selectolax 0.3.32__cp310-cp310-win_amd64.whl → 0.3.34__cp310-cp310-win_amd64.whl

selectolax/parser.pxd

@@ -33,9 +33,9 @@ cdef extern from "myhtml/myhtml.h" nogil:
         MyHTML_OPTIONS_PARSE_MODE_SEPARATELY   = 0x04
 
     ctypedef struct myhtml_collection_t:
-        myhtml_tree_node_t **list;
-        size_t size;
-        size_t length;
+        myhtml_tree_node_t **list
+        size_t size
+        size_t length
 
     ctypedef  struct myhtml_tree_node_t:
         myhtml_tree_node_flags flags
@@ -86,7 +86,6 @@ cdef extern from "myhtml/myhtml.h" nogil:
         MyHTML_TOKEN_TYPE_COMMENT          = 0x400
         MyHTML_TOKEN_TYPE_NULL             = 0x800
 
-
     ctypedef enum myhtml_tags:
         MyHTML_TAG__UNDEF              = 0x000
         MyHTML_TAG__TEXT               = 0x001
@@ -392,8 +391,6 @@ cdef extern from "myhtml/myhtml.h" nogil:
         size_t raw_value_begin
         size_t raw_value_length
 
-
-
     myhtml_t * myhtml_create()
     mystatus_t myhtml_init(myhtml_t* myhtml, myhtml_options opt, size_t thread_count, size_t queue_size)
     myhtml_tree_t * myhtml_tree_create()
@@ -415,7 +412,7 @@ cdef extern from "myhtml/myhtml.h" nogil:
     myhtml_tree_node_t* myhtml_tree_get_node_head(myhtml_tree_t* tree)
 
     myhtml_collection_t* myhtml_get_nodes_by_name(myhtml_tree_t* tree, myhtml_collection_t *collection,
-                         const char* name, size_t length, mystatus_t *status)
+                                                  const char* name, size_t length, mystatus_t *status)
 
     void myhtml_node_delete(myhtml_tree_node_t *node)
     void myhtml_node_delete_recursive(myhtml_tree_node_t *node)
@@ -427,7 +424,7 @@ cdef extern from "myhtml/myhtml.h" nogil:
     myhtml_tree_node_t * myhtml_node_append_child(myhtml_tree_node_t* target, myhtml_tree_node_t* node)
 
     mycore_string_t * myhtml_node_text_set(myhtml_tree_node_t *node, const char* text, size_t length,
-                                          myencoding_t encoding)
+                                           myencoding_t encoding)
     myhtml_tree_attr_t * myhtml_attribute_by_key(myhtml_tree_node_t *node, const char *key, size_t key_len)
     myhtml_tree_attr_t * myhtml_attribute_remove_by_key(myhtml_tree_node_t *node, const char *key, size_t key_len)
     myhtml_tree_attr_t * myhtml_attribute_add(myhtml_tree_node_t *node, const char *key, size_t key_len,
@@ -515,16 +512,16 @@ cdef extern from "mycss/mycss.h" nogil:
     ctypedef mycss_selectors_flags mycss_selectors_flags_t
 
     ctypedef struct mycss_selectors_list_t:
-        mycss_selectors_entries_list_t* entries_list;
-        size_t entries_list_length;
+        mycss_selectors_entries_list_t* entries_list
+        size_t entries_list_length
 
-        mycss_declaration_entry_t* declaration_entry;
+        mycss_declaration_entry_t* declaration_entry
 
-        mycss_selectors_flags_t flags;
+        mycss_selectors_flags_t flags
 
-        mycss_selectors_list_t* parent;
-        mycss_selectors_list_t* next;
-        mycss_selectors_list_t* prev;
+        mycss_selectors_list_t* parent
+        mycss_selectors_list_t* next
+        mycss_selectors_list_t* prev
 
     # CSS init routines
     mycss_t * mycss_create()
@@ -542,12 +539,11 @@ cdef extern from "mycss/mycss.h" nogil:
     mycss_t * mycss_destroy(mycss_t* mycss, bint self_destroy)
 
