com/rishiiicreates/rawfy/issues
+Keywords: ai,agent,mcp,web,scraper,markdown,rawfy
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+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: Topic :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+
+# Rawfy Python Wrapper
+
+Python bindings for the [Rawfy](https://github.com/rishiiicreates/rawfy) AI agent skill.
+
+## Prerequisites
+
+- **Node.js >= 18** — Rawfy is a Node.js tool
+- **Rawfy CLI** — `npm install -g rawfy`
+
+## Install
+
+```bash
+pip install rawfy
+```
+
+## Quick Start
+
+```python
+from rawfy import fetch, metadata
+
+# Full page fetch (returns WSM markdown)
+content = fetch("https://example.com")
+
+# Get structured JSON data
+import json
+data = fetch("https://example.com", format="json")
+parsed = json.loads(data)
+
+# Or use the convenience wrapper
+from rawfy import fetch_json
+data = fetch_json("https://example.com")
+print(data["metadata"]["title"])
+
+# Lightweight metadata only
+meta = metadata("https://docs.python.org")
+print(f"Title: {meta['title']}, Words: {meta['word_count']}")
+```
+
+## API
+
+### `fetch(url, *, format="markdown", vision=False, no_playwright=False, max_tokens=50000, timeout=30)`
+
+Fetch and process a URL. Returns the content as a string.
+
+### `fetch_json(url, **kwargs)`
+
+Same as `fetch()` with `format="json"`, returns a parsed dict.
+
+### `metadata(url, *, no_playwright=False, timeout=15)`
+
+Fetch only page metadata (lightweight). Returns a dict.
+
+### `check_installation()`
+
+Check if Rawfy and dependencies are installed. Returns a status dict.
+
+## Error Handling
+
+```python
+from rawfy import fetch, RawfyError
+
+try:
+    content = fetch("https://example.com")
+except RawfyError as e:
+    print(f"Error [{e.code}]: {e}")
+    print(f"URL: {e.url}")
+```
+
+## CLI
+
+```bash
+python -m rawfy https://example.com
+python -m rawfy https://example.com --format json
+```

rawfy-0.1.0/README.md

@@ -0,0 +1,74 @@
+# Rawfy Python Wrapper
+
+Python bindings for the [Rawfy](https://github.com/rishiiicreates/rawfy) AI agent skill.
+
+## Prerequisites
+
+- **Node.js >= 18** — Rawfy is a Node.js tool
+- **Rawfy CLI** — `npm install -g rawfy`
+
+## Install
+
+```bash
+pip install rawfy
+```
+
+## Quick Start
+
+```python
+from rawfy import fetch, metadata
+
+# Full page fetch (returns WSM markdown)
+content = fetch("https://example.com")
+
+# Get structured JSON data
+import json
+data = fetch("https://example.com", format="json")
+parsed = json.loads(data)
+
+# Or use the convenience wrapper
+from rawfy import fetch_json
+data = fetch_json("https://example.com")
+print(data["metadata"]["title"])
+
+# Lightweight metadata only
+meta = metadata("https://docs.python.org")
+print(f"Title: {meta['title']}, Words: {meta['word_count']}")
+```
+
+## API
+
+### `fetch(url, *, format="markdown", vision=False, no_playwright=False, max_tokens=50000, timeout=30)`
+
+Fetch and process a URL. Returns the content as a string.
+
+### `fetch_json(url, **kwargs)`
+
+Same as `fetch()` with `format="json"`, returns a parsed dict.
+
+### `metadata(url, *, no_playwright=False, timeout=15)`
+
+Fetch only page metadata (lightweight). Returns a dict.
+
+### `check_installation()`
+
+Check if Rawfy and dependencies are installed. Returns a status dict.
+
+## Error Handling
+
+```python
+from rawfy import fetch, RawfyError
+
+try:
+    content = fetch("https://example.com")
+except RawfyError as e:
+    print(f"Error [{e.code}]: {e}")
+    print(f"URL: {e.url}")
+```
+
+## CLI
+
+```bash
+python -m rawfy https://example.com
+python -m rawfy https://example.com --format json
+```

