summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorCoprDistGit <infra@openeuler.org>2023-04-10 21:14:54 +0000
committerCoprDistGit <infra@openeuler.org>2023-04-10 21:14:54 +0000
commit22e309a83b0ca3a4173c55a45fea69f9b9a99a9d (patch)
tree60d30d41f7332d6458f144f624fe9ebc040bca9d
parent4d4a93f8b383c23bca69ff4f7bef95b53b970ad1 (diff)
automatic import of python-trafilatura
-rw-r--r--.gitignore1
-rw-r--r--python-trafilatura.spec90
-rw-r--r--sources1
3 files changed, 92 insertions, 0 deletions
diff --git a/.gitignore b/.gitignore
index e69de29..6aaa816 100644
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1 @@
+/trafilatura-1.5.0.tar.gz
diff --git a/python-trafilatura.spec b/python-trafilatura.spec
new file mode 100644
index 0000000..71a1863
--- /dev/null
+++ b/python-trafilatura.spec
@@ -0,0 +1,90 @@
+%global _empty_manifest_terminate_build 0
+Name: python-trafilatura
+Version: 1.5.0
+Release: 1
+Summary: Python package and command-line tool designed to gather text on the Web. It includes discovery, extraction and text processing components. Its main applications are web crawling, downloads, scraping, and extraction of main texts, metadata and comments.
+License: GPLv3+
+URL: https://trafilatura.readthedocs.io
+Source0: https://mirrors.nju.edu.cn/pypi/web/packages/d8/aa/5e4f48ecbd5399ff0e3b452fa7befeb7d21060c698ebc71409fd3ad79e18/trafilatura-1.5.0.tar.gz
+BuildArch: noarch
+
+Requires: python3-certifi
+Requires: python3-courlan
+Requires: python3-htmldate
+Requires: python3-justext
+Requires: python3-lxml
+Requires: python3-urllib3
+Requires: python3-charset-normalizer
+Requires: python3-charset-normalizer
+Requires: python3-brotli
+Requires: python3-htmldate[speed]
+Requires: python3-py3langid
+Requires: python3-pycurl
+Requires: python3-cchardet
+Requires: python3-faust-cchardet
+Requires: python3-Gooey
+
+%description
+|
+|
+
+%package -n python3-trafilatura
+Summary: Python package and command-line tool designed to gather text on the Web. It includes discovery, extraction and text processing components. Its main applications are web crawling, downloads, scraping, and extraction of main texts, metadata and comments.
+Provides: python-trafilatura
+BuildRequires: python3-devel
+BuildRequires: python3-setuptools
+BuildRequires: python3-pip
+%description -n python3-trafilatura
+|
+|
+
+%package help
+Summary: Development documents and examples for trafilatura
+Provides: python3-trafilatura-doc
+%description help
+|
+|
+
+%prep
+%autosetup -n trafilatura-1.5.0
+
+%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-trafilatura -f filelist.lst
+%dir %{python3_sitelib}/*
+
+%files help -f doclist.lst
+%{_docdir}/*
+
+%changelog
+* Mon Apr 10 2023 Python_Bot <Python_Bot@openeuler.org> - 1.5.0-1
+- Package Spec generated
diff --git a/sources b/sources
new file mode 100644
index 0000000..ce68eed
--- /dev/null
+++ b/sources
@@ -0,0 +1 @@
+737260e5226905807d8a830238af484a trafilatura-1.5.0.tar.gz