refactor(api)!: Unifying log under 1 logger and removing debug parameter

So now you control the logging and the debugging from the shell through the logger with the name 'scrapling'

scrapling/core/storage_adaptors.py

@@ -1,4 +1,3 @@
-import logging
 import sqlite3
 import threading
 from abc import ABC, abstractmethod
@@ -9,7 +8,7 @@ from lxml import html
 from tldextract import extract as tld
 
 from scrapling.core._types import Dict, Optional, Union
-from scrapling.core.utils import _StorageTools, cache
+from scrapling.core.utils import _StorageTools, log, lru_cache
 
 
 class StorageSystemMixin(ABC):
@@ -20,7 +19,7 @@ class StorageSystemMixin(ABC):
         """
         self.url = url
 
-    @cache(None, typed=True)
+    @lru_cache(None, typed=True)
     def _get_base_url(self, default_value: str = 'default') -> str:
         if not self.url or type(self.url) is not str:
             return default_value
@@ -52,7 +51,7 @@ class StorageSystemMixin(ABC):
         raise NotImplementedError('Storage system must implement `save` method')
 
     @staticmethod
-    @cache(None, typed=True)
+    @lru_cache(None, typed=True)
     def _get_hash(identifier: str) -> str:
         """If you want to hash identifier in your storage system, use this safer"""
         identifier = identifier.lower().strip()
@@ -64,7 +63,7 @@ class StorageSystemMixin(ABC):
         return f"{hash_value}_{len(identifier)}"  # Length to reduce collision chance
 
 
-@cache(None, typed=True)
+@lru_cache(None, typed=True)
 class SQLiteStorageSystem(StorageSystemMixin):
     """The recommended system to use, it's race condition safe and thread safe.
     Mainly built so the library can run in threaded frameworks like scrapy or threaded tools
@@ -86,7 +85,7 @@ class SQLiteStorageSystem(StorageSystemMixin):
         self.connection.execute("PRAGMA journal_mode=WAL")
         self.cursor = self.connection.cursor()
         self._setup_database()
-        logging.debug(
+        log.debug(
             f'Storage system loaded with arguments (storage_file="{storage_file}", url="{url}")'
         )
 

scrapling/core/translator.py

@@ -17,7 +17,7 @@ from cssselect.xpath import XPathExpr as OriginalXPathExpr
 from w3lib.html import HTML5_WHITESPACE
 
 from scrapling.core._types import Any, Optional, Protocol, Self
-from scrapling.core.utils import cache
+from scrapling.core.utils import lru_cache
 
 regex = f"[{HTML5_WHITESPACE}]+"
 replace_html5_whitespaces = re.compile(regex).sub
@@ -139,6 +139,6 @@ class TranslatorMixin:
 
 
 class HTMLTranslator(TranslatorMixin, OriginalHTMLTranslator):
-    @cache(maxsize=256)
+    @lru_cache(maxsize=256)
     def css_to_xpath(self, css: str, prefix: str = "descendant-or-self::") -> str:
         return super().css_to_xpath(css, prefix)

scrapling/core/utils.py

@@ -9,18 +9,36 @@ from scrapling.core._types import Any, Dict, Iterable, Union
 
 # Using cache on top of a class is brilliant way to achieve Singleton design pattern without much code
 # functools.cache is available on Python 3.9+ only so let's keep lru_cache
-from functools import lru_cache as cache  # isort:skip
-
+from functools import lru_cache  # isort:skip
 
 html_forbidden = {html.HtmlComment, }
-logging.basicConfig(
-    level=logging.INFO,
-    format="[%(asctime)s] %(levelname)s: %(message)s",
-    datefmt="%Y-%m-%d %H:%M:%S",
-    handlers=[
-        logging.StreamHandler()
-    ]
-)
+
+
+@lru_cache(1, typed=True)
+def setup_logger():
+    """Create and configure a logger with a standard format.
+
+    :returns: logging.Logger: Configured logger instance
+    """
+    logger = logging.getLogger('scrapling')
+    logger.setLevel(logging.INFO)
+
+    formatter = logging.Formatter(
+        fmt="[%(asctime)s] %(levelname)s: %(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S"
+    )
+
+    console_handler = logging.StreamHandler()
+    console_handler.setFormatter(formatter)
+
+    # Add handler to logger (if not already added)
+    if not logger.handlers:
+        logger.addHandler(console_handler)
+
+    return logger
+
+
+log = setup_logger()
 
 
 def is_jsonable(content: Union[bytes, str]) -> bool:
@@ -34,23 +52,6 @@ def is_jsonable(content: Union[bytes, str]) -> bool:
         return False
 
 
-@cache(None, typed=True)
-def setup_basic_logging(level: str = 'debug'):
-    levels = {
-        'debug': logging.DEBUG,
-        'info': logging.INFO,
-        'warning': logging.WARNING,
-        'error': logging.ERROR,
-        'critical': logging.CRITICAL
-    }
-    formatter = logging.Formatter("[%(asctime)s] %(levelname)s: %(message)s", "%Y-%m-%d %H:%M:%S")
-    lvl = levels[level.lower()]
-    handler = logging.StreamHandler()
-    handler.setFormatter(formatter)
-    # Configure the root logger
-    logging.basicConfig(level=lvl, handlers=[handler])
-
-
 def flatten(lst: Iterable):
     return list(chain.from_iterable(lst))
 
@@ -114,7 +115,7 @@ class _StorageTools:
 #     return _impl
 
 
-@cache(None, typed=True)
+@lru_cache(None, typed=True)
 def clean_spaces(string):
     string = string.replace('\t', ' ')
     string = re.sub('[\n|\r]', '', string)