rawfy-0.1.0/pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools>=68.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "rawfy"
+version = "0.1.0"
+description = "Python wrapper for the Rawfy AI agent skill — converts any URL into structured, agent-readable content"
+readme = "README.md"
+license = {text = "MIT"}
+authors = [{name = "rishiiicreates"}]
+requires-python = ">=3.10"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Internet :: WWW/HTTP",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Text Processing :: Markup :: Markdown",
+]
+keywords = ["ai", "agent", "mcp", "web", "scraper", "markdown", "rawfy"]
+
+[project.urls]
+Homepage = "https://github.com/rishiiicreates/rawfy"
+Repository = "https://github.com/rishiiicreates/rawfy"
+Issues = "https://github.com/rishiiicreates/rawfy/issues"
+
+[project.scripts]
+rawfy-py = "rawfy.client:main"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["rawfy*"]

rawfy-0.1.0/rawfy/__init__.py

@@ -0,0 +1,26 @@
+"""
+Rawfy — Python wrapper for the Rawfy AI agent skill.
+
+Provides a Pythonic interface to the Rawfy CLI for fetching and
+processing web pages into agent-readable content.
+
+Usage:
+    from rawfy import fetch, metadata
+
+    # Full page fetch
+    result = fetch("https://example.com")
+    print(result)
+
+    # JSON format for structured data
+    data = fetch("https://example.com", format="json")
+    import json
+    parsed = json.loads(data)
+
+    # Metadata only (lightweight)
+    meta = metadata("https://example.com")
+"""
+
+from rawfy.client import fetch, metadata, RawfyError
+
+__version__ = "0.1.0"
+__all__ = ["fetch", "metadata", "RawfyError", "__version__"]

rawfy-0.1.0/rawfy/__main__.py

@@ -0,0 +1,5 @@
+"""Allow running as `python -m rawfy`."""
+from rawfy.client import main
+
+if __name__ == "__main__":
+    main()

