change license to Apache 2.0 (adbar#526)

steineggerroland · Mar 20, 2024 · c7e00f3 · c7e00f3
1 parent e87b5a1
commit c7e00f3
Show file tree

Hide file tree

Showing 21 changed files with 184 additions and 738 deletions.
diff --git a/LICENSE b/LICENSE
diff --git a/README.rst b/README.rst
@@ -136,11 +136,9 @@ Youtube playlist with video tutorials in several languages:
 License
 -------
 
-*Trafilatura* is distributed under the `GNU General Public License v3.0 <https://github.com/adbar/trafilatura/blob/master/LICENSE>`_. This license promotes collaboration in software development and ensures that Trafilatura's code remains publicly accessible.
+This package is distributed under the `Apache 2.0 license <https://www.apache.org/licenses/LICENSE-2.0.html>`_.
 
-If you wish to redistribute this library but are concerned about the license conditions, consider interacting `at arms length <https://www.gnu.org/licenses/gpl-faq.html#GPLInProprietarySystem>`_, combining with `compatible licenses <https://www.gnu.org/licenses/license-list.html#GPLCompatibleLicenses>`_, or `contacting the author <#author>`_ for more options.
-
-For insights into GPL and free software licensing with emphasis on a business context, see `GPL and Free Software Licensing: What's in it for Business? <https://web.archive.org/web/20230127221311/https://www.techrepublic.com/article/gpl-and-free-software-licensing-whats-in-it-for-business/>`_
+Versions prior to v1.8.0 are under GPLv3+ license.
 
 
 Contributing

diff --git a/docs/index.rst b/docs/index.rst
@@ -114,11 +114,9 @@ For more see `usage documentation <usage.html>`_ and `tutorials <tutorials.html>
 License
 -------
 
-*Trafilatura* is distributed under the `GNU General Public License v3.0 <https://github.com/adbar/trafilatura/blob/master/LICENSE>`_. This license promotes collaboration in software development and ensures that Trafilatura's code remains publicly accessible.
+This package is distributed under the `Apache 2.0 license <https://www.apache.org/licenses/LICENSE-2.0.html>`_.
 
-If you wish to redistribute this library but are concerned about the license conditions, consider interacting `at arms length <https://www.gnu.org/licenses/gpl-faq.html#GPLInProprietarySystem>`_, combining with `compatible licenses <https://www.gnu.org/licenses/license-list.html#GPLCompatibleLicenses>`_, or `contacting the author <https://adrien.barbaresi.eu>`_ for more options.
-
-For insights into GPL and free software licensing with emphasis on a business context, see `GPL and Free Software Licensing: What's in it for Business? <https://web.archive.org/web/20230127221311/https://www.techrepublic.com/article/gpl-and-free-software-licensing-whats-in-it-for-business/>`_
+Versions prior to v1.8.0 are under GPLv3+ license.
 
 
 

diff --git a/setup.py b/setup.py
@@ -54,7 +54,7 @@ def get_long_description():
         "Intended Audience :: Education",
         "Intended Audience :: Information Technology",
         "Intended Audience :: Science/Research",
-        "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)",
+        "License :: OSI Approved :: Apache Software License",
         "Operating System :: MacOS",
         "Operating System :: Microsoft",
         "Operating System :: POSIX",
@@ -96,7 +96,7 @@ def get_long_description():
     },
     author="Adrien Barbaresi",
     author_email="[email protected]",
-    license="GPLv3+",
+    license="Apache-2.0",
     packages=["trafilatura"],
     package_data={
         "trafilatura": [

diff --git a/trafilatura/__init__.py b/trafilatura/__init__.py
@@ -4,10 +4,10 @@
 web crawling/scraping, extraction of text, metadata, comments.
 """
 
