Merge pull request #43 from D4Vinci/dev

v0.2.96

README.md

@@ -1,4 +1,4 @@
-# 🕷️ Scrapling: Undetectable, Lightning-Fast, and Adaptive Web Scraping for Python
+# 🕷️ Scrapling: Undetectable, Lightning-Fast, and Easy Web Scraping with Python
 [![Tests](https://github.com/D4Vinci/Scrapling/actions/workflows/tests.yml/badge.svg)](https://github.com/D4Vinci/Scrapling/actions/workflows/tests.yml) [![PyPI version](https://badge.fury.io/py/Scrapling.svg)](https://badge.fury.io/py/Scrapling) [![Supported Python versions](https://img.shields.io/pypi/pyversions/scrapling.svg)](https://pypi.org/project/scrapling/) [![PyPI Downloads](https://static.pepy.tech/badge/scrapling)](https://pepy.tech/project/scrapling)
 
 Dealing with failing web scrapers due to anti-bot protections or website changes? Meet Scrapling.

scrapling/__init__.py

@@ -5,7 +5,7 @@ from scrapling.fetchers import (AsyncFetcher, CustomFetcher, Fetcher,
 from scrapling.parser import Adaptor, Adaptors
 
 __author__ = "Karim Shoair (karim.shoair@pm.me)"
-__version__ = "0.2.95"
+__version__ = "0.2.96"
 __copyright__ = "Copyright (c) 2024 Karim Shoair"
 
 

scrapling/cli.py

@@ -12,13 +12,14 @@ def get_package_dir():
 
 def run_command(command, line):
     print(f"Installing {line}...")
-    _ = subprocess.check_call(command, shell=True)
+    _ = subprocess.check_call(' '.join(command), shell=True)
     # I meant to not use try except here
 
 
 @click.command(help="Install all Scrapling's Fetchers dependencies")
-def install():
-    if not get_package_dir().joinpath(".scrapling_dependencies_installed").exists():
+@click.option('-f', '--force', 'force', is_flag=True, default=False, type=bool, help="Force Scrapling to reinstall all Fetchers dependencies")
+def install(force):
+    if force or not get_package_dir().joinpath(".scrapling_dependencies_installed").exists():
         run_command([sys.executable, "-m", "playwright", "install", 'chromium'], 'Playwright browsers')
         run_command([sys.executable, "-m", "playwright", "install-deps", 'chromium', 'firefox'], 'Playwright dependencies')
         run_command([sys.executable, "-m", "camoufox", "fetch", '--browserforge'], 'Camoufox browser and databases')

scrapling/core/custom_types.py

@@ -23,19 +23,8 @@ class TextHandler(str):
             return super().__new__(cls, string)
         return super().__new__(cls, '')
 
-    @typing.overload
-    def __getitem__(self, key: SupportsIndex) -> 'TextHandler':
-        pass
-
-    @typing.overload
-    def __getitem__(self, key: slice) -> "TextHandlers":
-        pass
-
-    def __getitem__(self, key: Union[SupportsIndex, slice]) -> Union["TextHandler", "TextHandlers"]:
+    def __getitem__(self, key: Union[SupportsIndex, slice]) -> "TextHandler":
         lst = super().__getitem__(key)
-        if isinstance(key, slice):
-            lst = [TextHandler(s) for s in lst]
-            return TextHandlers(typing.cast(List[_TextHandlerType], lst))
         return typing.cast(_TextHandlerType, TextHandler(lst))
 
     def split(self, sep: str = None, maxsplit: SupportsIndex = -1) -> 'TextHandlers':

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = scrapling
-version = 0.2.95
+version = 0.2.96
 author = Karim Shoair
 author_email = karim.shoair@pm.me
 description = Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy again!

setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setup(
     name="scrapling",
-    version="0.2.95",
+    version="0.2.96",
     description="""Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy again! In an internet filled with complications,
     it simplifies web scraping, even when websites' design changes, while providing impressive speed that surpasses almost all alternatives.""",
     long_description=long_description,