%global _empty_manifest_terminate_build 0
Name:		python-warc3-wet-clueweb09
Version:	0.2.5
Release:	1
Summary:	Python library to work with ARC and WARC files, with fixes for ClueWeb09
License:	GPLv2
URL:		https://github.com/seanmacavaney/warc3-clueweb
Source0:	https://mirrors.nju.edu.cn/pypi/web/packages/9f/c1/dd817bf57e0274dacb10e0ac868cb6cd70876950cf361c41879c030a2b8b/warc3-wet-clueweb09-0.2.5.tar.gz
BuildArch:	noarch


%description
Note: This is a fork of the original (now dead) warc repository.
Updated to handle problems with the ClueWeb09_ files.
Changes are based on this repository_ (which only supports python2)
WARC (Web ARChive) is a file format for storing web crawls.
http://bibnum.bnf.fr/WARC/ 
This `warc` library makes it very easy to work with WARC files.::
    import warc
    with warc.open("test.warc") as f:
        for record in f:
            print(record['WARC-Target-URI'], record['Content-Length'])
And WET files.::
    import warc
    with warc.open("test.warc.wet") as f:
        for record in f:
            print(record['WARC-Target-URI'], record['Content-Length'])

%package -n python3-warc3-wet-clueweb09
Summary:	Python library to work with ARC and WARC files, with fixes for ClueWeb09
Provides:	python-warc3-wet-clueweb09
BuildRequires:	python3-devel
BuildRequires:	python3-setuptools
BuildRequires:	python3-pip
%description -n python3-warc3-wet-clueweb09
Note: This is a fork of the original (now dead) warc repository.
Updated to handle problems with the ClueWeb09_ files.
Changes are based on this repository_ (which only supports python2)
WARC (Web ARChive) is a file format for storing web crawls.
http://bibnum.bnf.fr/WARC/ 
This `warc` library makes it very easy to work with WARC files.::
    import warc
    with warc.open("test.warc") as f:
        for record in f:
            print(record['WARC-Target-URI'], record['Content-Length'])
And WET files.::
    import warc
    with warc.open("test.warc.wet") as f:
        for record in f:
            print(record['WARC-Target-URI'], record['Content-Length'])

%package help
Summary:	Development documents and examples for warc3-wet-clueweb09
Provides:	python3-warc3-wet-clueweb09-doc
%description help
Note: This is a fork of the original (now dead) warc repository.
Updated to handle problems with the ClueWeb09_ files.
Changes are based on this repository_ (which only supports python2)
WARC (Web ARChive) is a file format for storing web crawls.
http://bibnum.bnf.fr/WARC/ 
This `warc` library makes it very easy to work with WARC files.::
    import warc
    with warc.open("test.warc") as f:
        for record in f:
            print(record['WARC-Target-URI'], record['Content-Length'])
And WET files.::
    import warc
    with warc.open("test.warc.wet") as f:
        for record in f:
            print(record['WARC-Target-URI'], record['Content-Length'])

%prep
%autosetup -n warc3-wet-clueweb09-0.2.5

%build
%py3_build

%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
	find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
	find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
	find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
	find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
	find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .

%files -n python3-warc3-wet-clueweb09 -f filelist.lst
%dir %{python3_sitelib}/*

%files help -f doclist.lst
%{_docdir}/*

%changelog
* Tue May 30 2023 Python_Bot <Python_Bot@openeuler.org> - 0.2.5-1
- Package Spec generated