rawfy-0.1.0/rawfy/client.py

@@ -0,0 +1,291 @@
+"""
+Rawfy Python client — subprocess wrapper around the Rawfy CLI.
+
+This module shells out to the `rawfy` Node.js CLI and parses
+the output. It requires Node.js >= 18 and `rawfy` to be installed
+globally or available via npx.
+"""
+
+from __future__ import annotations
+
+import json
+import shutil
+import subprocess
+import sys
+from typing import Any, Literal
+
+
+class RawfyError(Exception):
+    """Raised when the Rawfy CLI returns an error."""
+
+    def __init__(self, message: str, code: str | None = None, url: str | None = None):
+        self.code = code
+        self.url = url
+        super().__init__(message)
+
+    def __repr__(self) -> str:
+        parts = [f"RawfyError({self.args[0]!r}"]
+        if self.code:
+            parts.append(f", code={self.code!r}")
+        if self.url:
+            parts.append(f", url={self.url!r}")
+        parts.append(")")
+        return "".join(parts)
+
+
+OutputFormat = Literal["markdown", "json", "text"]
+
+
+def _find_rawfy_cli() -> list[str]:
+    """
+    Locate the rawfy CLI executable.
+
+    Search order:
+    1. `rawfy` in PATH (global npm install)
+    2. `npx rawfy` (local install / npx resolution)
+    3. `node node_modules/.bin/rawfy` (project-local)
+
+    Returns the command prefix as a list of strings.
+    """
+    # 1. Check if rawfy is directly in PATH
+    if shutil.which("rawfy"):
+        return ["rawfy"]
+
+    # 2. Check if npx is available
+    if shutil.which("npx"):
+        return ["npx", "-y", "rawfy"]
+
+    # 3. Check if node is available for direct execution
+    if shutil.which("node"):
+        return ["node", "node_modules/.bin/rawfy"]
+
+    raise RawfyError(
+        "Could not find rawfy CLI. Install it with: npm install -g rawfy",
+        code="CLI_NOT_FOUND",
+    )
+
+
+def fetch(
+    url: str,
+    *,
+    format: OutputFormat = "markdown",
+    vision: bool = False,
+    no_playwright: bool = False,
+    max_tokens: int = 50_000,
+    timeout: int = 30,
+) -> str:
+    """
+    Fetch a URL and return its content in the specified format.
+
+    Args:
+        url: The URL to fetch and process.
+        format: Output format — "markdown" (default), "json", or "text".
+        vision: Enable vision API for image descriptions.
+        no_playwright: Skip Playwright, use static fetch only.
+        max_tokens: Maximum output tokens (default: 50000).
+        timeout: Subprocess timeout in seconds (default: 30).
+
+    Returns:
+        The processed page content as a string.
+
+    Raises:
+        RawfyError: If the fetch fails or the CLI is not found.
+    """
+    cmd = _find_rawfy_cli()
+    cmd.extend(["fetch", url, "--format", format, "--max-tokens", str(max_tokens)])
+
+    if vision:
+        cmd.append("--vision")
+    if no_playwright:
+        cmd.append("--no-playwright")
+
+    try:
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            timeout=timeout,
+        )
+    except FileNotFoundError:
+        raise RawfyError(
+            "Node.js not found. Rawfy requires Node.js >= 18.",
+            code="NODE_NOT_FOUND",
+        )
+    except subprocess.TimeoutExpired:
+        raise RawfyError(
+            f"Rawfy timed out after {timeout}s fetching {url}",
+            code="TIMEOUT",
+            url=url,
+        )
+
+    if result.returncode != 0:
+        stderr = result.stderr.strip()
+        raise RawfyError(
+            stderr or f"rawfy fetch failed with exit code {result.returncode}",
+            code="FETCH_FAILED",
+            url=url,
+        )
+
+    return result.stdout
+
+
+def fetch_json(
+    url: str,
+    *,
+    vision: bool = False,
+    no_playwright: bool = False,
+    max_tokens: int = 50_000,
+    timeout: int = 30,
+) -> dict[str, Any]:
+    """
+    Fetch a URL and return structured data as a Python dict.
+
+    Convenience wrapper around fetch() with format="json".
+
+    Args:
+        url: The URL to fetch and process.
+        vision: Enable vision API for image descriptions.
+        no_playwright: Skip Playwright, use static fetch only.
+        max_tokens: Maximum output tokens (default: 50000).
+        timeout: Subprocess timeout in seconds (default: 30).
+
+    Returns:
+        Parsed JSON as a dict with keys: metadata, content, media,
+        interactive_elements, fetch_stats.
+
+    Raises:
+        RawfyError: If the fetch fails or JSON parsing fails.
+    """
+    raw = fetch(
+        url,
+        format="json",
+        vision=vision,
+        no_playwright=no_playwright,
+        max_tokens=max_tokens,
+        timeout=timeout,
+    )
+
+    try:
+        return json.loads(raw)
+    except json.JSONDecodeError as e:
+        raise RawfyError(
+            f"Failed to parse rawfy JSON output: {e}",
+            code="JSON_PARSE_ERROR",
+            url=url,
+        )
+
+
+def metadata(
+    url: str,
+    *,
+    no_playwright: bool = False,
+    timeout: int = 15,
+) -> dict[str, Any]:
+    """
+    Fetch only the metadata for a URL (lightweight).
+
+    Returns title, description, type, language, word count, etc.
+    without processing media or generating full content.
+
+    Args:
+        url: The URL to fetch metadata for.
+        no_playwright: Skip Playwright, use static fetch only.
+        timeout: Subprocess timeout in seconds (default: 15).
+
+    Returns:
+        Metadata dict with keys: url, title, description, type,
+        lang, word_count, reading_time_minutes, etc.
+
+    Raises:
+        RawfyError: If the fetch fails.
+    """
+    # Use the JSON format and extract just the metadata
+    data = fetch_json(
+        url,
+        no_playwright=no_playwright,
+        max_tokens=10_000,
+        timeout=timeout,
+    )
+    return data.get("metadata", {})
+
+
+def check_installation() -> dict[str, Any]:
+    """
+    Check if Rawfy and its dependencies are properly installed.
+
+    Returns:
+        Dict with installation status:
+        {
+            "node": True/False,
+            "rawfy_cli": True/False,
+            "playwright": True/False,
+            "version": "0.1.0" or None
+        }
+    """
+    status: dict[str, Any] = {
+        "node": False,
+        "rawfy_cli": False,
+        "playwright": False,
+        "version": None,
+    }
+
+    # Check Node.js
+    if shutil.which("node"):
+        status["node"] = True
+
+    # Check rawfy CLI
+    try:
+        cmd = _find_rawfy_cli()
+        result = subprocess.run(
+            [*cmd, "version"],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+        if result.returncode == 0:
+            status["rawfy_cli"] = True
+            status["version"] = result.stdout.strip()
+    except (RawfyError, subprocess.TimeoutExpired, FileNotFoundError):
+        pass
+
+    # Check Playwright
+    try:
+        result = subprocess.run(
+            ["npx", "playwright", "--version"],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+        if result.returncode == 0:
+            status["playwright"] = True
+    except (subprocess.TimeoutExpired, FileNotFoundError):
+        pass
+
+    return status
+
+
+def main() -> None:
+    """CLI entry point for python -m rawfy."""
+    if len(sys.argv) < 2:
+        print("Usage: python -m rawfy <url> [--format markdown|json|text]")
+        sys.exit(1)
+
+    url = sys.argv[1]
+    fmt: OutputFormat = "markdown"
+
+    if "--format" in sys.argv:
+        idx = sys.argv.index("--format")
+        if idx + 1 < len(sys.argv):
+            fmt = sys.argv[idx + 1]  # type: ignore[assignment]
+
+    try:
+        output = fetch(url, format=fmt)
+        print(output)
+    except RawfyError as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+# Entry point for `python -m rawfy`
+if __name__ == "__main__":
+    main()

