diff options
author | CoprDistGit <infra@openeuler.org> | 2023-05-31 06:55:39 +0000 |
---|---|---|
committer | CoprDistGit <infra@openeuler.org> | 2023-05-31 06:55:39 +0000 |
commit | e3d96659311961a5cc93c785c8908f6287dc674a (patch) | |
tree | 6a23021c2d8956d57b89db7e93224ea2fe54b9f5 | |
parent | 6873d6a6dc020ceefcf3bd791fa1e7252fa2af99 (diff) |
automatic import of python-stimson-web-scraper
-rw-r--r-- | .gitignore | 1 | ||||
-rw-r--r-- | python-stimson-web-scraper.spec | 100 | ||||
-rw-r--r-- | sources | 1 |
3 files changed, 102 insertions, 0 deletions
@@ -0,0 +1 @@ +/stimson-web-scraper-0.0.63.tar.gz diff --git a/python-stimson-web-scraper.spec b/python-stimson-web-scraper.spec new file mode 100644 index 0000000..accd4ba --- /dev/null +++ b/python-stimson-web-scraper.spec @@ -0,0 +1,100 @@ +%global _empty_manifest_terminate_build 0 +Name: python-stimson-web-scraper +Version: 0.0.63 +Release: 1 +Summary: website article / adobe pdf file discovery & extraction +License: MIT +URL: https://github.com/Stimson-Center/stimson-web-scraper +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/3a/68/572ede8ee6d3d19a093941d44bc1fe3516d5496e6584aa443139fe252f57/stimson-web-scraper-0.0.63.tar.gz +BuildArch: noarch + +Requires: python3-beautifulsoup4 +Requires: python3-click +Requires: python3-cssselect +Requires: python3-date-extractor +Requires: python3-fake-useragent +Requires: python3-feedfinder2 +Requires: python3-feedparser +Requires: python3-fpdf2 +Requires: python3-jieba3k +Requires: python3-lxml +Requires: python3-numpy +Requires: python3-pandas +Requires: python3-pdftotext +Requires: python3-Pillow +Requires: python3-psutil +Requires: python3-pyarabic +Requires: python3-pytextrank +Requires: python3-pythainlp +Requires: python3-dateutil +Requires: python3-dateparser +Requires: python3-PyPDF4 +Requires: python3-PyYAML +Requires: python3-requests +Requires: python3-requests-toolbelt +Requires: python3-spacy +Requires: python3-tldextract +Requires: python3-tinysegmenter +Requires: python3-waitress + +%description +Scrapes and crawls websites for textual data and urls in any ISO language + +%package -n python3-stimson-web-scraper +Summary: website article / adobe pdf file discovery & extraction +Provides: python-stimson-web-scraper +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-stimson-web-scraper +Scrapes and crawls websites for textual data and urls in any ISO language + +%package help +Summary: Development documents and examples for stimson-web-scraper +Provides: python3-stimson-web-scraper-doc +%description help +Scrapes and crawls websites for textual data and urls in any ISO language + +%prep +%autosetup -n stimson-web-scraper-0.0.63 + +%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-stimson-web-scraper -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Wed May 31 2023 Python_Bot <Python_Bot@openeuler.org> - 0.0.63-1 +- Package Spec generated @@ -0,0 +1 @@ +b3267a58f769647053b5fd1a65df671c stimson-web-scraper-0.0.63.tar.gz |