2024-05-09 19:10:25 +08:00
|
|
|
from setuptools import setup, find_packages
|
2024-05-17 22:11:00 +08:00
|
|
|
import os
|
2024-06-19 18:32:20 +08:00
|
|
|
from pathlib import Path
|
2024-05-17 22:11:00 +08:00
|
|
|
import subprocess
|
|
|
|
from setuptools.command.install import install
|
2024-05-09 19:10:25 +08:00
|
|
|
|
2024-06-19 18:32:20 +08:00
|
|
|
# Create the .crawl4ai folder in the user's home directory if it doesn't exist
|
|
|
|
crawl4ai_folder = os.path.join(Path.home(), ".crawl4ai")
|
|
|
|
os.makedirs(crawl4ai_folder, exist_ok=True)
|
|
|
|
os.makedirs(f"{crawl4ai_folder}/cache", exist_ok=True)
|
|
|
|
|
2024-05-17 15:21:45 +08:00
|
|
|
# Read the requirements from requirements.txt
|
|
|
|
with open("requirements.txt") as f:
|
|
|
|
requirements = f.read().splitlines()
|
2024-05-17 15:52:39 +08:00
|
|
|
|
|
|
|
# Define the requirements for different environments
|
2024-06-30 00:15:29 +08:00
|
|
|
default_requirements = [req for req in requirements if not req.startswith(("torch", "transformers", "onnxruntime", "nltk", "spacy", "tokenizers", "scikit-learn", "numpy"))]
|
|
|
|
torch_requirements = [req for req in requirements if req.startswith(("torch", "nltk", "spacy", "scikit-learn", "numpy"))]
|
|
|
|
transformer_requirements = [req for req in requirements if req.startswith(("transformers", "tokenizers", "onnxruntime"))]
|
2024-05-17 15:52:39 +08:00
|
|
|
|
2024-05-09 19:10:25 +08:00
|
|
|
setup(
|
|
|
|
name="Crawl4AI",
|
2024-07-03 15:19:22 +08:00
|
|
|
version="0.2.73",
|
2024-05-09 19:10:25 +08:00
|
|
|
description="🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper",
|
|
|
|
long_description=open("README.md").read(),
|
|
|
|
long_description_content_type="text/markdown",
|
|
|
|
url="https://github.com/unclecode/crawl4ai",
|
|
|
|
author="Unclecode",
|
|
|
|
author_email="unclecode@kidocode.com",
|
|
|
|
license="MIT",
|
|
|
|
packages=find_packages(),
|
2024-06-30 00:15:29 +08:00
|
|
|
install_requires=default_requirements,
|
2024-05-17 15:52:39 +08:00
|
|
|
extras_require={
|
2024-06-30 00:15:29 +08:00
|
|
|
"torch": torch_requirements,
|
|
|
|
"transformer": transformer_requirements,
|
|
|
|
"all": requirements,
|
2024-05-17 15:52:39 +08:00
|
|
|
},
|
2024-05-16 20:08:21 +08:00
|
|
|
entry_points={
|
|
|
|
'console_scripts': [
|
|
|
|
'crawl4ai-download-models=crawl4ai.model_loader:main',
|
|
|
|
],
|
|
|
|
},
|
2024-05-09 19:10:25 +08:00
|
|
|
classifiers=[
|
|
|
|
"Development Status :: 3 - Alpha",
|
|
|
|
"Intended Audience :: Developers",
|
|
|
|
"License :: OSI Approved :: Apache Software License",
|
|
|
|
"Programming Language :: Python :: 3",
|
|
|
|
"Programming Language :: Python :: 3.7",
|
|
|
|
"Programming Language :: Python :: 3.8",
|
|
|
|
"Programming Language :: Python :: 3.9",
|
|
|
|
"Programming Language :: Python :: 3.10",
|
|
|
|
],
|
|
|
|
python_requires=">=3.7",
|
2024-06-30 00:15:29 +08:00
|
|
|
)
|