security-geeks · pull · Apr 24, 2025 · Jul 19, 2026 · Jul 19, 2026 · Jul 19, 2026
diff --git a/.github/workflows/flake8.yml b/.github/workflows/flake8.yml
@@ -2,6 +2,9 @@ name: Flake8
 
 on: [push]
 
+permissions:
+  contents: read
+
 jobs:
   build:
     runs-on: ubuntu-latest

diff --git a/README.md b/README.md
@@ -42,6 +42,7 @@
 ### Recent improvements
 - The CLI now allows `--version` and `--update` to run without requiring a URL.
 - The crawler now resolves relative links against the current page and skips unsupported or malformed hrefs more gracefully.
+- The optional TorBotApp desktop UI can be launched from the CLI with `torbot app` when installed as a sibling checkout.
 
 ...(will be updated)
 
@@ -78,6 +79,9 @@ python main.py -u https://example.com --depth 2 --save json
 
 # Disable SOCKS5 if you are not using Tor locally
 python main.py -u https://example.com --disable-socks5 --visualize tree
+
+# Launch the optional desktop app when TorBotApp is installed
+torbot app
 ```
 
 ### Options
@@ -93,6 +97,8 @@ optional arguments:
   -v                    Displays DEBUG level logging, default is INFO
   --version             Show the current version of TorBot.
   --update              Update TorBot to the latest stable version
+  --app                 Run optional TorBot desktop app
+  --app-dir APP_DIR     Path to a TorBotApp checkout
   -q, --quiet           Prevents display of header and IP address
   --save FORMAT         Save results in a file. (tree, JSON)
   --visualize FORMAT    Visualizes tree of data gathered. (tree, JSON, table)
@@ -106,6 +112,36 @@ If you are using Tor locally, keep the SOCKS5 proxy enabled. If you are not usin
 
 Read more about torrc here: [Torrc](https://github.com/DedSecInside/TorBoT/blob/master/Tor.md)
 
+## Optional desktop app
+
+TorBot remains a CLI-first Python tool. The desktop UI lives in the separate
+[TorBotApp](https://github.com/KingAkeem/TorBotApp) Electron project so Node and
+Electron are not required for CLI users.
+
+To launch it from this CLI, install TorBotApp as a sibling checkout:
+
+```text
+code/
++-- TorBot/
++-- TorBotApp/
+```
+
+Then run:
+
+```sh
+torbot app
+```
+
+If TorBotApp is somewhere else, use either:
+
+```sh
+TORBOT_APP_DIR=/path/to/TorBotApp torbot app
+torbot --app --app-dir /path/to/TorBotApp
+```
+
+See [Desktop App Architecture](docs/DESKTOP_APP.md) for how the CLI, optional UI,
+and backend services fit together.
+
 ## Curated Features
 - [x] Visualization Module Revamp
 - [x] Implement BFS Search for webcrawler

diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
@@ -2,6 +2,37 @@
 --------------------
 All notable changes to this project will be documented in this file.
 
+## 4.3.0 - 2026-07-28
+
+### Changed
+- Made NLP classification train lazily from the packaged CSV and cache the classifier for the process, avoiding model retraining for every crawled page.
+- Changed the NLP score returned by `classify()` from a misleading random-split accuracy value to prediction confidence for the selected category.
+
+### Fixed
+- Removed runtime `training_data/` generation from page classification so installed packages do not try to write generated files into `site-packages`.
+- Removed process-wide directory changes from the NLP helpers.
+
+### Tests
+- Added direct NLP coverage for HTML text extraction, CSV loading, classifier scoring, and path-safe training-data export.
+
+## 4.2.0 - 2026-07-28
+
+Install from PyPI after publishing with:
+
+```sh
+pip install torbot==4.2.0
+```
+
+### Added
+- Added optional `torbot app` and `torbot --app` CLI commands for launching the TorBotApp desktop UI when installed separately.
+- Added TorBotApp discovery through `--app-dir`, `TORBOT_APP_DIR`, or a sibling `TorBotApp` checkout.
+- Documented the optional desktop app architecture while keeping Node and Electron out of the Python package dependencies.
+- Added a safer publish helper that checks current-version artifacts and prompts for a PyPI token only when uploading.
+
+### Fixed
+- Moved the CLI implementation into the installed package so the `torbot` console command works from a wheel install.
+- Removed the deprecated `sklearn` package dependency in favor of the existing `scikit-learn` dependency so fresh installs do not fail.
+
 ## 4.1.1
 
 ### Fixed

diff --git a/docs/DESKTOP_APP.md b/docs/DESKTOP_APP.md
