From 7b7562d930648380d03c2ffa06cbd0f145791ce9 Mon Sep 17 00:00:00 2001 From: Liliana Marie Prikler Date: Sat, 17 Sep 2022 21:50:48 +0200 Subject: [PATCH] gnu: Add python-readability-lxml. * gnu/packages/python-xyz.scm (python-readability-lxml): New variable. --- gnu/packages/python-xyz.scm | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/gnu/packages/python-xyz.scm b/gnu/packages/python-xyz.scm index 34d6aa5ea0..74fa826889 100644 --- a/gnu/packages/python-xyz.scm +++ b/gnu/packages/python-xyz.scm @@ -27967,6 +27967,38 @@ characteristics. These measures are basically linear regressions based on the number of words, syllables, and sentences.") (license license:asl2.0))) +(define-public python-readability-lxml + (package + (name "python-readability-lxml") + (version "0.8.1") + (source (origin + (method git-fetch) + (uri (git-reference + (url "https://github.com/buriy/python-readability") + (commit (string-append "v" version)))) + (sha256 + (base32 + "13nfy2v0pbbf62jn9qwgi489gg97hbb22q6w3f78mnvjxd2m19rh")) + (snippet + #~(begin (delete-file "readability/compat/two.py"))))) + (build-system python-build-system) + (arguments + (list + #:phases + #~(modify-phases %standard-phases + (replace 'check + (lambda* (#:key tests? #:allow-other-keys) + (when tests? + (invoke "python" "-m" "pytest" "-v" "tests/"))))))) + (propagated-inputs (list python-chardet python-cssselect python-lxml)) + (native-inputs (list python-timeout-decorator python-pytest)) + (home-page "http://github.com/buriy/python-readability") + (synopsis "HTML to text parser") + (description + "This package provides classes and function that strip gratuitous markup +from web pages to make them easier to read.") + (license license:asl2.0))) + (define-public python-listparser (package (name "python-listparser")