better-websearch-cli 0.0.1__tar.gz

better_websearch_cli-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Websearch CLI
+
+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.

better_websearch_cli-0.0.1/PKG-INFO

@@ -0,0 +1,148 @@
+Metadata-Version: 2.4
+Name: better-websearch-cli
+Version: 0.0.1
+Summary: CLI tool to fetch URLs and search the web
+Requires-Python: >=3.14
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: typer[all]>=0.12
+Requires-Dist: httpx>=0.25
+Requires-Dist: selectolax>=0.3
+Requires-Dist: markdownify>=0.12
+Requires-Dist: rich>=13.0
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Provides-Extra: spa
+Requires-Dist: playwright>=1.40; extra == "spa"
+Dynamic: license-file
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="public/banner.jpg">
+    <source media="(prefers-color-scheme: light)" srcset="public/banner.jpg">
+    <img src="public/banner.jpg" alt="Websearch CLI Logo" width="100%">
+  </picture>
+</p>
+
+<h1 align="center">Websearch CLI</h1>
+
+<p align="center">
+  Fetch URLs and search the web from your terminal. Fast, simple, and extensible.
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/websearch/">
+    <img src="https://img.shields.io/pypi/v/websearch" alt="PyPI Version">
+  </a>
+  <a href="https://github.com/AliiiBenn/websearch">
+    <img src="https://img.shields.io/github/license/AliiiBenn/websearch" alt="License">
+  </a>
+  <a href="https://github.com/AliiiBenn/websearch/actions">
+    <img src="https://img.shields.io/github/actions/workflow/status/AliiiBenn/websearch/test" alt="Tests">
+  </a>
+  <a href="https://www.python.org/">
+    <img src="https://img.shields.io/badge/python-3.14+-blue" alt="Python">
+  </a>
+</p>
+
+Fetch web pages and search the internet - all from your command line.
+
+## Why Websearch CLI?
+
+- **Fast** - Async HTTP powered by httpx
+- **Smart caching** - Local cache with TTL and automatic eviction
+- **Clean output** - HTML to Markdown conversion with XSS protection
+- **Type-safe** - 100% type-annotated Python
+
+## Features
+
+- Fetch URLs and convert to Markdown
+- Web search via Brave Search API
+- Local caching with TTL and size limits
+- XSS protection and HTML sanitization
+- SPA (Single Page App) detection
+- Retry with exponential backoff
+
+## Quick Start
+
+```bash
+# Install
+uv add websearch
+
+# Fetch a URL as Markdown
+websearch fetch https://example.com
+
+# Search the web
+websearch search "python async tutorial"
+
+# Fetch with options
+websearch fetch https://example.com --no-cache --verbose
+websearch search "python" -n 20 -t news
+```
+
+## Command Overview
+
+| Command | Description |
+|---------|-------------|
+| `websearch fetch <url>` | Fetch URL and convert to Markdown |
+| `websearch search <query>` | Search the web |
+| `websearch ping` | Check if CLI is working |
+
+## Fetch Options
+
+```
+--refresh, -r       Skip cache and force fresh fetch
+--no-cache          Disable caching
+--no-verify         Skip SSL certificate verification
+--output, -o PATH    Output file path
+--verbose, -v        Show verbose output
+```
+
+## Search Options
+
+```
+--count, -n <n>      Number of results (1-50, default: 10)
+--type, -t <type>   Result type: web, news, images, videos
+--output, -o PATH    Output file path
+--json               Output raw JSON response
+--no-cache           Disable caching
+```
+
+## Configuration
+
+Set your Brave API key:
+
+```bash
+export BRAVE_API_KEY=your_api_key_here
+```
+
+Get your API key at https://brave.com/search/api/
+
+## Development
+
+```bash
+# Clone and install
+git clone https://github.com/AliiiBenn/websearch.git
+cd websearch
+uv sync --dev
+
+# Run tests
+uv run pytest
+
+# Lint and type-check
+uv run ruff check websearch/
+uv run mypy websearch/
+
+# Try it out
+uv run websearch fetch https://example.com
+```
+
+## Contributing
+
+Contributions are welcome! Feel free to open issues or submit PRs.
+
+## License
+
+MIT - See [LICENSE](LICENSE) for details.

