perf: General code restructure to not use more than needed memory

scrapling/cli.py

@@ -2,8 +2,9 @@ from pathlib import Path
 from subprocess import check_output
 from sys import executable as python_executable
 
+from scrapling.core.utils import log
 from scrapling.engines.toolbelt.custom import Response
-from scrapling.core.utils import log, _CookieParser, _ParseHeaders
+from scrapling.core.utils._shell import _CookieParser, _ParseHeaders
 from scrapling.core._types import List, Optional, Dict, Tuple, Any, Callable
 
 from orjson import loads as json_loads, JSONDecodeError

scrapling/core/shell.py

@@ -22,10 +22,11 @@ from logging import (
 from orjson import loads as json_loads, JSONDecodeError
 
 from scrapling import __version__
+from scrapling.core.utils import log
 from scrapling.parser import Selector, Selectors
 from scrapling.core.custom_types import TextHandler
 from scrapling.engines.toolbelt.custom import Response
-from scrapling.core.utils import log, _ParseHeaders, _CookieParser
+from scrapling.core.utils._shell import _ParseHeaders, _CookieParser
 from scrapling.core._types import (
     Optional,
     Dict,

scrapling/core/storage.py

@@ -6,7 +6,6 @@ from sqlite3 import connect as db_connect
 
 from orjson import dumps, loads
 from lxml.html import HtmlElement
-from tldextract import extract as tld
 
 from scrapling.core.utils import _StorageTools, log
 from scrapling.core._types import Dict, Optional, Any
@@ -26,6 +25,8 @@ class StorageSystemMixin(ABC):  # pragma: no cover
             return default_value
 
         try:
+            from tldextract import extract as tld
+
             extracted = tld(self.url)
             return extracted.top_domain_under_public_suffix or extracted.domain or default_value
         except AttributeError:

scrapling/core/utils/__init__.py

@@ -7,4 +7,3 @@ from ._utils import (
     clean_spaces,
     html_forbidden,
 )
-from ._shell import _CookieParser, _ParseHeaders

scrapling/parser.py

@@ -1,8 +1,8 @@
-import re
 from pathlib import Path
 from inspect import signature
 from urllib.parse import urljoin
 from difflib import SequenceMatcher
+from re import Pattern as re_Pattern
 
 from lxml.html import HtmlElement, HtmlMixin, HTMLParser
 from cssselect import SelectorError, SelectorSyntaxError, parse as split_selectors
@@ -751,7 +751,7 @@ class Selector(SelectorsGeneration):
                     )
                 attributes.update(arg)
 
-            elif isinstance(arg, re.Pattern):
+            elif isinstance(arg, re_Pattern):
                 patterns.add(arg)
 
             elif callable(arg):