-# meta
+
 __title__ = 'trafilatura'
 __author__ = 'Adrien Barbaresi and contributors'
-__license__ = 'GNU GPL v3+'
+__license__ = "Apache-2.0"
 __copyright__ = 'Copyright 2019-2024, Adrien Barbaresi'
 __version__ = '1.7.0'
 

diff --git a/trafilatura/cli.py b/trafilatura/cli.py
@@ -2,9 +2,6 @@
 Implementing a basic command-line interface.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
 import argparse
 import logging
 import sys

diff --git a/trafilatura/cli_utils.py b/trafilatura/cli_utils.py
@@ -2,10 +2,6 @@
 Functions dedicated to command-line processing.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
-
 import gzip
 import logging
 import random

diff --git a/trafilatura/core.py b/trafilatura/core.py
@@ -3,11 +3,6 @@
 Module bundling all functions needed to extract the text in a webpage.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
-
-# standard
 import logging
 import re  # import regex as re
 import warnings

diff --git a/trafilatura/downloads.py b/trafilatura/downloads.py
@@ -3,7 +3,6 @@
 All functions needed to steer and execute downloads of web documents.
 """
 
-
 import logging
 import random
 import warnings

diff --git a/trafilatura/external.py b/trafilatura/external.py
@@ -3,10 +3,6 @@
 Functions grounding on third-party software.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
-
 import logging
 import lzma
 from pathlib import Path

diff --git a/trafilatura/feeds.py b/trafilatura/feeds.py
@@ -2,9 +2,6 @@
 Examining feeds and extracting links for further processing.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
 import json
 import logging
 import re

diff --git a/trafilatura/gui.py b/trafilatura/gui.py
@@ -2,9 +2,6 @@
 This script implements a basic guided user interface (GUI).
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
 import sys
 
 from gooey import Gooey, GooeyParser

diff --git a/trafilatura/htmlprocessing.py b/trafilatura/htmlprocessing.py
@@ -3,9 +3,6 @@
 Functions to process nodes in HTML code.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
 import logging
 from collections import defaultdict
 from copy import deepcopy

diff --git a/trafilatura/lru.py b/trafilatura/lru.py
@@ -5,10 +5,6 @@
 First adapted by https://github.com/vbarbaresi
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
-
 from threading import RLock
 
 PREV, NEXT, KEY, RESULT = 0, 1, 2, 3  # names for the link fields

diff --git a/trafilatura/metaxpaths.py b/trafilatura/metaxpaths.py
@@ -2,9 +2,6 @@
 File containing XPath expressions to extract metadata.
 """
 
-# code available from https://github.com/adbar/trafilatura/
-# under GNU GPLv3+ license
-
 from lxml.etree import XPath
 
 

diff --git a/trafilatura/readability_lxml.py b/trafilatura/readability_lxml.py
@@ -15,10 +15,8 @@
 https://github.com/buriy/python-readability
 
 License of forked code: Apache-2.0 License
-This code: GPLv3+
 """
 
-
 import logging
 import re
 

diff --git a/trafilatura/settings.py b/trafilatura/settings.py
@@ -3,10 +3,6 @@
 Listing a series of settings that are applied module-wide.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
-
 from configparser import ConfigParser
 try:
     from os import sched_getaffinity

diff --git a/trafilatura/sitemaps.py b/trafilatura/sitemaps.py
@@ -2,10 +2,6 @@
 Deriving link info from sitemaps.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
-
 import logging
 import re
 

diff --git a/trafilatura/utils.py b/trafilatura/utils.py
@@ -3,9 +3,6 @@
 Module bundling functions related to HTML and text processing.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
 import logging
 import re
 import warnings

diff --git a/trafilatura/xml.py b/trafilatura/xml.py
@@ -3,9 +3,6 @@
 All functions related to XML generation, processing and validation.
 """
 
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
 import csv
 import logging
 import lzma

diff --git a/trafilatura/xpaths.py b/trafilatura/xpaths.py
@@ -1,9 +1,6 @@
 """
 X-Path expressions needed to extract and filter the main text content
 """
-## This file is available from https://github.com/adbar/trafilatura
-## under GNU GPL v3 license
-
 
 from lxml.etree import XPath