www-misc/urlwatch: fix CSS selectors with dev-python/lxml >= 5.0.0

Closes: https://bugs.gentoo.org/926767
Signed-off-by: Louis Sautier <sbraz@gentoo.org>

2 files changed, 104 insertions, 0 deletions

diff --git a/www-misc/urlwatch/files/urlwatch-2.28-lxml-5.patch b/www-misc/urlwatch/files/urlwatch-2.28-lxml-5.patch
new file mode 100644
index 000000000000..d5f80410859f
--- /dev/null
+++ b/www-misc/urlwatch/files/urlwatch-2.28-lxml-5.patch
@@ -0,0 +1,28 @@
+https://github.com/thp/urlwatch/commit/123de66d019aef7fc18fab6d56cc2a54d81fea3f
+
+From: James Hewitt <james.hewitt@uk.ibm.com>
+Date: Wed, 17 Jan 2024 13:50:28 +0000
+Subject: [PATCH] Update CSS Selector to use new style
+
+New style of calling the CSSSelector directly instead of using the
+evaluate function. This has been supported since lxml 1.1 [1] and the
+evaluate method has been deprecated since lxml 2.1 [2].
+
+[1] https://github.com/lxml/lxml/blob/lxml-1.1/src/lxml/xpath.pxi#L66
+[2] https://github.com/lxml/lxml/blob/lxml-2.1/src/lxml/xpath.pxi#L143
+
+Signed-off-by: James Hewitt <james.hewitt@uk.ibm.com>
+--- a/lib/urlwatch/filters.py
++++ b/lib/urlwatch/filters.py
+@@ -761,9 +761,9 @@ def _get_filtered_elements(self):
+         excluded_elems = None
+         if self.filter_kind == 'css':
+             selected_elems = CSSSelector(self.expression,
+-                                         namespaces=self.namespaces).evaluate(root)
++                                         namespaces=self.namespaces)(root)
+             excluded_elems = CSSSelector(self.exclude,
+-                                         namespaces=self.namespaces).evaluate(root) if self.exclude else None
++                                         namespaces=self.namespaces)(root) if self.exclude else None
+         elif self.filter_kind == 'xpath':
+             selected_elems = root.xpath(self.expression, namespaces=self.namespaces)
+             excluded_elems = root.xpath(self.exclude, namespaces=self.namespaces) if self.exclude else None
diff --git a/www-misc/urlwatch/urlwatch-2.28-r1.ebuild b/www-misc/urlwatch/urlwatch-2.28-r1.ebuild
new file mode 100644
index 000000000000..ae6e35c21106
--- /dev/null
+++ b/www-misc/urlwatch/urlwatch-2.28-r1.ebuild
@@ -0,0 +1,76 @@
+# Copyright 1999-2024 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=8
+
+DISTUTILS_USE_PEP517=setuptools
+PYTHON_COMPAT=( python3_{10..12} )
+
+inherit distutils-r1 pypi
+
+DESCRIPTION="A tool for monitoring webpages for updates"
+HOMEPAGE="
+	https://thp.io/2008/urlwatch/
+	https://github.com/thp/urlwatch/
+	https://pypi.org/project/urlwatch/
+"
+
+LICENSE="BSD"
+SLOT="0"
+KEYWORDS="~amd64 ~x86"
+
+RDEPEND="
+	dev-python/appdirs[${PYTHON_USEDEP}]
+	dev-python/cssselect[${PYTHON_USEDEP}]
+	dev-python/keyring[${PYTHON_USEDEP}]
+	dev-python/lxml[${PYTHON_USEDEP}]
+	>=dev-python/minidb-2.0.6[${PYTHON_USEDEP}]
+	dev-python/pyyaml[${PYTHON_USEDEP}]
+	dev-python/requests[${PYTHON_USEDEP}]
+"
+BDEPEND="
+	test? (
+		app-text/tesseract[png]
+		dev-python/docutils[${PYTHON_USEDEP}]
+		dev-python/jq[${PYTHON_USEDEP}]
+		dev-python/pytesseract[${PYTHON_USEDEP}]
+	)
+"
+
+PATCHES=(
+	"${FILESDIR}/${P}-lxml-5.patch"
+)
+
+DOCS=( CHANGELOG.md README.md )
+
+distutils_enable_sphinx docs/source dev-python/alabaster
+distutils_enable_tests pytest
+
+EPYTEST_DESELECT=(
+	# Require the pdftotext module
+	"lib/urlwatch/tests/test_filter_documentation.py::test_url[https://example.net/pdf-test.pdf]"
+	"lib/urlwatch/tests/test_filter_documentation.py::test_url[https://example.net/pdf-test-password.pdf]"
+	# Skip code quality check
+	"lib/urlwatch/tests/test_handler.py::test_pep8_conformance"
+)
+
+pkg_postinst() {
+	if [[ -z "${REPLACING_VERSIONS}" ]]; then
+		if ! has_version dev-python/chump; then
+			elog "Install 'dev-python/chump' to enable Pushover" \
+				"notifications support"
+		fi
+		if ! has_version dev-python/jq; then
+			elog "Install 'dev-python/jq' to enable jq filtering support"
+		fi
+		if ! has_version dev-python/pytesseract; then
+			elog "Install 'dev-python/pytesseract' to enable OCR support"
+		fi
+		elog "HTML parsing can be improved by installing one of the following packages"
+		elog "and changing the html2text subfilter parameter:"
+		elog "dev-python/beautifulsoup4"
+		elog "app-text/html2text"
+		elog "dev-python/html2text"
+		elog "www-client/lynx"
+	fi
+}