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/engines/camo.py

@@ -1,10 +1,9 @@
-import logging
-
 from camoufox import DefaultAddons
 from camoufox.sync_api import Camoufox
 
 from scrapling.core._types import (Callable, Dict, List, Literal, Optional,
                                    Union)
+from scrapling.core.utils import log
 from scrapling.engines.toolbelt import (Response, StatusText,
                                         check_type_validity,
                                         construct_proxy_dict, do_nothing,
@@ -63,7 +62,7 @@ class CamoufoxEngine:
             self.page_action = page_action
         else:
             self.page_action = do_nothing
-            logging.error('[Ignored] Argument "page_action" must be callable')
+            log.error('[Ignored] Argument "page_action" must be callable')
 
         self.wait_selector = wait_selector
         self.wait_selector_state = wait_selector_state

scrapling/engines/pw.py

@@ -1,7 +1,7 @@
 import json
-import logging
 
 from scrapling.core._types import Callable, Dict, List, Optional, Union
+from scrapling.core.utils import log
 from scrapling.engines.constants import (DEFAULT_STEALTH_FLAGS,
                                          NSTBROWSER_DEFAULT_QUERY)
 from scrapling.engines.toolbelt import (Response, StatusText,
@@ -78,7 +78,7 @@ class PlaywrightEngine:
             self.page_action = page_action
         else:
             self.page_action = do_nothing
-            logging.error('[Ignored] Argument "page_action" must be callable')
+            log.error('[Ignored] Argument "page_action" must be callable')
 
         self.wait_selector = wait_selector
         self.wait_selector_state = wait_selector_state

scrapling/engines/static.py

@@ -1,5 +1,3 @@
-import logging
-
 import httpx
 from httpx._models import Response as httpxResponse
 
@@ -36,7 +34,6 @@ class StaticEngine:
         # Validate headers
         if not headers.get('user-agent') and not headers.get('User-Agent'):
             headers['User-Agent'] = generate_headers(browser_mode=False).get('User-Agent')
-            logging.info(f"Can't find useragent in headers so '{headers['User-Agent']}' was used.")
 
         if stealth:
             extra_headers = generate_headers(browser_mode=False)

scrapling/engines/toolbelt/custom.py

@@ -2,13 +2,12 @@
 Functions related to custom types or type checking
 """
 import inspect
-import logging
 from email.message import Message
 
 from scrapling.core._types import (Any, Callable, Dict, List, Optional, Tuple,
                                    Type, Union)
 from scrapling.core.custom_types import MappingProxyType
-from scrapling.core.utils import cache, setup_basic_logging
+from scrapling.core.utils import log, lru_cache
 from scrapling.parser import Adaptor, SQLiteStorageSystem
 
 
@@ -17,7 +16,7 @@ class ResponseEncoding:
     __ISO_8859_1_CONTENT_TYPES = {"text/plain", "text/html", "text/css", "text/javascript"}
 
     @classmethod
-    @cache(maxsize=None)
+    @lru_cache(maxsize=None)
     def __parse_content_type(cls, header_value: str) -> Tuple[str, Dict[str, str]]:
         """Parse content type and parameters from a content-type header value.
 
@@ -39,7 +38,7 @@ class ResponseEncoding:
         return content_type, params
 
     @classmethod
-    @cache(maxsize=None)
+    @lru_cache(maxsize=None)
     def get_value(cls, content_type: Optional[str], text: Optional[str] = 'test') -> str:
         """Determine the appropriate character encoding from a content-type header.
 
@@ -98,7 +97,7 @@ class Response(Adaptor):
         # For back-ward compatibility
         self.adaptor = self
         # For easier debugging while working from a Python shell
-        logging.info(f'Fetched ({status}) <{method} {url}> (referer: {request_headers.get("referer")})')
+        log.info(f'Fetched ({status}) <{method} {url}> (referer: {request_headers.get("referer")})')
 
