Skip to content

Commit

Permalink
Merge pull request #273 from Medno/remove_newspaper3k_from_setup
Browse files Browse the repository at this point in the history
Remove newspaper3k from setup
  • Loading branch information
fhamborg authored Jul 8, 2024
2 parents 048a455 + fa83667 commit d79ae58
Showing 1 changed file with 63 additions and 65 deletions.
128 changes: 63 additions & 65 deletions setup.py
Original file line number Diff line number Diff line change
@@ -1,68 +1,66 @@
from setuptools import setup, find_packages

setup(name='news-please',
version='1.6.11',
description="news-please is an open source easy-to-use news extractor that just works.",
long_description="""\
setup(
name="news-please",
version="1.6.11",
description="news-please is an open source easy-to-use news extractor that just works.",
long_description="""\
news-please is an open source, easy-to-use news crawler that extracts structured information from almost any news website. It can follow recursively internal hyperlinks and read RSS feeds to fetch both most recent and also old, archived articles. You only need to provide the root URL of the news website. Furthermore, its API allows developers to access the exctraction functionality within their software. news-please also implements a workflow optimized for the news archive provided by commoncrawl.org, allowing users to efficiently crawl and extract news articles including various filter options.""",
classifiers=[
'Development Status :: 5 - Production/Stable',
'Environment :: Console',
'Intended Audience :: Developers',
'Intended Audience :: Science/Research',
'License :: OSI Approved :: Apache Software License',
'Operating System :: MacOS',
'Operating System :: Microsoft',
'Operating System :: POSIX :: Linux',
'Programming Language :: Python :: 3.4',
'Programming Language :: Python :: 3.5',
'Programming Language :: Python :: 3.6',
'Topic :: Internet',
'Topic :: Scientific/Engineering :: Information Analysis',
],
keywords='news crawler news scraper news extractor crawler extractor scraper information retrieval',
author='Felix Hamborg',
author_email='[email protected]',
url='https://github.com/fhamborg/news-please',
download_url='https://github.com/fhamborg/news-please',
license='Apache License 2.0',
packages=find_packages(exclude=['ez_setup', 'examples', 'tests']),
include_package_data=True,
zip_safe=False,
install_requires=[
'Scrapy>=1.1.0',
'PyMySQL>=0.7.9',
'psycopg2-binary>=2.8.4',
'hjson>=1.5.8',
'elasticsearch>=2.4',
'beautifulsoup4>=4.3.2',
'readability-lxml>=0.6.2',
'newspaper3k>=0.2.8',
'langdetect>=1.0.7',
'python-dateutil>=2.4.0',
'plac>=0.9.6',
'dotmap>=1.2.17',
'readability-lxml>=0.6.2',
'PyDispatcher>=2.0.5',
'warcio>=1.3.3',
'ago>=0.0.9',
'six>=1.10.0',
'lxml>=3.3.5',
'hurry.filesize>=0.9',
'bs4',
'faust-cchardet>=2.1.18',
'boto3',
'redis',
'newspaper4k>=0.9.3.1',
'lxml-html-clean>=0.1.1',
],
extras_require={
':sys_platform == "win32"': [
'pywin32>=220'
]
},
entry_points={
'console_scripts': ['news-please = newsplease.__main__:main',
'news-please-cc = newsplease.examples.commoncrawl:main']
},
)
classifiers=[
"Development Status :: 5 - Production/Stable",
"Environment :: Console",
"Intended Audience :: Developers",
"Intended Audience :: Science/Research",
"License :: OSI Approved :: Apache Software License",
"Operating System :: MacOS",
"Operating System :: Microsoft",
"Operating System :: POSIX :: Linux",
"Programming Language :: Python :: 3.4",
"Programming Language :: Python :: 3.5",
"Programming Language :: Python :: 3.6",
"Topic :: Internet",
"Topic :: Scientific/Engineering :: Information Analysis",
],
keywords="news crawler news scraper news extractor crawler extractor scraper information retrieval",
author="Felix Hamborg",
author_email="[email protected]",
url="https://github.com/fhamborg/news-please",
download_url="https://github.com/fhamborg/news-please",
license="Apache License 2.0",
packages=find_packages(exclude=["ez_setup", "examples", "tests"]),
include_package_data=True,
zip_safe=False,
install_requires=[
"Scrapy>=1.1.0",
"PyMySQL>=0.7.9",
"psycopg2-binary>=2.8.4",
"hjson>=1.5.8",
"elasticsearch>=2.4",
"beautifulsoup4>=4.3.2",
"readability-lxml>=0.6.2",
"langdetect>=1.0.7",
"python-dateutil>=2.4.0",
"plac>=0.9.6",
"dotmap>=1.2.17",
"readability-lxml>=0.6.2",
"PyDispatcher>=2.0.5",
"warcio>=1.3.3",
"ago>=0.0.9",
"six>=1.10.0",
"lxml>=3.3.5",
"hurry.filesize>=0.9",
"bs4",
"faust-cchardet>=2.1.18",
"boto3",
"redis",
"newspaper4k>=0.9.3.1",
"lxml-html-clean>=0.1.1",
],
extras_require={':sys_platform == "win32"': ["pywin32>=220"]},
entry_points={
"console_scripts": [
"news-please = newsplease.__main__:main",
"news-please-cc = newsplease.examples.commoncrawl:main",
]
},
)

0 comments on commit d79ae58

Please sign in to comment.