html-reader-llm 0.0.1__tar.gz

html_reader_llm-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 ClericPy
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

html_reader_llm-0.0.1/PKG-INFO

@@ -0,0 +1,52 @@
+Metadata-Version: 2.4
+Name: html-reader-llm
+Version: 0.0.1
+Summary: HTML simplification and intelligent extraction for LLM
+Author-email: Clericpy <clericpy@gmail.com>
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: minify-html>=0.18.1
+Requires-Dist: python-dotenv>=1.2.2
+Requires-Dist: selectolax>=0.4.7
+Requires-Dist: trafilatura>=2.2.0
+
+# html-reader-llm
+
+HTML simplification and intelligent extraction for LLM.
+
+## Features
+
+- HTML simplification for LLM consumption
+- Render detection (HTTP vs Chrome)
+- LLM-powered page classification and CSS selector generation
+- CSS selector validation
+
+## Installation
+
+```bash
+pip install html-reader-llm
+```
+
+## Usage
+
+```bash
+# Simplify HTML
+html-reader-llm simplify < page.html
+
+# Detect if browser rendering is needed
+html-reader-llm detect https://example.com
+
+# Full analysis with LLM
+html-reader-llm analyze https://example.com
+
+# Fetch HTML
+html-reader-llm fetch https://example.com
+
+# Validate CSS selectors
+html-reader-llm validate https://example.com --rules-file selectors.json
+```
+
+## License
+
+MIT

html_reader_llm-0.0.1/README.md

@@ -0,0 +1,39 @@
+# html-reader-llm
+
+HTML simplification and intelligent extraction for LLM.
+
+## Features
+
+- HTML simplification for LLM consumption
+- Render detection (HTTP vs Chrome)
+- LLM-powered page classification and CSS selector generation
+- CSS selector validation
+
+## Installation
+
+```bash
+pip install html-reader-llm
+```
+
+## Usage
+
+```bash
+# Simplify HTML
+html-reader-llm simplify < page.html
+
+# Detect if browser rendering is needed
+html-reader-llm detect https://example.com
+
+# Full analysis with LLM
+html-reader-llm analyze https://example.com
+
+# Fetch HTML
+html-reader-llm fetch https://example.com
+
+# Validate CSS selectors
+html-reader-llm validate https://example.com --rules-file selectors.json
+```
+
+## License
+
+MIT

html_reader_llm-0.0.1/pyproject.toml

@@ -0,0 +1,28 @@
+[project]
+name = "html-reader-llm"
+version = "0.0.1"
+description = "HTML simplification and intelligent extraction for LLM"
+readme = "README.md"
+authors = [
+    { name = "Clericpy", email = "clericpy@gmail.com" }
+]
+requires-python = ">=3.12"
+dependencies = [
+    "minify-html>=0.18.1",
+    "python-dotenv>=1.2.2",
+    "selectolax>=0.4.7",
+    "trafilatura>=2.2.0",
+]
+
+
+[project.scripts]
+html-reader-llm = "html_reader_llm.cli:main"
+
+[build-system]
+requires = ["flit_core>=3.12,<4"]
+build-backend = "flit_core.buildapi"
+
+[dependency-groups]
+dev = [
+    "pytest>=9.1.1",
+]

html_reader_llm-0.0.1/src/html_reader_llm/__init__.py

@@ -0,0 +1,39 @@
+"""html-reader-llm — HTML simplification and intelligent extraction for LLM.
+
+Quick start (pip install):
+    pip install selectolax
+    from html_reader_llm import simplify_html
+    result = simplify_html(html_string)
+
+Copy usage (no pip):
+    Copy settings.py and simplify.py into your project,
+    change `from html_reader_llm import settings` to `from . import settings` (or
+    adjust the import path), then use:
+    from simplify import simplify_html
+    result = simplify_html(html_string)
+"""
+
+from html_reader_llm.browser import (
+    BrowserNotFoundError,
+    detect_browser_paths,
+    get_browser_path,
+    validate_browser_path,
+)
+from html_reader_llm.llm import AnalysisResult, analyze_page
+from html_reader_llm.render_detect import RenderDetectResult, detect_render
+from html_reader_llm.selector_validator import SelectorValidator, validate_url_selectors
+from html_reader_llm.simplify import simplify_html
+
+__all__ = [
+    "AnalysisResult",
+    "BrowserNotFoundError",
+    "RenderDetectResult",
+    "SelectorValidator",
+    "analyze_page",
+    "detect_browser_paths",
+    "detect_render",
+    "get_browser_path",
+    "simplify_html",
+    "validate_browser_path",
+    "validate_url_selectors",
+]

