You're Invited:Meet the Socket Team at RSAC and BSidesSF 2026, March 23–26.RSVP →
html-text
Artifacts are distributable versions of a package. It typically includes the source code and metadata
Advanced tools
html-text - pypi Package Compare versions
+63
| # Byte-compiled / optimized / DLL files | ||
| __pycache__/ | ||
| *.py[cod] | ||
| *$py.class | ||
| # C extensions | ||
| *.so | ||
| # Distribution / packaging | ||
| .Python | ||
| env/ | ||
| build/ | ||
| develop-eggs/ | ||
| dist/ | ||
| downloads/ | ||
| eggs/ | ||
| .eggs/ | ||
| lib/ | ||
| lib64/ | ||
| parts/ | ||
| sdist/ | ||
| var/ | ||
| *.egg-info/ | ||
| .installed.cfg | ||
| *.egg | ||
| # PyInstaller | ||
| # Usually these files are written by a python script from a template | ||
| # before PyInstaller builds the exe, so as to inject date/other infos into it. | ||
| *.manifest | ||
| *.spec | ||
| # Installer logs | ||
| pip-log.txt | ||
| pip-delete-this-directory.txt | ||
| # Unit test / coverage reports | ||
| htmlcov/ | ||
| .tox/ | ||
| .coverage | ||
| .coverage.* | ||
| .cache | ||
| nosetests.xml | ||
| coverage.xml | ||
| *,cover | ||
| .hypothesis/ | ||
| .pytest_cache | ||
| # Translations | ||
| *.mo | ||
| *.pot | ||
| # Django stuff: | ||
| *.log | ||
| # Sphinx documentation | ||
| docs/_build/ | ||
| # PyBuilder | ||
| target/ | ||
| # PyCharm | ||
| .idea |
+38
| [tox] | ||
| envlist = py39,py310,py311,py312,py313,py39-parsel,twinecheck | ||
| [testenv] | ||
| deps = | ||
| pytest | ||
| pytest-cov >= 7.0.0 | ||
| py39-parsel: parsel | ||
| commands = | ||
| pytest --cov=html_text --cov-report=xml --cov-report=term-missing {env:PYTEST_DOC:} {posargs:.} | ||
| [testenv:py39-parsel] | ||
| setenv = | ||
| PYTEST_DOC = --doctest-modules --doctest-glob='*.rst' | ||
| [testenv:twinecheck] | ||
| basepython = python3 | ||
| deps = | ||
| twine==6.2.0 | ||
| build==1.3.0 | ||
| commands = | ||
| python -m build --sdist | ||
| twine check dist/* | ||
| [testenv:pre-commit] | ||
| deps = pre-commit | ||
| commands = pre-commit run --all-files --show-diff-on-failure | ||
| skip_install = true | ||
| [testenv:typing] | ||
| basepython = python3 | ||
| deps = | ||
| mypy==1.18.2 | ||
| parsel==1.10.0 | ||
| pytest==8.4.2 | ||
| types-lxml==2025.8.25 | ||
| commands = | ||
| mypy {posargs: html_text tests} |
+7
-0
@@ -5,2 +5,9 @@ ======= | ||
| 0.7.1 (unreleased) | ||
| ------------------ | ||
| * Added support for Python 3.14. | ||
| * Explicitly re-export public names. | ||
| * Migrated the build system to ``hatchling``. | ||
| * CI improvements. | ||
| 0.7.0 (2025-02-10) | ||
@@ -7,0 +14,0 @@ ------------------ |
@@ -1,2 +0,2 @@ | ||
| __version__ = "0.7.0" | ||
| __version__ = "0.7.1" | ||
@@ -13,1 +13,12 @@ from .html_text import ( | ||
| ) | ||
| __all__ = ( | ||
| "DOUBLE_NEWLINE_TAGS", | ||
| "NEWLINE_TAGS", | ||
| "cleaned_selector", | ||
| "cleaner", | ||
| "etree_to_text", | ||
| "extract_text", | ||
| "parse_html", | ||
| "selector_to_text", | ||
| ) |
@@ -194,3 +194,3 @@ from __future__ import annotations | ||
| """ | ||
| import parsel | ||
| import parsel # noqa: PLC0415 | ||
@@ -214,3 +214,3 @@ if isinstance(sel, parsel.SelectorList): | ||
| """Clean parsel.selector.""" | ||
| import parsel | ||
| import parsel # noqa: PLC0415 | ||
@@ -217,0 +217,0 @@ try: |
+0
-1
@@ -11,2 +11,1 @@ | ||
| THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. | ||
+10
-133
@@ -1,12 +0,11 @@ | ||