rawfy-0.1.0/rawfy.egg-info/PKG-INFO

@@ -0,0 +1,98 @@
+Metadata-Version: 2.4
+Name: rawfy
+Version: 0.1.0
+Summary: Python wrapper for the Rawfy AI agent skill — converts any URL into structured, agent-readable content
+Author: rishiiicreates
+License: MIT
+Project-URL: Homepage, https://github.com/rishiiicreates/rawfy
+Project-URL: Repository, https://github.com/rishiiicreates/rawfy
+Project-URL: Issues, https://github.com/rishiiicreates/rawfy/issues
+Keywords: ai,agent,mcp,web,scraper,markdown,rawfy
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+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: Topic :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+
+# Rawfy Python Wrapper
+
+Python bindings for the [Rawfy](https://github.com/rishiiicreates/rawfy) AI agent skill.
+
+## Prerequisites
+
+- **Node.js >= 18** — Rawfy is a Node.js tool
+- **Rawfy CLI** — `npm install -g rawfy`
+
+## Install
+
+```bash
+pip install rawfy
+```
+
+## Quick Start
+
+```python
+from rawfy import fetch, metadata
+
+# Full page fetch (returns WSM markdown)
+content = fetch("https://example.com")
+
+# Get structured JSON data
+import json
+data = fetch("https://example.com", format="json")
+parsed = json.loads(data)
+
+# Or use the convenience wrapper
+from rawfy import fetch_json
+data = fetch_json("https://example.com")
+print(data["metadata"]["title"])
+
+# Lightweight metadata only
+meta = metadata("https://docs.python.org")
+print(f"Title: {meta['title']}, Words: {meta['word_count']}")
+```
+
+## API
+
+### `fetch(url, *, format="markdown", vision=False, no_playwright=False, max_tokens=50000, timeout=30)`
+
+Fetch and process a URL. Returns the content as a string.
+
+### `fetch_json(url, **kwargs)`
+
+Same as `fetch()` with `format="json"`, returns a parsed dict.
+
+### `metadata(url, *, no_playwright=False, timeout=15)`
+
+Fetch only page metadata (lightweight). Returns a dict.
+
+### `check_installation()`
+
+Check if Rawfy and dependencies are installed. Returns a status dict.
+
+## Error Handling
+
+```python
+from rawfy import fetch, RawfyError
+
+try:
+    content = fetch("https://example.com")
+except RawfyError as e:
+    print(f"Error [{e.code}]: {e}")
+    print(f"URL: {e.url}")
+```
+
+## CLI
+
+```bash
+python -m rawfy https://example.com
+python -m rawfy https://example.com --format json
+```

rawfy-0.1.0/rawfy.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+rawfy/__init__.py
+rawfy/__main__.py
+rawfy/client.py
+rawfy.egg-info/PKG-INFO
+rawfy.egg-info/SOURCES.txt
+rawfy.egg-info/dependency_links.txt
+rawfy.egg-info/entry_points.txt
+rawfy.egg-info/top_level.txt

rawfy-0.1.0/rawfy.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

rawfy-0.1.0/rawfy.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+rawfy-py = rawfy.client:main

rawfy-0.1.0/rawfy.egg-info/top_level.txt

@@ -0,0 +1 @@
+rawfy

rawfy-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+