html_reader_llm-0.0.1/src/html_reader_llm/browser.py

@@ -0,0 +1,161 @@
+"""Chrome/Edge browser path detection — platform-aware discovery and validation.
+
+Three usage modes:
+- detect_browser_paths() → list all found paths
+- get_browser_path() → auto-select first (or None), checks ENV first
+- validate_browser_path(path) → validate user path, raise if invalid
+
+ENV override: HTMLREADER_CHROME_PATH
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+import platform
+import shutil
+import subprocess
+
+logger = logging.getLogger(__name__)
+
+# --- Platform-specific known paths ---
+
+WIN32_PATHS: list[str] = [
+    "C:/Program Files (x86)/Google/Chrome/Application/chrome.exe",
+    "C:/Program Files/Google/Chrome/Application/chrome.exe",
+    "C:/Program Files (x86)/Microsoft/Edge/Application/msedge.exe",
+    "C:/Program Files/Microsoft/Edge/Application/msedge.exe",
+]
+
+# Add %USERPROFILE% based paths at runtime
+_WIN32_USERPROFILE_PATHS: list[str] = [
+    "AppData/Local/Google/Chrome/Application/chrome.exe",
+    "AppData/Local/Microsoft/Edge/Application/msedge.exe",
+]
+
+LINUX_PATHS: list[str] = [
+    "google-chrome",
+    "google-chrome-stable",
+    "google-chrome-beta",
+    "google-chrome-dev",
+    "microsoft-edge-stable",
+]
+
+DARWIN_PATHS: list[str] = [
+    "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome",
+    "/Applications/Microsoft Edge.app/Contents/MacOS/Microsoft Edge",
+]
+
+_VERSION_PREFIXES = (b"Google Chrome ", b"Microsoft Edge")
+
+
+class BrowserNotFoundError(Exception):
+    """Raised when no valid Chrome/Edge executable is found."""
+
+
+def _iter_browser_paths() -> list[str]:
+    """Detect installed Chrome/Edge paths on the current platform.
+
+    Returns a list of absolute paths, sorted by mtime descending (newest first).
+    """
+    current = platform.system()
+    found: set[str] = set()
+
+    if current == "Windows":
+        # Fixed known paths
+        for p in WIN32_PATHS:
+            if os.path.isfile(p):
+                found.add(os.path.abspath(p))
+        # USERPROFILE-based paths
+        userprofile = os.environ.get("USERPROFILE", "")
+        if userprofile:
+            for rel in _WIN32_USERPROFILE_PATHS:
+                full = os.path.join(userprofile, rel)
+                if os.path.isfile(full):
+                    found.add(os.path.abspath(full))
+
+    elif current == "Linux":
+        for cmd in LINUX_PATHS:
+            resolved = shutil.which(cmd)
+            if resolved and _verify_browser(resolved):
+                found.add(os.path.abspath(resolved))
+
+    elif current == "Darwin":
+        for p in DARWIN_PATHS:
+            if os.path.isfile(p):
+                found.add(os.path.abspath(p))
+
+    else:
+        logger.warning("Unsupported platform: %s", current)
+
+    result = sorted(found, key=_mtime_key, reverse=True)
+    return result
+
+
+def _verify_browser(path: str) -> bool:
+    """Check if a binary is actually Chrome/Edge by running --version."""
+    try:
+        out = subprocess.check_output(
+            [path, "--version"], timeout=2, stderr=subprocess.DEVNULL
+        )
+        return any(out.startswith(prefix) for prefix in _VERSION_PREFIXES)
+    except (FileNotFoundError, subprocess.TimeoutExpired, OSError):
+        return False
+
+
+def _mtime_key(path: str) -> float:
+    """Get mtime for sorting, 0 if file doesn't exist."""
+    try:
+        return os.path.getmtime(path)
+    except OSError:
+        return 0.0
+
+
+def detect_browser_paths() -> list[str]:
+    """List all detected Chrome/Edge browser paths on this platform.
+
+    Returns absolute paths sorted by modification time (newest first).
+    """
+    return _iter_browser_paths()
+
+
+def get_browser_path() -> str | None:
+    """Auto-select the best browser path.
+
+    Priority:
+    1. HTMLREADER_CHROME_PATH env var (if set and valid)
+    2. First detected path (newest by mtime)
+
+    Returns None if no browser is found.
+    """
+    # ENV override
+    env_path = os.environ.get("HTMLREADER_CHROME_PATH", "").strip()
+    if env_path:
+        try:
+            return validate_browser_path(env_path)
+        except BrowserNotFoundError:
+            logger.warning(
+                "HTMLREADER_CHROME_PATH=%s is invalid, falling back to auto-detect",
+                env_path,
+            )
+
+    paths = detect_browser_paths()
+    return paths[0] if paths else None
+
+
+def validate_browser_path(path: str) -> str:
+    """Validate a user-provided browser path.
+
+    Args:
+        path: Path to Chrome/Edge executable.
+
+    Returns:
+        Absolute resolved path.
+
+    Raises:
+        BrowserNotFoundError: If the path does not exist or is not a valid file.
+    """
+    resolved = os.path.abspath(path)
+    if not os.path.isfile(resolved):
+        raise BrowserNotFoundError(f"Browser executable not found: {resolved}")
+    return resolved