chore: update code comments and add pre-commit

.flake8

@@ -0,0 +1,3 @@
+[flake8]
+ignore = E501, E203
+max-line-length = 200

.pre-commit-config.yaml

@@ -0,0 +1,48 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+    - repo: https://github.com/PyCQA/isort
+      rev: 5.13.2
+      hooks:
+          - id: isort
+            args: [--profile, black]
+
+    # Using this mirror lets us use mypyc-compiled black, which is about 2x faster
+    - repo: https://github.com/psf/black-pre-commit-mirror
+      rev: 24.4.2
+      hooks:
+          - id:
+                black
+                # It is recommended to specify the latest version of Python
+                # supported by your project here, or alternatively use
+                # pre-commit's default_language_version, see
+                # https://pre-commit.com/#top_level-default_language_version
+            language_version: python3.12
+            args: ["--line-length", "200", "--exclude", "migrations/"]
+
+    -   repo: https://github.com/astral-sh/ruff-pre-commit
+        rev: v0.0.285
+        hooks:
+        -   id: ruff
+            alias: autoformat
+            args: [--fix]
+
+    - repo: https://github.com/pycqa/flake8
+      rev: 7.1.0
+      hooks:
+          - id: flake8
+            exclude: ^tests/(data|examples)/
+
+    - repo: https://github.com/pre-commit/mirrors-mypy
+      rev: v1.10.1
+      hooks:
+          - id: mypy
+            args: [--ignore-missing-imports, --no-namespace-packages]
+
+    - repo: https://github.com/pre-commit/pre-commit-hooks
+      rev: v3.2.0
+      hooks:
+          - id: trailing-whitespace
+          - id: end-of-file-fixer
+          - id: check-yaml
+          - id: check-added-large-files

.ruff.toml

@@ -0,0 +1,32 @@
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".ipynb_checkpoints",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pyenv",
+    ".pytest_cache",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    ".vscode",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "site-packages",
+    "venv",
+]
+
+line-length = 200
+target-version = "py312"

src/configs.py

@@ -75,9 +75,13 @@ LANGUAGES = [
 
 # regex, have_many_results, result_too_lang
 REGEX_LIST = [
-    (re.compile(r"sk-proj-[A-Za-z0-9-_]{74}T3BlbkFJ[A-Za-z0-9-_]{73}A"), True, True),  # Named Project API Key (no matter normal or restricted)
+    # Named Project API Key (no matter normal or restricted) still valid until Dec 2, 2024
-    (re.compile(r"sk-proj-[A-Za-z0-9-_]{58}T3BlbkFJ[A-Za-z0-9-_]{58}"), True, True),  # Old Project API Key
+    (re.compile(r"sk-proj-[A-Za-z0-9-_]{74}T3BlbkFJ[A-Za-z0-9-_]{73}A"), True, True),
-    (re.compile(r"sk-svcacct-[A-Za-z0-9-_]+T3BlbkFJ[A-Za-z0-9-_]+"), False, False),  # Service Account Key
+    # Old Project API Key
+    (re.compile(r"sk-proj-[A-Za-z0-9-_]{58}T3BlbkFJ[A-Za-z0-9-_]{58}"), True, True),
+    # Service Account Key
+    (re.compile(r"sk-svcacct-[A-Za-z0-9-_]+T3BlbkFJ[A-Za-z0-9-_]+"), False, False),
     (re.compile(r"sk-proj-[A-Za-z0-9]{20}T3BlbkFJ[A-Za-z0-9]{20}"), True, False),
-    (re.compile(r"sk-[a-zA-Z0-9]{48}"), True, False),  # Deprecated by OpenAI
+    # Old key format (deprecated by OpenAI)
+    (re.compile(r"sk-[a-zA-Z0-9]{48}"), True, False),
 ]

src/manager.py

@@ -1,16 +1,20 @@
 """
-This module is used to manage the progress and the cookies.
+Progress and Cookie Management Module
 