@@ -0,0 +1,41 @@
+# Desktop App Architecture
+
+TorBot is CLI-first. The optional desktop experience is provided by
+[TorBotApp](https://github.com/KingAkeem/TorBotApp), a separate Electron and
+React project.
+
+Keeping the app separate preserves a lightweight Python install for CLI users:
+
+- TorBot owns the Python package, command-line crawler, and library modules.
+- TorBotApp owns the desktop UI, Electron packaging, and Node dependency tree.
+- Backend crawl services expose the API consumed by TorBotApp.
+
+## Launching from TorBot
+
+The CLI can launch TorBotApp when it is installed locally:
+
+```sh
+torbot app
+```
+
+Discovery order:
+
+1. `--app-dir /path/to/TorBotApp`
+2. `TORBOT_APP_DIR=/path/to/TorBotApp`
+3. A sibling `TorBotApp` directory next to this repository
+
+If the app is not found, TorBot prints setup guidance and exits without changing
+normal CLI behavior.
+
+## Expected development layout
+
+```text
+code/
++-- TorBot/
++-- TorBotApp/
++-- gotor/
+```
+
+TorBotApp currently talks to the GoTor job-control API. If this Python package
+later grows a compatible `torbot serve` API, TorBotApp can support either
+backend without making Electron a required dependency of the CLI.
diff --git a/main.py b/main.py
@@ -1,192 +1,12 @@
 #!/usr/bin/env python3
 
-import os
-import argparse
-import sys
-import logging
-import toml
-import httpx
+from torbot.cli import get_version, main, run, set_arguments
 
-from torbot.modules.api import get_ip
-from torbot.modules.color import color
-from torbot.modules.updater import check_version
-from torbot.modules.info import execute_all, fetch_html
-from torbot.modules.linktree import LinkTree
-
-
-def print_tor_ip_address(client: httpx.Client) -> None:
-    """
-    https://check.torproject.org/ tells you if you are using tor and it
-    displays your IP address which we scape and display
-    """
-    resp = get_ip(client)
-    print(resp["header"])
-    print(color(resp["body"], "yellow"))
-
-
-def print_header(version: str) -> None:
-    """
-    Prints the TorBot banner including version and license.
-    """
-    license_msg = color("LICENSE: GNU Public License v3", "red")
-    banner = r"""
-                            __  ____  ____  __        ______
-                            / /_/ __ \/ __ \/ /_  ____/_  __/
-                        / __/ / / / /_/ / __ \/ __ \/ /
-                        / /_/ /_/ / _, _/ /_/ / /_/ / /
-                        \__/\____/_/ |_/_____/\____/_/  v{VERSION}
-            """.format(VERSION=version)
-    banner = color(banner, "red")
-
-    title = r"""
-                                    {banner}
-                    #######################################################
-                    #  TorBot - Dark Web OSINT Tool                       #
-                    #  GitHub : https://github.com/DedsecInside/TorBot    #
-                    #  Help : use -h for help text                        #
-                    #######################################################
-                                {license_msg}
-            """
-
-    title = title.format(license_msg=license_msg, banner=banner)
-    print(title)
-
-
-def run(arg_parser: argparse.ArgumentParser, version: str) -> None:
-    args = arg_parser.parse_args()
-
-    # setup logging
-    date_fmt = "%d-%b-%y %H:%M:%S"
-    logging_fmt = "%(asctime)s - %(levelname)s - %(message)s"
-    logging_lvl = logging.DEBUG if args.v else logging.INFO
-    logging.basicConfig(level=logging_lvl, format=logging_fmt, datefmt=date_fmt)
-
-    # Print verison then exit
-    if args.version:
-        print(f"TorBot Version: {version}")
-        sys.exit()
-
-    # check version and update if necessary
-    if args.update:
-        check_version()
-        sys.exit()
-
-    # URL is required for crawl-related actions
-    if not args.url:
-        arg_parser.print_help()
-        sys.exit()
-
-    socks5_host = args.host
-    socks5_port = str(args.port)
-    socks5_proxy = f"socks5://{socks5_host}:{socks5_port}"
-    with httpx.Client(
-        timeout=60, proxies=socks5_proxy if not args.disable_socks5 else None
-    ) as client:
-        # print header and IP address if not set to quiet
-        if not args.quiet:
-            print_header(version)
-            print_tor_ip_address(client)
-