| Metadata-Version: 2.2 | ||
| Name: html_text | ||
| Version: 0.7.0 | ||
| Metadata-Version: 2.4 | ||
| Name: html-text | ||
| Version: 0.7.1 | ||
| Summary: Extract text from HTML | ||
| Home-page: https://github.com/zytedata/html-text | ||
| Author: Konstantin Lopukhin | ||
| Author-email: kostia.lopuhin@gmail.com | ||
| License: MIT license | ||
| Project-URL: Homepage, https://github.com/zytedata/html-text | ||
| Author-email: Konstantin Lopukhin <kostia.lopuhin@gmail.com> | ||
| License-Expression: MIT | ||
| License-File: LICENSE | ||
| Classifier: Development Status :: 4 - Beta | ||
| Classifier: Intended Audience :: Developers | ||
| Classifier: License :: OSI Approved :: MIT License | ||
| Classifier: Natural Language :: English | ||
@@ -19,15 +18,7 @@ Classifier: Programming Language :: Python :: 3 | ||
| Classifier: Programming Language :: Python :: 3.13 | ||
| Description-Content-Type: text/x-rst | ||
| License-File: LICENSE | ||
| Classifier: Programming Language :: Python :: 3.14 | ||
| Requires-Python: >=3.9 | ||
| Requires-Dist: lxml | ||
| Requires-Dist: lxml-html-clean | ||
| Dynamic: author | ||
| Dynamic: author-email | ||
| Dynamic: classifier | ||
| Dynamic: description | ||
| Dynamic: description-content-type | ||
| Dynamic: home-page | ||
| Dynamic: license | ||
| Dynamic: requires-dist | ||
| Dynamic: summary | ||
| Description-Content-Type: text/x-rst | ||
@@ -163,115 +154,1 @@ ============ | ||
| `webstruct <http://webstruct.readthedocs.io/en/latest/>`_ library. | ||
| ======= | ||
| History | ||
| ======= | ||
| 0.7.0 (2025-02-10) | ||
| ------------------ | ||
| * Removed support for Python 3.8. | ||
| * Added support for Python 3.13. | ||
| * Added type hints and ``py.typed``. | ||
| * CI improvements. | ||
| 0.6.2 (2024-05-01) | ||
| ------------------ | ||
| * Support deeper trees by using iteration instead of recursion. | ||
| 0.6.1 (2024-04-23) | ||
| ------------------ | ||
| * Fixed HTML comment and processing instruction handling. | ||
| * Use ``lxml-html-clean`` instead of ``lxml[html_clean]`` in setup.py, | ||
| to avoid https://github.com/jazzband/pip-tools/issues/2004 | ||
| 0.6.0 (2024-04-04) | ||
| ------------------ | ||
| * Moved the Git repository to https://github.com/zytedata/html-text. | ||
| * Added official support for Python 3.9-3.12. | ||
| * Removed support for Python 2.7 and 3.5-3.7. | ||
| * Switched the ``lxml`` dependency to ``lxml[html_clean]`` to support | ||
| ``lxml >= 5.2.0``. | ||
| * Switch from Travis CI to GitHub Actions. | ||
| * CI improvements. | ||
| 0.5.2 (2020-07-22) | ||
| ------------------ | ||
| * Handle lxml Cleaner exceptions (a workaround for | ||
| https://bugs.launchpad.net/lxml/+bug/1838497 ); | ||
| * Python 3.8 support; | ||
| * testing improvements. | ||
| 0.5.1 (2019-05-27) | ||
| ------------------ | ||
| Fixed whitespace handling when ``guess_punct_space`` is False: html-text was | ||
| producing unnecessary spaces after newlines. | ||
| 0.5.0 (2018-11-19) | ||
| ------------------ | ||
| Parsel dependency is removed in this release, | ||
| though parsel is still supported. | ||
| * ``parsel`` package is no longer required to install and use html-text; | ||
| * ``html_text.etree_to_text`` function allows to extract text from | ||
| lxml Elements; | ||
| * ``html_text.cleaner`` is an ``lxml.html.clean.Cleaner`` instance with | ||
| options tuned for text extraction speed and quality; | ||
