From dad53eb8ce6a0f27f584144aba5cf63cc9d67e21 Mon Sep 17 00:00:00 2001 From: CoprDistGit Date: Wed, 17 May 2023 03:43:08 +0000 Subject: automatic import of python-brozzler --- python-brozzler.spec | 90 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 90 insertions(+) create mode 100644 python-brozzler.spec (limited to 'python-brozzler.spec') diff --git a/python-brozzler.spec b/python-brozzler.spec new file mode 100644 index 0000000..aeb73c8 --- /dev/null +++ b/python-brozzler.spec @@ -0,0 +1,90 @@ +%global _empty_manifest_terminate_build 0 +Name: python-brozzler +Version: 1.5.18 +Release: 1 +Summary: Distributed web crawling with browsers +License: Apache License 2.0 +URL: https://github.com/internetarchive/brozzler +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/b9/9e/7fa23d061f1dcbbe659740a675bff85804d715ce552ae7a3780e27c81537/brozzler-1.5.18.tar.gz +BuildArch: noarch + + +%description +"browser" \| "crawler" = "brozzler" +Brozzler is a distributed web crawler (爬虫) that uses a real browser (Chrome +or Chromium) to fetch pages and embedded URLs and to extract links. It employs +`youtube-dl `_ to enhance media capture +capabilities and `rethinkdb `_ to +manage crawl state. +Brozzler is designed to work in conjuction with warcprox for web archiving. + +%package -n python3-brozzler +Summary: Distributed web crawling with browsers +Provides: python-brozzler +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-brozzler +"browser" \| "crawler" = "brozzler" +Brozzler is a distributed web crawler (爬虫) that uses a real browser (Chrome +or Chromium) to fetch pages and embedded URLs and to extract links. It employs +`youtube-dl `_ to enhance media capture +capabilities and `rethinkdb `_ to +manage crawl state. +Brozzler is designed to work in conjuction with warcprox for web archiving. + +%package help +Summary: Development documents and examples for brozzler +Provides: python3-brozzler-doc +%description help +"browser" \| "crawler" = "brozzler" +Brozzler is a distributed web crawler (爬虫) that uses a real browser (Chrome +or Chromium) to fetch pages and embedded URLs and to extract links. It employs +`youtube-dl `_ to enhance media capture +capabilities and `rethinkdb `_ to +manage crawl state. +Brozzler is designed to work in conjuction with warcprox for web archiving. + +%prep +%autosetup -n brozzler-1.5.18 + +%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-brozzler -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Wed May 17 2023 Python_Bot - 1.5.18-1 +- Package Spec generated -- cgit v1.2.3