selectolax 0.3.28__cp38-cp38-musllinux_1_2_aarch64.whl

selectolax-0.3.28.dist-info/METADATA

@@ -0,0 +1,183 @@
+Metadata-Version: 2.1
+Name: selectolax
+Version: 0.3.28
+Summary: Fast HTML5 parser with CSS selectors.
+Home-page: https://github.com/rushter/selectolax
+Author: Artem Golubin
+Author-email: me@rushter.com
+License: MIT license
+Project-URL: Source code, https://github.com/rushter/selectolax
+Keywords: selectolax
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Internet
+Classifier: Topic :: Internet :: WWW/HTTP
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+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
+License-File: LICENSE
+Provides-Extra: cython
+Requires-Dist: Cython==3.0.11; extra == "cython"
+
+.. image:: docs/logo.png
+  :alt: selectolax logo
+
+-------------------------
+
+.. image:: https://img.shields.io/pypi/v/selectolax.svg
+        :target: https://pypi.python.org/pypi/selectolax
+
+A fast HTML5 parser with CSS selectors using `Modest <https://github.com/lexborisov/Modest/>`_ and
+`Lexbor <https://github.com/lexbor/lexbor>`_ engines.
+
+
+Installation
+------------
+From PyPI using pip:
+
+.. code-block:: bash
+
+        pip install selectolax
+
+If installation fails due to compilation errors, you may need to install `Cython <https://github.com/cython/cython>`_:
+
+.. code-block:: bash
+
+        pip install selectolax[cython]
+
+This usually happens when you try to install an outdated version of selectolax on a newer version of Python.
+
+
+Development version from GitHub:
+
+.. code-block:: bash
+
+        git clone --recursive  https://github.com/rushter/selectolax
+        cd selectolax
+        pip install -r requirements_dev.txt
+        python setup.py install
+
+How to compile selectolax while developing:
+
+.. code-block:: bash
+
+    make clean
+    make dev
+
+Basic examples
+--------------
+
+Here are some basic examples to get you started with selectolax:
+
+Parsing HTML and extracting text:
+
+.. code:: python
+
+    In [1]: from selectolax.parser import HTMLParser
+       ...:
+       ...: html = """
+       ...: <h1 id="title" data-updated="20201101">Hi there</h1>
+       ...: <div class="post">Lorem Ipsum is simply dummy text of the printing and typesetting industry. </div>
+       ...: <div class="post">Lorem ipsum dolor sit amet, consectetur adipiscing elit.</div>
+       ...: """
+       ...: tree = HTMLParser(html)
+
+    In [2]: tree.css_first('h1#title').text()
+    Out[2]: 'Hi there'
+
+    In [3]: tree.css_first('h1#title').attributes
+    Out[3]: {'id': 'title', 'data-updated': '20201101'}
+
+    In [4]: [node.text() for node in tree.css('.post')]
+    Out[4]:
+    ['Lorem Ipsum is simply dummy text of the printing and typesetting industry. ',
+     'Lorem ipsum dolor sit amet, consectetur adipiscing elit.']
+
+Using advanced CSS selectors:
+
+.. code:: python
+
+    In [1]: html = "<div><p id=p1><p id=p2><p id=p3><a>link</a><p id=p4><p id=p5>text<p id=p6></div>"
+       ...: selector = "div > :nth-child(2n+1):not(:has(a))"
+
+    In [2]: for node in HTMLParser(html).css(selector):
+       ...:     print(node.attributes, node.text(), node.tag)
+       ...:     print(node.parent.tag)
+       ...:     print(node.html)
+       ...:
+    {'id': 'p1'}  p
+    div
+    <p id="p1"></p>
+    {'id': 'p5'} text p
+    div
+    <p id="p5">text</p>
+
+
+* `Detailed overview <https://github.com/rushter/selectolax/blob/master/examples/walkthrough.ipynb>`_
+
+Available backends
+------------------
+
+Selectolax supports two backends: ``Modest`` and ``Lexbor``. By default, all examples use the Modest backend.
+Most of the features between backends are almost identical, but there are still some differences.
+
+As of 2024, the preferred backend is ``Lexbor``. The ``Modest`` backend is still available for compatibility reasons
+and the underlying C library that selectolax uses is not maintained anymore.
+
+
+To use ``lexbor``, just import the parser and use it in the similar way to the `HTMLParser`.
+
+.. code:: python
+
+    In [1]: from selectolax.lexbor import LexborHTMLParser
+
+    In [2]: html = """
+       ...: <title>Hi there</title>
+       ...: <div id="updated">2021-08-15</div>
+       ...: """
+
+    In [3]: parser = LexborHTMLParser(html)
+    In [4]: parser.root.css_first("#updated").text()
+    Out[4]: '2021-08-15'
+
+
+Simple Benchmark
+----------------
+
+* Extract title, links, scripts and a meta tag from main pages of top 754 domains. See ``examples/benchmark.py`` for more information.
+
+============================ ===========
+Package                       Time
+============================ ===========
+Beautiful Soup (html.parser)  61.02 sec.
+lxml / Beautiful Soup (lxml)  9.09 sec.
+html5_parser                  16.10 sec.
+selectolax (Modest)           2.94 sec.
+selectolax (Lexbor)           2.39 sec.
+============================ ===========
+
+Links
+-----
+
+*  `selectolax API reference <http://selectolax.readthedocs.io/en/latest/parser.html>`_
+*  `Video introduction to web scraping using selectolax <https://youtu.be/HpRsfpPuUzE>`_
+*  `How to Scrape 7k Products with Python using selectolax and httpx <https://www.youtube.com/watch?v=XpGvq755J2U>`_
+*  `Detailed overview <https://github.com/rushter/selectolax/blob/master/examples/walkthrough.ipynb>`_
+*  `Modest introduction <https://lexborisov.github.io/Modest/>`_
+*  `Modest benchmark <http://lexborisov.github.io/benchmark-html-persers/>`_
+*  `Python benchmark <https://rushter.com/blog/python-fast-html-parser/>`_
+*  `Another Python benchmark <https://www.peterbe.com/plog/selectolax-or-pyquery>`_
+
+License
+-------
+
+* Modest engine — `LGPL2.1 <https://github.com/lexborisov/Modest/blob/master/LICENSE>`_
+* selectolax - `MIT <https://github.com/rushter/selectolax/blob/master/LICENSE>`_