-It includes the following classes:
+This module provides functionality for managing application progress, cookies,
-- ProgressManager: to manage the progress
+and database operations.
-- CookieManager: to manage the cookies
+
-- DatabaseManager: to manage the database
+Classes:
+    ProgressManager: Handles progress tracking and persistence
+    CookieManager: Manages browser cookie operations
+    DatabaseManager: Handles database interactions
 """
+
 import logging
 import os
-import sys
 import pickle
 import sqlite3
+import sys
 import time
 from datetime import date
 from sqlite3 import Connection, Cursor
@@ -18,12 +22,31 @@ from sqlite3 import Connection, Cursor
 from selenium.common.exceptions import UnableToSetCookieException
 from selenium.webdriver.common.by import By
 
-FORMAT = "%(message)s"
+LOGGER_NAME = "ChatGPT-API-Leakage"
-logging.basicConfig(level=logging.INFO, format=FORMAT, datefmt="[%X]")
+LOG_FORMAT = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-log = logging.getLogger("ChatGPT-API-Leakage")
+logging.basicConfig(level=logging.INFO, format=LOG_FORMAT, datefmt="[%X]")
+logger = logging.getLogger(LOGGER_NAME)
+
+
+class ProgressManagerError(Exception):
+    """Custom exception for ProgressManager class errors"""
+
+    def __init__(self, message):
+        super().__init__(message)
 
 
 class ProgressManager:
+    """
+    Manages and persists progress information for long-running operations.
+
+    Attributes:
+        progress_file (Path): Path to the progress file
+
+    Methods:
+        save: Saves current progress
+        load: Loads saved progress
+    """
+
     def __init__(self, progress_file=".progress.txt"):
         self.progress_file = progress_file
 
@@ -32,6 +55,23 @@ class ProgressManager:
             file.write(f"{from_iter}/{total}/{time.time()}")
 
     def load(self, total: int) -> int:
+        """
+        Loads the previously saved progress if available and valid.
+
+        Args:
+            total (int): The total number of iterations expected in the current process
+
+        Returns:
+            int: The iteration number to continue from:
+                - Returns the last saved iteration if:
+                    - Progress file exists
+                    - Last save was within last hour (3600 seconds)
+                    - Saved total matches current total
+                    - User confirms to continue
+                - Returns 0 otherwise (fresh start)
+
+        The progress file format is: "{last_iteration}/{total_iterations}/{timestamp}"
+        """
         if not os.path.exists(self.progress_file):
             return 0
 
@@ -55,7 +95,7 @@ class CookieManager:
         cookies = self.driver.get_cookies()
         with open("cookies.pkl", "wb") as file:
             pickle.dump(cookies, file)
-            log.info("🍪 Cookies saved")
+            logger.info("🍪 Cookies saved")
 
     def load(self):
         try:
@@ -65,23 +105,23 @@ class CookieManager:
                     try:
                         self.driver.add_cookie(cookie)
                     except UnableToSetCookieException:
-                        log.debug("🟡 Warning, unable to set a cookie %s", cookie)
+                        logger.debug("🟡 Warning, unable to set a cookie %s", cookie)
         except (EOFError, pickle.UnpicklingError):
             if os.path.exists("cookies.pkl"):
                 os.remove("cookies.pkl")
-            log.error("🔴 Error, unable to load cookies, invalid cookies has been removed, please restart.")
+            logger.error("🔴 Error, unable to load cookies, invalid cookies has been removed, please restart.")
 
     def verify_user_login(self):
         """
         Test if the user is really logged in
         """
-        log.info("🤗 Redirecting ...")
+        logger.info("🤗 Redirecting ...")
         self.driver.get("https://github.com/")
 
         if self.driver.find_elements(by=By.XPATH, value="//*[contains(text(), 'Sign in')]"):
             if os.path.exists("cookies.pkl"):
                 os.remove("cookies.pkl")
-            log.error("🔴 Error, you are not logged in, please restart and try again.")
+            logger.error("🔴 Error, you are not logged in, please restart and try again.")
             sys.exit(1)
         return True
 
@@ -90,6 +130,7 @@ class DatabaseManager:
     """
     This class is used to manage the database.
     """
+
     def __init__(self, db_filename: str):
         self.db_filename = db_filename
         self.con: Connection | None = None
@@ -113,7 +154,6 @@ class DatabaseManager:
         if self.con:
             self.con.close()
 
-
     def all_keys(self) -> list:
         if self.cur is None:
             raise ValueError("Cursor is not initialized")