 
-
 cdef extern from "modest/finder/finder.h" nogil:
     ctypedef struct modest_finder_t
     modest_finder_t* modest_finder_create_simple()
     mystatus_t modest_finder_by_selectors_list(modest_finder_t* finder, myhtml_tree_node_t* scope_node,
-                                                mycss_selectors_list_t* selector_list, myhtml_collection_t** collection)
+                                               mycss_selectors_list_t* selector_list, myhtml_collection_t** collection)
     modest_finder_t * modest_finder_destroy(modest_finder_t* finder, bint self_destroy)
 
 
@@ -562,7 +558,8 @@ cdef class HTMLParser:
     cdef object cached_script_srcs
 
     cdef void _detect_encoding(self, char* html, size_t html_len) nogil
-    cdef _parse_html(self, char* html, size_t html_len)
+    cdef int _parse_html(self, char* html, size_t html_len) except -1
+
     @staticmethod
     cdef HTMLParser from_tree(
         myhtml_tree_t * tree, bytes raw_html, bint detect_encoding, bint use_meta_tags, str decode_errors,
@@ -576,6 +573,6 @@ cdef class Stack:
     cdef myhtml_tree_node_t ** _stack
 
     cdef bint is_empty(self)
-    cdef push(self, myhtml_tree_node_t* res)
+    cdef int push(self, myhtml_tree_node_t* res) except -1
     cdef myhtml_tree_node_t * pop(self)
-    cdef resize(self)
+    cdef int resize(self) except -1

selectolax/parser.pyi

@@ -1,4 +1,4 @@
-from typing import Iterator, TypeVar, Literal, overload
+from typing import Iterator, Literal, TypeVar, overload
 
 DefaultT = TypeVar("DefaultT")
 
@@ -268,7 +268,7 @@ class Node:
     def remove(self, recursive: bool = True) -> None:
         """An alias for the decompose method."""
         ...
-    def unwrap(self) -> None:
+    def unwrap(self, delete_empty: bool = False) -> None:
         """Replace node with whatever is inside this node.
 
         Parameters

selectolax/parser.pyx

@@ -1,5 +1,6 @@
 
-from cpython cimport bool
+from cpython.bool cimport bool
+from cpython.exc cimport PyErr_SetObject
 
 include "modest/selection.pxi"
 include "modest/node.pxi"
@@ -61,8 +62,7 @@ cdef class HTMLParser:
 
         """
 
-        node = Node()
-        node._init(self.html_tree.node_html, self)
+        cdef Node node = Node.new(self.html_tree.node_html, self)
         return node.css(query)
 
     def css_first(self, str query, default=None, strict=False):
@@ -84,12 +84,11 @@ cdef class HTMLParser:
 
         """
 
-        node = Node()
-        node._init(self.html_tree.node_html, self)
+        cdef Node node = Node.new(self.html_tree.node_html, self)
         return node.css_first(query, default, strict)
 
     cdef void _detect_encoding(self, char* html, size_t html_len) nogil:
-        cdef myencoding_t encoding = MyENCODING_DEFAULT;
+        cdef myencoding_t encoding = MyENCODING_DEFAULT
 
         if self.use_meta_tags:
             encoding = myencoding_prescan_stream_to_determine_encoding(html, html_len)
@@ -102,7 +101,7 @@ cdef class HTMLParser:
 
         self._encoding = encoding
 
-    cdef _parse_html(self, char* html, size_t html_len):
+    cdef int _parse_html(self, char* html, size_t html_len) except -1:
         cdef myhtml_t* myhtml
         cdef mystatus_t status
 
@@ -111,23 +110,28 @@ cdef class HTMLParser:
             status = myhtml_init(myhtml, MyHTML_OPTIONS_DEFAULT, 1, 0)
 
         if status != 0:
-            raise RuntimeError("Can't init MyHTML object.")
+            PyErr_SetObject(RuntimeError, "Can't init MyHTML object.")
+            return -1
 
         with nogil:
             self.html_tree = myhtml_tree_create()
             status = myhtml_tree_init(self.html_tree, myhtml)
 
         if status != 0:
-            raise RuntimeError("Can't init MyHTML Tree object.")
+            PyErr_SetObject(RuntimeError, "Can't init MyHTML Tree object.")
+            return -1
 
         with nogil:
             status = myhtml_parse(self.html_tree, self._encoding, html, html_len)
 
         if status != 0:
-            raise RuntimeError("Can't parse HTML (status code: %d)" % status)
-
-        assert self.html_tree.node_html != NULL
+            PyErr_SetObject(RuntimeError, "Can't parse HTML (status code: %d)" % status)
+            return -1
 