     # def __repr__(self):
     #     return f'<{self.__class__.__name__} [{self.status} {self.reason}]>'
@@ -107,7 +106,7 @@ class Response(Adaptor):
 class BaseFetcher:
     def __init__(
             self, huge_tree: bool = True, keep_comments: Optional[bool] = False, auto_match: Optional[bool] = True,
-            storage: Any = SQLiteStorageSystem, storage_args: Optional[Dict] = None, debug: Optional[bool] = False,
+            storage: Any = SQLiteStorageSystem, storage_args: Optional[Dict] = None,
             automatch_domain: Optional[str] = None, keep_cdata: Optional[bool] = False,
     ):
         """Arguments below are the same from the Adaptor class so you can pass them directly, the rest of Adaptor's arguments
@@ -124,7 +123,6 @@ class BaseFetcher:
             If empty, default values will be used.
         :param automatch_domain: For cases where you want to automatch selectors across different websites as if they were on the same website, use this argument to unify them.
             Otherwise, the domain of the request is used by default.
-        :param debug: Enable debug mode
         """
         # Adaptor class parameters
         # I won't validate Adaptor's class parameters here again, I will leave it to be validated later
@@ -134,14 +132,11 @@ class BaseFetcher:
             keep_cdata=keep_cdata,
             auto_match=auto_match,
             storage=storage,
-            storage_args=storage_args,
-            debug=debug,
+            storage_args=storage_args
         )
-        # If the user used fetchers first, then configure the logger from here instead of the `Adaptor` class
-        setup_basic_logging(level='debug' if debug else 'info')
         if automatch_domain:
             if type(automatch_domain) is not str:
-                logging.warning('[Ignored] The argument "automatch_domain" must be of string type')
+                log.warning('[Ignored] The argument "automatch_domain" must be of string type')
             else:
                 self.adaptor_arguments.update({'automatch_domain': automatch_domain})
 
@@ -217,7 +212,7 @@ class StatusText:
     })
 
     @classmethod
-    @cache(maxsize=128)
+    @lru_cache(maxsize=128)
     def get(cls, status_code: int) -> str:
         """Get the phrase for a given HTTP status code."""
         return cls._phrases.get(status_code, "Unknown Status Code")
@@ -284,7 +279,7 @@ def check_type_validity(variable: Any, valid_types: Union[List[Type], None], def
         error_msg = f'Argument "{var_name}" cannot be None'
         if critical:
             raise TypeError(error_msg)
-        logging.error(f'[Ignored] {error_msg}')
+        log.error(f'[Ignored] {error_msg}')
         return default_value
 
     # If no valid_types specified and variable has a value, return it
@@ -297,7 +292,7 @@ def check_type_validity(variable: Any, valid_types: Union[List[Type], None], def
         error_msg = f'Argument "{var_name}" must be of type {" or ".join(type_names)}'
         if critical:
             raise TypeError(error_msg)
-        logging.error(f'[Ignored] {error_msg}')
+        log.error(f'[Ignored] {error_msg}')
         return default_value
 
     return variable

scrapling/engines/toolbelt/fingerprints.py

@@ -9,10 +9,10 @@ from browserforge.headers import Browser, HeaderGenerator
 from tldextract import extract
 
 from scrapling.core._types import Dict, Union
-from scrapling.core.utils import cache
+from scrapling.core.utils import lru_cache
 
 
-@cache(None, typed=True)
+@lru_cache(None, typed=True)
 def generate_convincing_referer(url: str) -> str:
     """Takes the domain from the URL without the subdomain/suffix and make it look like you were searching google for this website
 
@@ -26,7 +26,7 @@ def generate_convincing_referer(url: str) -> str:
     return f'https://www.google.com/search?q={website_name}'
 
 
-@cache(None, typed=True)
+@lru_cache(None, typed=True)
 def get_os_name() -> Union[str, None]:
     """Get the current OS name in the same format needed for browserforge
 

scrapling/engines/toolbelt/navigation.py

@@ -1,15 +1,13 @@
 """
 Functions related to files and URLs
 """
-
-import logging
 import os
 from urllib.parse import urlencode, urlparse
 
 from playwright.sync_api import Route
 
 from scrapling.core._types import Dict, Optional, Union
-from scrapling.core.utils import cache
+from scrapling.core.utils import log, lru_cache
 from scrapling.engines.constants import DEFAULT_DISABLED_RESOURCES
 
 
@@ -20,7 +18,7 @@ def intercept_route(route: Route) -> Union[Route, None]:
     :return: PlayWright `Route` object
     """
     if route.request.resource_type in DEFAULT_DISABLED_RESOURCES:
-        logging.debug(f'Blocking background resource "{route.request.url}" of type "{route.request.resource_type}"')
+        log.debug(f'Blocking background resource "{route.request.url}" of type "{route.request.resource_type}"')
         return route.abort()
     return route.continue_()
 
@@ -97,7 +95,7 @@ def construct_cdp_url(cdp_url: str, query_params: Optional[Dict] = None) -> str:
         raise ValueError(f"Invalid CDP URL: {str(e)}")
 
 
-@cache(None, typed=True)
+@lru_cache(None, typed=True)
 def js_bypass_path(filename: str) -> str:
     """Takes the base filename of JS file inside the `bypasses` folder then return the full path of it