better_websearch_cli-0.0.1/README.md

@@ -0,0 +1,128 @@
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="public/banner.jpg">
+    <source media="(prefers-color-scheme: light)" srcset="public/banner.jpg">
+    <img src="public/banner.jpg" alt="Websearch CLI Logo" width="100%">
+  </picture>
+</p>
+
+<h1 align="center">Websearch CLI</h1>
+
+<p align="center">
+  Fetch URLs and search the web from your terminal. Fast, simple, and extensible.
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/websearch/">
+    <img src="https://img.shields.io/pypi/v/websearch" alt="PyPI Version">
+  </a>
+  <a href="https://github.com/AliiiBenn/websearch">
+    <img src="https://img.shields.io/github/license/AliiiBenn/websearch" alt="License">
+  </a>
+  <a href="https://github.com/AliiiBenn/websearch/actions">
+    <img src="https://img.shields.io/github/actions/workflow/status/AliiiBenn/websearch/test" alt="Tests">
+  </a>
+  <a href="https://www.python.org/">
+    <img src="https://img.shields.io/badge/python-3.14+-blue" alt="Python">
+  </a>
+</p>
+
+Fetch web pages and search the internet - all from your command line.
+
+## Why Websearch CLI?
+
+- **Fast** - Async HTTP powered by httpx
+- **Smart caching** - Local cache with TTL and automatic eviction
+- **Clean output** - HTML to Markdown conversion with XSS protection
+- **Type-safe** - 100% type-annotated Python
+
+## Features
+
+- Fetch URLs and convert to Markdown
+- Web search via Brave Search API
+- Local caching with TTL and size limits
+- XSS protection and HTML sanitization
+- SPA (Single Page App) detection
+- Retry with exponential backoff
+
+## Quick Start
+
+```bash
+# Install
+uv add websearch
+
+# Fetch a URL as Markdown
+websearch fetch https://example.com
+
+# Search the web
+websearch search "python async tutorial"
+
+# Fetch with options
+websearch fetch https://example.com --no-cache --verbose
+websearch search "python" -n 20 -t news
+```
+
+## Command Overview
+
+| Command | Description |
+|---------|-------------|
+| `websearch fetch <url>` | Fetch URL and convert to Markdown |
+| `websearch search <query>` | Search the web |
+| `websearch ping` | Check if CLI is working |
+
+## Fetch Options
+
+```
+--refresh, -r       Skip cache and force fresh fetch
+--no-cache          Disable caching
+--no-verify         Skip SSL certificate verification
+--output, -o PATH    Output file path
+--verbose, -v        Show verbose output
+```
+
+## Search Options
+
+```
+--count, -n <n>      Number of results (1-50, default: 10)
+--type, -t <type>   Result type: web, news, images, videos
+--output, -o PATH    Output file path
+--json               Output raw JSON response
+--no-cache           Disable caching
+```
+
+## Configuration
+
+Set your Brave API key:
+
+```bash
+export BRAVE_API_KEY=your_api_key_here
+```
+
+Get your API key at https://brave.com/search/api/
+
+## Development
+
+```bash
+# Clone and install
+git clone https://github.com/AliiiBenn/websearch.git
+cd websearch
+uv sync --dev
+
+# Run tests
+uv run pytest
+
+# Lint and type-check
+uv run ruff check websearch/
+uv run mypy websearch/
+
+# Try it out
+uv run websearch fetch https://example.com
+```
+
+## Contributing
+
+Contributions are welcome! Feel free to open issues or submit PRs.
+
+## License
+
+MIT - See [LICENSE](LICENSE) for details.

better_websearch_cli-0.0.1/better_websearch_cli.egg-info/PKG-INFO

@@ -0,0 +1,148 @@
+Metadata-Version: 2.4
+Name: better-websearch-cli
+Version: 0.0.1
+Summary: CLI tool to fetch URLs and search the web
+Requires-Python: >=3.14
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: typer[all]>=0.12
+Requires-Dist: httpx>=0.25
+Requires-Dist: selectolax>=0.3
+Requires-Dist: markdownify>=0.12
+Requires-Dist: rich>=13.0
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Provides-Extra: spa
+Requires-Dist: playwright>=1.40; extra == "spa"
+Dynamic: license-file
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="public/banner.jpg">
+    <source media="(prefers-color-scheme: light)" srcset="public/banner.jpg">
+    <img src="public/banner.jpg" alt="Websearch CLI Logo" width="100%">
+  </picture>
+</p>
+
+<h1 align="center">Websearch CLI</h1>
+
+<p align="center">
+  Fetch URLs and search the web from your terminal. Fast, simple, and extensible.
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/websearch/">
+    <img src="https://img.shields.io/pypi/v/websearch" alt="PyPI Version">
+  </a>
+  <a href="https://github.com/AliiiBenn/websearch">
+    <img src="https://img.shields.io/github/license/AliiiBenn/websearch" alt="License">
+  </a>
+  <a href="https://github.com/AliiiBenn/websearch/actions">
+    <img src="https://img.shields.io/github/actions/workflow/status/AliiiBenn/websearch/test" alt="Tests">
+  </a>
+  <a href="https://www.python.org/">
+    <img src="https://img.shields.io/badge/python-3.14+-blue" alt="Python">
+  </a>
+</p>
+
+Fetch web pages and search the internet - all from your command line.
+
+## Why Websearch CLI?
+
+- **Fast** - Async HTTP powered by httpx
+- **Smart caching** - Local cache with TTL and automatic eviction
+- **Clean output** - HTML to Markdown conversion with XSS protection
+- **Type-safe** - 100% type-annotated Python
+
+## Features
+
+- Fetch URLs and convert to Markdown
+- Web search via Brave Search API
+- Local caching with TTL and size limits
+- XSS protection and HTML sanitization
+- SPA (Single Page App) detection
+- Retry with exponential backoff
+
+## Quick Start
+
+```bash
+# Install
+uv add websearch
+
+# Fetch a URL as Markdown
+websearch fetch https://example.com
+
+# Search the web
+websearch search "python async tutorial"
+
+# Fetch with options
+websearch fetch https://example.com --no-cache --verbose
+websearch search "python" -n 20 -t news
+```
+
+## Command Overview
+
+| Command | Description |
+|---------|-------------|
+| `websearch fetch <url>` | Fetch URL and convert to Markdown |
+| `websearch search <query>` | Search the web |
+| `websearch ping` | Check if CLI is working |
+
+## Fetch Options
+
+```
+--refresh, -r       Skip cache and force fresh fetch
+--no-cache          Disable caching
+--no-verify         Skip SSL certificate verification
+--output, -o PATH    Output file path
+--verbose, -v        Show verbose output
+```
+
+## Search Options
+
+```
+--count, -n <n>      Number of results (1-50, default: 10)
+--type, -t <type>   Result type: web, news, images, videos
+--output, -o PATH    Output file path
+--json               Output raw JSON response
+--no-cache           Disable caching
+```
+
+## Configuration
+
+Set your Brave API key:
+
+```bash
+export BRAVE_API_KEY=your_api_key_here
+```
+
+Get your API key at https://brave.com/search/api/
+
+## Development
+
+```bash
+# Clone and install
+git clone https://github.com/AliiiBenn/websearch.git
+cd websearch
+uv sync --dev
+
+# Run tests
+uv run pytest
+
+# Lint and type-check
+uv run ruff check websearch/
+uv run mypy websearch/
+
+# Try it out
+uv run websearch fetch https://example.com
+```
+
+## Contributing
+
+Contributions are welcome! Feel free to open issues or submit PRs.
+
+## License
+
+MIT - See [LICENSE](LICENSE) for details.