-        if args.info:
-            execute_all(client, args.url)
-
-        tree = LinkTree(url=args.url, depth=args.depth, client=client)
-        tree.load()
-
-        # save data if desired
-        if args.save == "tree":
-            tree.save()
-        elif args.save == "json":
-            tree.saveJSON()
-
-        if args.html == "display":
-            fetch_html(client, args.url, tree)
-        elif args.html == "save":
-            fetch_html(client, args.url, tree, save_html=True)
-
-        # always print something, table is the default
-        if args.visualize == "table" or not args.visualize:
-            tree.showTable()
-        elif args.visualize == "tree":
-            print(tree)
-        elif args.visualize == "json":
-            tree.showJSON()
-
-    print("\n\n")
-
-
-def set_arguments() -> argparse.ArgumentParser:
-    """
-    Parses user flags passed to TorBot
-    """
-    parser = argparse.ArgumentParser(
-        prog="TorBot", usage="Gather and analayze data from Tor sites."
-    )
-    parser.add_argument(
-        "-u",
-        "--url",
-        type=str,
-        default=None,
-        help="Specifiy a website link to crawl",
-    )
-    parser.add_argument(
-        "--depth", type=int, help="Specifiy max depth of crawler (default 1)", default=1
-    )
-    parser.add_argument(
-        "--host", type=str, help="IP address for SOCKS5 proxy", default="127.0.0.1"
-    )
-    parser.add_argument("--port", type=int, help="Port for SOCKS5 proxy", default=9050)
-    parser.add_argument(
-        "--save", type=str, choices=["tree", "json"], help="Save results in a file"
-    )
-    parser.add_argument(
-        "--visualize",
-        type=str,
-        choices=["table", "tree", "json"],
-        help="Visualizes data collection.",
-    )
-    parser.add_argument("-q", "--quiet", action="store_true")
-    parser.add_argument(
-        "--version", action="store_true", help="Show current version of TorBot."
-    )
-    parser.add_argument(
-        "--update",
-        action="store_true",
-        help="Update TorBot to the latest stable version",
-    )
-    parser.add_argument(
-        "--info",
-        action="store_true",
-        help="Info displays basic info of the scanned site. Only supports a single URL at a time.",
-    )
-    parser.add_argument("-v", action="store_true", help="verbose logging")
-    parser.add_argument(
-        "--disable-socks5",
-        action="store_true",
-        help="Executes HTTP requests without using SOCKS5 proxy",
-    )
-    parser.add_argument(
-        "--html",
-        choices=["save", "display"],
-        help="Saves / Displays the html of the onion link",
-    )
-
-    return parser
+__all__ = ["get_version", "main", "run", "set_arguments"]
 
 
 if __name__ == "__main__":
     try:
-        arg_parser = set_arguments()
-        config_file_path = os.path.join(
-            os.path.dirname(os.path.realpath(__file__)), "pyproject.toml"
-        )
-        try:
-            with open(config_file_path, "r") as f:
-                data = toml.load(f)
-                version = data["project"]["version"]
-        except Exception as e:
-            raise Exception("unable to find version from pyproject.toml.\n", e)
-
-        run(arg_parser, version)
+        main()
     except KeyboardInterrupt:
         print("Interrupt received! Exiting cleanly...")
diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "torbot"
-version = "4.1.1"
+version = "4.3.0"
 authors = [
     { name="Akeem King", email="akeemtlking@gmail.com" },
     { name="PS Narayanan", email="thepsnarayanan@gmail.com" },
@@ -38,7 +38,6 @@ dependencies = [
   "scikit-learn>=1.5.0",
   "scipy>=1.13.0",
   "six>=1.16.0",
-  "sklearn>=0.0",
   "soupsieve>=2.8.4",
   "termcolor>=2.4.0",
   "texttable>=1.7.0",

diff --git a/requirements.txt b/requirements.txt
@@ -5,8 +5,8 @@ certifi==2024.7.4
 charset-normalizer==3.3.2
 colorama==0.4.6 ; sys_platform == "win32"
 decorator==5.1.1
-h11==0.14.0
-httpcore==1.0.5
+h11==0.16.0
+httpcore==1.0.9
 httpx[socks]==0.27.0
 idna==3.15
 igraph==0.11.4
@@ -27,9 +27,8 @@ python-dotenv==1.2.2
 pywin32-ctypes==0.2.2 ; sys_platform == "win32"
 scikit-learn==1.5.0
 scipy==1.13.0
-setuptools==78.1.1
+setuptools==83.0.0
 six==1.16.0
-sklearn==0.0
 sniffio==1.3.1
 socksio==1.0.0
 soupsieve==2.8.4