selectolax-0.3.28.dist-info/RECORD

@@ -0,0 +1,26 @@
+selectolax-0.3.28.dist-info/LICENSE,sha256=MYCcM-Cv_rC2-lQiwDumin0E-rMXAhK-qIGGA29434Y,1077
+selectolax-0.3.28.dist-info/WHEEL,sha256=BHRewEbUf61vtumHxoNlQbDQLU_vG0pDuFQgyArrrYE,111
+selectolax-0.3.28.dist-info/METADATA,sha256=vTdwlSLUc9k1DeDfD4h5ZcM0cB0aIgShNit3UMiniAU,6060
+selectolax-0.3.28.dist-info/top_level.txt,sha256=e5MuEM2PrQzoDlWetkFli9uXSlxa_ktW5jJEihhaI1c,11
+selectolax-0.3.28.dist-info/RECORD,,
+selectolax/parser.pxd,sha256=zZlg1vHUg6o4MXaiwKAo5S5hO_DqBGc4_E10qJ2EcM4,24564
+selectolax/__init__.py,sha256=IhnQaAtBWz03SUIe66y78uQqmWBontg4z13rRupwa7Q,175
+selectolax/base.pxi,sha256=eiPKlY9gG3l49qJoRQVLl1Ljza6z1k0A-met6sDPcqE,89
+selectolax/lexbor.pyi,sha256=gf0rPd2B1EZyz_oN6EER-wFojg__Sz18GwjjVYo7SkU,6552
+selectolax/lexbor.cpython-38-aarch64-linux-gnu.so,sha256=RdpEP3hSN58notcTjtbCPX_OtWKYdEJzDFv9hQNKRJE,9320136
+selectolax/parser.pyi,sha256=qLkvStGG4K3daXChLChzPHGV5w5gmIEMvFwRpC_Q4EM,11561
+selectolax/utils.pxi,sha256=uB0-0naFQPy1JpR2DiIlKnyLyC76yWLnUHSuH11xg6s,3459
+selectolax/parser.c,sha256=yd8gEU0netTAe3rf5haknFFz-QtMHTi6nhKGW5GUTTE,2214825
+selectolax/lexbor.pxd,sha256=PwygBdb1blWAQcxXubZS5uffhgcXaqgySNMPFMT02-c,20958
+selectolax/lexbor.pyx,sha256=rpb32yQ2E_6nJeaPDQs3kb3GFoALZqQbVCN35kcUM-M,10882
+selectolax/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+selectolax/parser.pyx,sha256=o1HkYE_nQr3TS7EPlldJx2-ygU9B5FI2uWYFzdF-VaI,12953
+selectolax/parser.cpython-38-aarch64-linux-gnu.so,sha256=UPArZ08hYBRVp22NBbvWfT2ecV9c4Rdu-j6pG0l6Vss,7582216
+selectolax/lexbor.c,sha256=UkiarPPcp6IKa-HMZLnhap1CRltADEZdwsDWo5EviLQ,2359509
+selectolax/modest/util.pxi,sha256=aX9UnRNTITImHVBTlIs9efOd3EyugLq_Lwuo0zVTiuQ,551
+selectolax/modest/node.pxi,sha256=NrMzJnQJDCmgTHpUxpMHDyAfQ_AS_n_Cr_2ryEKjyL0,32550
+selectolax/modest/selection.pxi,sha256=S55MMxEW2B1oPExB_DRwPM46WoWZU73J3rFRZU1URuQ,6393
+selectolax/lexbor/attrs.pxi,sha256=Ol2RNzXZAcWaqJdDBUe0ChOCcA8HC990Hjncj98XAkw,3138
+selectolax/lexbor/util.pxi,sha256=Zq7S-zlyU3wOo49wGHQHnmmhpbkrcJm59ZCTPENcZQA,563
+selectolax/lexbor/node.pxi,sha256=-cqsA4gz9yL6hCte6uGgdQKvhIBZF_BZc_xHJn0rkCM,29340
+selectolax/lexbor/selection.pxi,sha256=FA6npHtXjJjvS8H2_e_LS53i5zbpGYgb5zTh5Tf_XQY,6571

selectolax-0.3.28.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.1.0)
+Root-Is-Purelib: false
+Tag: cp38-cp38-musllinux_1_2_aarch64
+

selectolax-0.3.28.dist-info/top_level.txt

@@ -0,0 +1 @@
+selectolax