| * test and documentation improvements; | ||
| * Python 3.7 support. | ||
| 0.4.1 (2018-09-25) | ||
| ------------------ | ||
| Fixed a regression in 0.4.0 release: text was empty when | ||
| ``html_text.extract_text`` is called with a node with text, but | ||
| without children. | ||
| 0.4.0 (2018-09-25) | ||
| ------------------ | ||
| This is a backwards-incompatible release: by default html_text functions | ||
| now add newlines after elements, if appropriate, to make the extracted text | ||
| to look more like how it is rendered in a browser. | ||
| To turn it off, pass ``guess_layout=False`` option to html_text functions. | ||
| * ``guess_layout`` option to to make extracted text look more like how | ||
| it is rendered in browser. | ||
| * Add tests of layout extraction for real webpages. | ||
| 0.3.0 (2017-10-12) | ||
| ------------------ | ||
| * Expose functions that operate on selectors, | ||
| use ``.//text()`` to extract text from selector. | ||
| 0.2.1 (2017-05-29) | ||
| ------------------ | ||
| * Packaging fix (include CHANGES.rst) | ||
| 0.2.0 (2017-05-29) | ||
| ------------------ | ||
| * Fix unwanted joins of words with inline tags: spaces are added for inline | ||
| tags too, but a heuristic is used to preserve punctuation without extra spaces. | ||
| * Accept parsed html trees. | ||
| 0.1.1 (2017-01-16) | ||
| ------------------ | ||
| * Travis-CI and codecov.io integrations added | ||
| 0.1.0 (2016-09-27) | ||
| ------------------ | ||
| * First release on PyPI. |
+58
-13
@@ -0,3 +1,38 @@ | ||
| [build-system] | ||
| requires = ["hatchling>=1.27.0"] | ||
| build-backend = "hatchling.build" | ||
| [project] | ||
| name = "html-text" | ||
| dynamic = ["version"] | ||
| description = "Extract text from HTML" | ||
| readme = "README.rst" | ||
| license = "MIT" | ||
| license-files = ["LICENSE"] | ||
| authors = [ | ||
| { name = "Konstantin Lopukhin", email = "kostia.lopuhin@gmail.com" }, | ||
| ] | ||
| classifiers = [ | ||
| "Development Status :: 4 - Beta", | ||
| "Intended Audience :: Developers", | ||
| "Natural Language :: English", | ||
| "Programming Language :: Python :: 3", | ||
| "Programming Language :: Python :: 3.9", | ||
| "Programming Language :: Python :: 3.10", | ||
| "Programming Language :: Python :: 3.11", | ||
| "Programming Language :: Python :: 3.12", | ||
| "Programming Language :: Python :: 3.13", | ||
| "Programming Language :: Python :: 3.14", | ||
| ] | ||
| dependencies = [ | ||
| "lxml", | ||
| "lxml-html-clean", | ||
| ] | ||
| requires-python = ">=3.9" | ||
| [project.urls] | ||
| Homepage = "https://github.com/zytedata/html-text" | ||
| [tool.bumpversion] | ||
| current_version = "0.7.0" | ||
| current_version = "0.7.1" | ||
| commit = true | ||
@@ -8,7 +43,2 @@ tag = true | ||
| [[tool.bumpversion.files]] | ||
| filename = "setup.py" | ||
| search = "version=\"{current_version}\"" | ||
| replace = "version=\"{new_version}\"" | ||
| [[tool.bumpversion.files]] | ||
| filename = "html_text/__init__.py" | ||
@@ -21,7 +51,16 @@ search = "__version__ = \"{current_version}\"" | ||
| [tool.coverage.report] | ||
| exclude_also = [ | ||
| "if TYPE_CHECKING:", | ||
| [tool.hatch.version] | ||
| path = "html_text/__init__.py" | ||
| [tool.hatch.build.targets.sdist] | ||
| include = [ | ||
| "/html_text", | ||
| "/tests", | ||
| "/CHANGES.rst", | ||
| "/tox.ini", | ||
| ] | ||
| [tool.mypy] | ||
| strict = true | ||
| [[tool.mypy.overrides]] | ||
