Merge branch 'dev' into fix/quoted-charset-encoding

scrapling/__init__.py

@@ -1,5 +1,5 @@
 __author__ = "Karim Shoair (karim.shoair@pm.me)"
-__version__ = "0.4.8"
+__version__ = "0.4.9"
 __copyright__ = "Copyright (c) 2024 Karim Shoair"
 
 from typing import Any, TYPE_CHECKING

scrapling/cli.py

@@ -2,6 +2,7 @@ from pathlib import Path
 from subprocess import check_output
 from sys import executable as python_executable
 
+from scrapling import __version__
 from scrapling.core.utils import log
 from scrapling.engines.toolbelt.custom import Response
 from scrapling.core.utils._shell import _CookieParser, _ParseHeaders
@@ -10,7 +11,7 @@ from scrapling.core._types import List, Optional, Dict, Tuple, Any, Callable
 from orjson import loads as json_loads, JSONDecodeError
 
 try:
-    from click import command, option, Choice, group, argument
+    from click import command, option, Choice, group, argument, version_option
 except (ImportError, ModuleNotFoundError) as e:
     raise ModuleNotFoundError(
         "You need to install scrapling with any of the extras to enable Shell commands. See: https://scrapling.readthedocs.io/en/latest/#installation"
@@ -650,6 +651,7 @@ def stealthy_fetch(
 
 
 @group()
+@version_option(version=__version__, prog_name="Scrapling")
 def main():
     pass
 

scrapling/engines/toolbelt/fingerprints.py

@@ -13,8 +13,8 @@ from scrapling.core._types import Dict, Literal, Tuple
 __OS_NAME__ = platform_system()
 OSName = Literal["linux", "macos", "windows"]
 # Current versions hardcoded for now (Playwright doesn't allow to know the version of a browser without launching it)
-chromium_version = 147
-chrome_version = 147
+chromium_version = 148
+chrome_version = 148
 
 
 @lru_cache(1, typed=True)

scrapling/parser.py

@@ -671,7 +671,7 @@ class Selector(SelectorsGeneration):
                     element_data = self.retrieve(identifier or selector)
                     if element_data:
                         elements = self.relocate(element_data, percentage)
-                        if elements is not None and auto_save:
+                        if elements and auto_save:
                             self.save(elements[0], identifier or selector)
 
                 return self.__handle_elements(elements)
@@ -991,7 +991,9 @@ class Selector(SelectorsGeneration):
                 SequenceMatcher(None, v, candidate_attributes.get(k, "")).ratio()
                 for k, v in original_attributes.items()
             )
-            checks += len(candidate_attributes)
+            # Using `max` so candidates with extra attributes are penalized and candidates
+            # with fewer attributes don't get inflated scores from a smaller denominator
+            checks += max(len(original_attributes), len(candidate_attributes))
         else:
             if not candidate_attributes:
                 # Both don't have attributes, this must mean something

scrapling/spiders/cache.py

@@ -64,7 +64,7 @@ class ResponseCacheManager:
             async with await anyio.open_file(temp_path, "wb") as f:
                 await f.write(serialized)
 
-            await temp_path.rename(self._cache_path(fingerprint))
+            await temp_path.replace(self._cache_path(fingerprint))
         except Exception as e:
             if await temp_path.exists():
                 await temp_path.unlink()

scrapling/spiders/checkpoint.py

@@ -50,7 +50,7 @@ class CheckpointManager:
             async with await anyio.open_file(temp_path, "wb") as f:
                 await f.write(serialized)
 
-            await temp_path.rename(self._checkpoint_path)
+            await temp_path.replace(self._checkpoint_path)
 
             log.info(f"Checkpoint saved: {len(data.requests)} requests, {len(data.seen)} seen URLs")
         except Exception as e: