2020-07-23 00:25:35 +08:00
|
|
|
from setuptools import setup, find_packages
|
2020-07-22 20:12:37 +08:00
|
|
|
import re
|
|
|
|
|
2020-07-23 00:25:35 +08:00
|
|
|
from wikiextractor.WikiExtractor import version
|
2020-07-22 20:12:37 +08:00
|
|
|
|
|
|
|
|
2020-07-23 00:25:35 +08:00
|
|
|
def get_version(version):
|
2020-07-22 20:12:37 +08:00
|
|
|
if re.match(r'^\d+\.\d+$', version):
|
|
|
|
return version + '.0'
|
|
|
|
return version
|
|
|
|
|
2020-07-23 00:25:35 +08:00
|
|
|
with open("README.md", "r") as fh:
|
|
|
|
long_description = fh.read()
|
|
|
|
|
2020-07-22 20:12:37 +08:00
|
|
|
setup(
|
|
|
|
name='wikiextractor',
|
2020-07-23 00:25:35 +08:00
|
|
|
version=get_version(version),
|
|
|
|
author='Giuseppe Attardi',
|
|
|
|
author_email='attardi@gmail.com',
|
2020-07-22 20:12:37 +08:00
|
|
|
description='A tool for extracting plain text from Wikipedia dumps',
|
2020-07-23 00:25:35 +08:00
|
|
|
long_description=long_description,
|
|
|
|
long_description_content_type="text/markdown",
|
|
|
|
license='GNU Affero General Public License',
|
|
|
|
install_requires=[],
|
|
|
|
url="https://github.com/attardi/wikiextractor",
|
|
|
|
packages=find_packages(include=["wikiextractor"]),
|
|
|
|
classifiers=[
|
|
|
|
'Development Status :: 5 - Production/Stable',
|
|
|
|
'Intended Audience :: Developers',
|
|
|
|
'Topic :: Text Processing :: Linguistic',
|
|
|
|
'License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)',
|
|
|
|
'Programming Language :: Python :: 3'
|
|
|
|
],
|
|
|
|
entry_points={
|
|
|
|
"console_scripts": [
|
|
|
|
"wikiextractor = wikiextractor.Wikiextractor:main",
|
|
|
|
"extractPage = wikiextractor.extractPage:main",
|
|
|
|
]
|
|
|
|
},
|
|
|
|
python_requires='>=3.6',
|
2020-07-22 20:12:37 +08:00
|
|
|
)
|