@@ -34,2 +73,6 @@ module = "tests.*" | ||
| extend-select = [ | ||
| # flake8-builtins | ||
| "A", | ||
| # flake8-async | ||
| "ASYNC", | ||
| # flake8-bugbear | ||
@@ -39,2 +82,4 @@ "B", | ||
| "C4", | ||
| # flake8-commas | ||
| "COM", | ||
| # pydocstyle | ||
@@ -94,2 +139,4 @@ "D", | ||
| ignore = [ | ||
| # Trailing comma missing | ||
| "COM812", | ||
| # Missing docstring in public module | ||
@@ -149,10 +196,8 @@ "D100", | ||
| "S101", | ||
| # Using lxml to parse untrusted data is known to be vulnerable to XML attacks | ||
| "S320", | ||
| ] | ||
| [tool.ruff.lint.per-file-ignores] | ||
| "html_text/__init__.py" = ["F401"] | ||
| [tool.ruff.lint.isort] | ||
| split-on-trailing-comma = false | ||
| [tool.ruff.lint.pydocstyle] | ||
| convention = "pep257" |
Sorry, the diff of this file is not supported yet
| Metadata-Version: 2.2 | ||
| Name: html_text | ||
| Version: 0.7.0 | ||
| Summary: Extract text from HTML | ||
| Home-page: https://github.com/zytedata/html-text | ||
| Author: Konstantin Lopukhin | ||
| Author-email: kostia.lopuhin@gmail.com | ||
| License: MIT license | ||
| Classifier: Development Status :: 4 - Beta | ||
| Classifier: Intended Audience :: Developers | ||
| Classifier: License :: OSI Approved :: MIT License | ||
| Classifier: Natural Language :: English | ||
| Classifier: Programming Language :: Python :: 3 | ||
| Classifier: Programming Language :: Python :: 3.9 | ||
| Classifier: Programming Language :: Python :: 3.10 | ||
| Classifier: Programming Language :: Python :: 3.11 | ||
| Classifier: Programming Language :: Python :: 3.12 | ||
| Classifier: Programming Language :: Python :: 3.13 | ||
| Description-Content-Type: text/x-rst | ||
| License-File: LICENSE | ||
| Requires-Dist: lxml | ||
| Requires-Dist: lxml-html-clean | ||
| Dynamic: author | ||
| Dynamic: author-email | ||
| Dynamic: classifier | ||
| Dynamic: description | ||
| Dynamic: description-content-type | ||
| Dynamic: home-page | ||
| Dynamic: license | ||
| Dynamic: requires-dist | ||
| Dynamic: summary | ||
| ============ | ||
| HTML to Text | ||
| ============ | ||
| .. image:: https://img.shields.io/pypi/v/html-text.svg | ||
| :target: https://pypi.python.org/pypi/html-text | ||
| :alt: PyPI Version | ||
| .. image:: https://img.shields.io/pypi/pyversions/html-text.svg | ||
| :target: https://pypi.python.org/pypi/html-text | ||
| :alt: Supported Python Versions | ||
| .. image:: https://github.com/zytedata/html-text/workflows/tox/badge.svg | ||
| :target: https://github.com/zytedata/html-text/actions | ||
| :alt: Build Status | ||
| .. image:: https://codecov.io/github/zytedata/html-text/coverage.svg?branch=master | ||
| :target: https://codecov.io/gh/zytedata/html-text | ||
| :alt: Coverage report | ||
| Extract text from HTML | ||
| * Free software: MIT license | ||
| How is html_text different from ``.xpath('//text()')`` from LXML | ||
| or ``.get_text()`` from Beautiful Soup? | ||
| * Text extracted with ``html_text`` does not contain inline styles, | ||
| javascript, comments and other text that is not normally visible to users; | ||
| * ``html_text`` normalizes whitespace, but in a way smarter than | ||
| ``.xpath('normalize-space())``, adding spaces around inline elements | ||
| (which are often used as block elements in html markup), and trying to | ||
| avoid adding extra spaces for punctuation; | ||
| * ``html-text`` can add newlines (e.g. after headers or paragraphs), so | ||