+        if self.html_tree.node_html == NULL:
+            PyErr_SetObject(RuntimeError, "html_tree is still NULL even after parsing ")
+            return -1
+        return 0
 
     @property
     def input_encoding(self):
@@ -148,9 +152,7 @@ cdef class HTMLParser:
         """Returns root node."""
         if self.html_tree and self.html_tree.node_html:
             try:
-                node = Node()
-                node._init(self.html_tree.node_html, self)
-                return node
+                return Node.new(self.html_tree.node_html, self)
             except Exception:
                 # If Node creation or initialization fails, return None
                 return None
@@ -163,9 +165,7 @@ cdef class HTMLParser:
         head = myhtml_tree_get_node_head(self.html_tree)
 
         if head != NULL:
-            node = Node()
-            node._init(head, self)
-            return node
+            return Node.new(head, self)
         return None
 
     @property
@@ -175,10 +175,7 @@ cdef class HTMLParser:
         body = myhtml_tree_get_node_body(self.html_tree)
 
         if body != NULL:
-            node = Node()
-            node._init(body, self)
-            return node
-
+            return Node.new(body, self)
         return None
 
     def tags(self, str name):
@@ -197,7 +194,7 @@ cdef class HTMLParser:
 
         cdef myhtml_collection_t* collection = NULL
         pybyte_name = name.encode('UTF-8')
-        cdef mystatus_t status = 0;
+        cdef mystatus_t status = 0
 
         result = list()
         collection = myhtml_get_nodes_by_name(self.html_tree, NULL, pybyte_name, len(pybyte_name), &status)
@@ -207,8 +204,7 @@ cdef class HTMLParser:
 
         if status == 0:
             for i in range(collection.length):
-                node = Node()
-                node._init(collection.list[i], self)
+                node = Node.new(collection.list[i], self)
                 result.append(node)
 
         myhtml_collection_destroy(collection)
@@ -258,7 +254,7 @@ cdef class HTMLParser:
         """
         cdef myhtml_collection_t* collection = NULL
 
-        cdef mystatus_t status = 0;
+        cdef mystatus_t status = 0
 
         for tag in tags:
             pybyte_name = tag.encode('UTF-8')
@@ -278,7 +274,6 @@ cdef class HTMLParser:
 
             myhtml_collection_destroy(collection)
 
-
     def unwrap_tags(self, list tags, delete_empty : bool = False):
         """Unwraps specified tags from the HTML tree.
 
@@ -305,9 +300,9 @@ cdef class HTMLParser:
     @property
     def html(self):
         """Return HTML representation of the page."""
-        if self.html_tree and self.html_tree.document:
-            node = Node()
-            node._init(self.html_tree.document, self)
+        cdef Node node
+        if self.html_tree != NULL and self.html_tree.document != NULL:
+            node = Node.new(self.html_tree.document, self)
             return node.html
         return None
 
@@ -361,6 +356,7 @@ cdef class HTMLParser:
 
     def css_matches(self, str selector):
         return self.root.css_matches(selector)
+
     def merge_text_nodes(self):
         """Iterates over all text nodes and merges all text nodes that are close to each other.
 
@@ -380,6 +376,7 @@ cdef class HTMLParser:
         "John Doe"
         """
         return self.root.merge_text_nodes()
+
     @staticmethod
     cdef HTMLParser from_tree(
             myhtml_tree_t * tree, bytes raw_html, bint detect_encoding, bint use_meta_tags, str decode_errors,
@@ -396,13 +393,13 @@ cdef class HTMLParser:
         obj.cached_script_srcs = None
         return obj
 
-
     def clone(self):
         """Clone the current tree."""
         cdef myhtml_t* myhtml
         cdef mystatus_t status
         cdef myhtml_tree_t* html_tree
         cdef myhtml_tree_node_t* node
+        cdef HTMLParser cls
 
         with nogil:
             myhtml = myhtml_create()

selectolax/utils.pxi

@@ -4,6 +4,16 @@ MAX_HTML_INPUT_SIZE = 250e+7
 
 ParserCls = Union[Type["HTMLParser"], Type["LexborHTMLParser"]]
 Parser = