Better CJK support (and fix for lxml-clean), thanks @cdhigh

Author: buriy

.gitignore

@@ -14,4 +14,5 @@ nosetests.xml
 .idea
 .cache
 /.noseids
-/.venv
+/.venv
+/poetry.lock

Makefile

@@ -50,13 +50,14 @@ clean_all: clean_venv
 # ###########
 .PHONY: dist
 dist:
+	$(PY) -m pip install wheel
 	$(PY) setup.py sdist bdist_wheel
 	$(TWINE) check dist/*
 
 .PHONY: upload
 upload:
 	$(TWINE) upload dist/*
 
-.PHONY: version_update
-version_update:
-	$(EDITOR) setup.py
+.PHONY: bump
+bump:
+	$(EDITOR) readability/__init__.py

README.rst

@@ -48,7 +48,9 @@ Usage
 
 Change Log
 ----------
-
+-  0.8.4 Better CJK support, thanks @cdhigh
+-  0.8.3.1 Support for python 3.8 - 3.13
+-  0.8.3 We can now save all images via keep_all_images=True (default is to save 1 main image), thanks @botlabsDev
 -  0.8.2 Added article author(s) (thanks @mattblaha)
 -  0.8.1 Fixed processing of non-ascii HTMLs via regexps.
 -  0.8 Replaced XHTML output with HTML5 output in summary() call.

pyproject.toml

@@ -0,0 +1,19 @@
+[tool.poetry]
+name = "readability-lxml"
+version = "0.8.4"
+description = "fast html to text parser (article readability tool) with python 3 support"
+authors = ["Yuri Baburov <[email protected]>"]
+license = "Apache License 2.0"
+readme = "README.rst"
+
+[tool.poetry.dependencies]
+python = ">=3.8.2,<3.14"
+chardet = "^5.2.0"
+cssselect = "~1.2"
+lxml = {extras = ["html-clean"], version = "^5.4.0"}
+lxml-html-clean = {markers = "python_version < \"3.11\"", version = "^0.4.2"}
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

readability/__init__.py

@@ -1,3 +1,3 @@
-__version__ = "0.8.3"
+__version__ = "0.8.4"
 
 from .readability import Document