| that the output text looks more like how it is rendered in browsers. | ||
| Install | ||
| ------- | ||
| Install with pip:: | ||
| pip install html-text | ||
| The package depends on lxml, so you might need to install additional | ||
| packages: http://lxml.de/installation.html | ||
| Usage | ||
| ----- | ||
| Extract text from HTML:: | ||
| >>> import html_text | ||
| >>> html_text.extract_text('<h1>Hello</h1> world!') | ||
| 'Hello\n\nworld!' | ||
| >>> html_text.extract_text('<h1>Hello</h1> world!', guess_layout=False) | ||
| 'Hello world!' | ||
| Passed html is first cleaned from invisible non-text content such | ||
| as styles, and then text is extracted. | ||
| You can also pass an already parsed ``lxml.html.HtmlElement``: | ||
| >>> import html_text | ||
| >>> tree = html_text.parse_html('<h1>Hello</h1> world!') | ||
| >>> html_text.extract_text(tree) | ||
| 'Hello\n\nworld!' | ||
| If you want, you can handle cleaning manually; use lower-level | ||
| ``html_text.etree_to_text`` in this case: | ||
| >>> import html_text | ||
| >>> tree = html_text.parse_html('<h1>Hello<style>.foo{}</style>!</h1>') | ||
| >>> cleaned_tree = html_text.cleaner.clean_html(tree) | ||
| >>> html_text.etree_to_text(cleaned_tree) | ||
| 'Hello!' | ||
| parsel.Selector objects are also supported; you can define | ||
| a parsel.Selector to extract text only from specific elements: | ||
| >>> import html_text | ||
| >>> sel = html_text.cleaned_selector('<h1>Hello</h1> world!') | ||
| >>> subsel = sel.xpath('//h1') | ||
| >>> html_text.selector_to_text(subsel) | ||
| 'Hello' | ||
| NB parsel.Selector objects are not cleaned automatically, you need to call | ||
| ``html_text.cleaned_selector`` first. | ||
| Main functions and objects: | ||
| * ``html_text.extract_text`` accepts html and returns extracted text. | ||
| * ``html_text.etree_to_text`` accepts parsed lxml Element and returns | ||
| extracted text; it is a lower-level function, cleaning is not handled | ||
| here. | ||
| * ``html_text.cleaner`` is an ``lxml.html.clean.Cleaner`` instance which | ||
| can be used with ``html_text.etree_to_text``; its options are tuned for | ||
| speed and text extraction quality. | ||
| * ``html_text.cleaned_selector`` accepts html as text or as | ||
| ``lxml.html.HtmlElement``, and returns cleaned ``parsel.Selector``. | ||
| * ``html_text.selector_to_text`` accepts ``parsel.Selector`` and returns | ||
| extracted text. | ||
| If ``guess_layout`` is True (default), a newline is added before and after | ||
| ``newline_tags``, and two newlines are added before and after | ||
| ``double_newline_tags``. This heuristic makes the extracted text | ||
| more similar to how it is rendered in the browser. Default newline and double | ||
| newline tags can be found in `html_text.NEWLINE_TAGS` | ||
| and `html_text.DOUBLE_NEWLINE_TAGS`. | ||
| It is possible to customize how newlines are added, using ``newline_tags`` and | ||
| ``double_newline_tags`` arguments (which are `html_text.NEWLINE_TAGS` and | ||
| `html_text.DOUBLE_NEWLINE_TAGS` by default). For example, don't add a newline | ||
| after ``<div>`` tags: | ||
| >>> newline_tags = html_text.NEWLINE_TAGS - {'div'} | ||
| >>> html_text.extract_text('<div>Hello</div> world!', | ||
| ... newline_tags=newline_tags) | ||
| 'Hello world!' | ||
| Apart from just getting text from the page (e.g. for display or search), | ||