better_websearch_cli-0.0.1/better_websearch_cli.egg-info/SOURCES.txt

@@ -0,0 +1,39 @@
+LICENSE
+README.md
+pyproject.toml
+better_websearch_cli.egg-info/PKG-INFO
+better_websearch_cli.egg-info/SOURCES.txt
+better_websearch_cli.egg-info/dependency_links.txt
+better_websearch_cli.egg-info/entry_points.txt
+better_websearch_cli.egg-info/requires.txt
+better_websearch_cli.egg-info/top_level.txt
+tests/test_cache.py
+tests/test_converter.py
+tests/test_fetcher.py
+tests/test_maybe.py
+tests/test_result.py
+tests/test_search.py
+websearch/__main__.py
+websearch/main.py
+websearch/core/__init__.py
+websearch/core/cache/__init__.py
+websearch/core/cache/cache.py
+websearch/core/cache/key.py
+websearch/core/cache/storage.py
+websearch/core/cache/ttl.py
+websearch/core/converter/__init__.py
+websearch/core/converter/converter.py
+websearch/core/converter/encoding.py
+websearch/core/converter/security.py
+websearch/core/fetcher/__init__.py
+websearch/core/fetcher/backoff.py
+websearch/core/fetcher/detection.py
+websearch/core/fetcher/errors.py
+websearch/core/fetcher/fetcher.py
+websearch/core/search/__init__.py
+websearch/core/search/client.py
+websearch/core/search/search.py
+websearch/core/search/types.py
+websearch/core/types/__init__.py
+websearch/core/types/maybe.py
+websearch/core/types/result.py

better_websearch_cli-0.0.1/better_websearch_cli.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

better_websearch_cli-0.0.1/better_websearch_cli.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+websearch = websearch.main:main

better_websearch_cli-0.0.1/better_websearch_cli.egg-info/requires.txt

@@ -0,0 +1,13 @@
+typer[all]>=0.12
+httpx>=0.25
+selectolax>=0.3
+markdownify>=0.12
+rich>=13.0
+
+[dev]
+pytest
+ruff
+mypy
+
+[spa]
+playwright>=1.40

better_websearch_cli-0.0.1/better_websearch_cli.egg-info/top_level.txt

@@ -0,0 +1 @@
+websearch

better_websearch_cli-0.0.1/pyproject.toml

@@ -0,0 +1,47 @@
+[project]
+name = "better-websearch-cli"
+version = "0.0.1"
+description = "CLI tool to fetch URLs and search the web"
+readme = "README.md"
+requires-python = ">=3.14"
+dependencies = [
+    "typer[all]>=0.12",
+    "httpx>=0.25",
+    "selectolax>=0.3",
+    "markdownify>=0.12",
+    "rich>=13.0",
+]
+
+[project.optional-dependencies]
+dev = ["pytest", "ruff", "mypy"]
+spa = ["playwright>=1.40"]
+
+[project.scripts]
+websearch = "websearch.main:main"
+
+[tool.uv]
+package = true
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["websearch*"]
+exclude = ["public*"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+target-version = "py314"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "N", "W"]
+ignore = ["E501"]
+
+[tool.mypy]
+python_version = "3.14"
+warn_return_any = false
+warn_unused_ignores = false
+explicit_package_bases = true
+ignore_missing_imports = true
+ignore_errors = true
+

better_websearch_cli-0.0.1/setup.cfg

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