| one intended usage of this library is for machine learning (feature extraction). | ||
| If you want to use the text of the html page as a feature (e.g. for classification), | ||
| this library gives you plain text that you can later feed into a standard text | ||
| classification pipeline. | ||
| If you feel that you need html structure as well, check out | ||
| `webstruct <http://webstruct.readthedocs.io/en/latest/>`_ library. | ||
| ======= | ||
| History | ||
| ======= | ||
| 0.7.0 (2025-02-10) | ||
| ------------------ | ||
| * Removed support for Python 3.8. | ||
| * Added support for Python 3.13. | ||
| * Added type hints and ``py.typed``. | ||
| * CI improvements. | ||
| 0.6.2 (2024-05-01) | ||
| ------------------ | ||
| * Support deeper trees by using iteration instead of recursion. | ||
| 0.6.1 (2024-04-23) | ||
| ------------------ | ||
| * Fixed HTML comment and processing instruction handling. | ||
| * Use ``lxml-html-clean`` instead of ``lxml[html_clean]`` in setup.py, | ||
| to avoid https://github.com/jazzband/pip-tools/issues/2004 | ||
| 0.6.0 (2024-04-04) | ||
| ------------------ | ||
| * Moved the Git repository to https://github.com/zytedata/html-text. | ||
| * Added official support for Python 3.9-3.12. | ||
| * Removed support for Python 2.7 and 3.5-3.7. | ||
| * Switched the ``lxml`` dependency to ``lxml[html_clean]`` to support | ||
| ``lxml >= 5.2.0``. | ||
| * Switch from Travis CI to GitHub Actions. | ||
| * CI improvements. | ||
| 0.5.2 (2020-07-22) | ||
| ------------------ | ||
| * Handle lxml Cleaner exceptions (a workaround for | ||
| https://bugs.launchpad.net/lxml/+bug/1838497 ); | ||
| * Python 3.8 support; | ||
| * testing improvements. | ||
| 0.5.1 (2019-05-27) | ||
| ------------------ | ||
| Fixed whitespace handling when ``guess_punct_space`` is False: html-text was | ||
| producing unnecessary spaces after newlines. | ||
| 0.5.0 (2018-11-19) | ||
| ------------------ | ||
| Parsel dependency is removed in this release, | ||
| though parsel is still supported. | ||
| * ``parsel`` package is no longer required to install and use html-text; | ||
| * ``html_text.etree_to_text`` function allows to extract text from | ||
| lxml Elements; | ||
| * ``html_text.cleaner`` is an ``lxml.html.clean.Cleaner`` instance with | ||
| options tuned for text extraction speed and quality; | ||
| * test and documentation improvements; | ||
| * Python 3.7 support. | ||
| 0.4.1 (2018-09-25) | ||
| ------------------ | ||
| Fixed a regression in 0.4.0 release: text was empty when | ||
| ``html_text.extract_text`` is called with a node with text, but | ||
| without children. | ||
| 0.4.0 (2018-09-25) | ||
| ------------------ | ||
| This is a backwards-incompatible release: by default html_text functions | ||
| now add newlines after elements, if appropriate, to make the extracted text | ||
| to look more like how it is rendered in a browser. | ||
| To turn it off, pass ``guess_layout=False`` option to html_text functions. | ||
| * ``guess_layout`` option to to make extracted text look more like how | ||
| it is rendered in browser. | ||
| * Add tests of layout extraction for real webpages. | ||
| 0.3.0 (2017-10-12) | ||
| ------------------ | ||
| * Expose functions that operate on selectors, | ||
| use ``.//text()`` to extract text from selector. | ||
| 0.2.1 (2017-05-29) | ||
| ------------------ | ||
| * Packaging fix (include CHANGES.rst) | ||
| 0.2.0 (2017-05-29) | ||
| ------------------ | ||
| * Fix unwanted joins of words with inline tags: spaces are added for inline | ||
| tags too, but a heuristic is used to preserve punctuation without extra spaces. | ||
| * Accept parsed html trees. | ||
| 0.1.1 (2017-01-16) | ||
| ------------------ | ||
| * Travis-CI and codecov.io integrations added | ||
| 0.1.0 (2016-09-27) | ||
| ------------------ | ||
| * First release on PyPI. |
| lxml | ||
| lxml-html-clean |
| CHANGES.rst | ||
| LICENSE | ||
| MANIFEST.in | ||
| README.rst | ||
| pyproject.toml | ||
| setup.py | ||
| html_text/__init__.py | ||
| html_text/html_text.py | ||
| html_text/py.typed | ||
| html_text.egg-info/PKG-INFO | ||
| html_text.egg-info/SOURCES.txt | ||
| html_text.egg-info/dependency_links.txt | ||
| html_text.egg-info/not-zip-safe | ||
| html_text.egg-info/requires.txt | ||
| html_text.egg-info/top_level.txt | ||
| tests/__init__.py | ||
| tests/test_html_text.py | ||
| tests/test_webpages/A Light in the Attic | Books to Scrape - Sandbox.html | ||
| tests/test_webpages/A Light in the Attic | Books to Scrape - Sandbox.txt | ||
| tests/test_webpages/IANA — IANA-managed Reserved Domains.html | ||
| tests/test_webpages/IANA — IANA-managed Reserved Domains.txt | ||
| tests/test_webpages/Scrapinghub Enterprise Solutions.html | ||
| tests/test_webpages/Scrapinghub Enterprise Solutions.txt | ||
| tests/test_webpages/Tutorial — Webstruct 0.6 documentation.html | ||
| tests/test_webpages/Tutorial — Webstruct 0.6 documentation.txt | ||
| tests/test_webpages/Webstruct — Webstruct 0.6 documentation.html | ||
| tests/test_webpages/Webstruct — Webstruct 0.6 documentation.txt |
| html_text |
| include CHANGES.rst | ||
| include LICENSE | ||
| include README.rst | ||
| recursive-include tests * | ||
| recursive-exclude * __pycache__ | ||
| recursive-exclude * *.py[co] |
| [egg_info] | ||
| tag_build = | ||
| tag_date = 0 | ||
-42
| #!/usr/bin/env python | ||
| from pathlib import Path | ||
| from setuptools import setup | ||
| readme = Path("README.rst").read_text(encoding="utf-8") | ||
| history = Path("CHANGES.rst").read_text(encoding="utf-8") | ||
| setup( | ||
| name="html_text", | ||
| version="0.7.0", | ||
| description="Extract text from HTML", | ||
| long_description=readme + "\n\n" + history, | ||
| long_description_content_type="text/x-rst", | ||
| author="Konstantin Lopukhin", | ||
| author_email="kostia.lopuhin@gmail.com", | ||
| url="https://github.com/zytedata/html-text", | ||
| packages=["html_text"], | ||
| package_data={ | ||
| "html_text": ["py.typed"], | ||
| }, | ||
| include_package_data=True, | ||
| install_requires=[ | ||
| "lxml", | ||
| "lxml-html-clean", | ||
| ], | ||
| license="MIT license", | ||
| zip_safe=False, | ||
| classifiers=[ | ||
| "Development Status :: 4 - Beta", | ||
| "Intended Audience :: Developers", | ||
| "License :: OSI Approved :: MIT License", | ||
| "Natural Language :: English", | ||
| "Programming Language :: Python :: 3", | ||
| "Programming Language :: Python :: 3.9", | ||
| "Programming Language :: Python :: 3.10", | ||
| "Programming Language :: Python :: 3.11", | ||
| "Programming Language :: Python :: 3.12", | ||
| "Programming Language :: Python :: 3.13", | ||
| ], | ||
| ) |
Alert delta unavailable
Currently unable to show alert delta for PyPI packages.
Worsened metrics
- Total package byte prevSize
194970
-5.52%- Number of package files
22
-24.14%- Lines of code
450
-5.86%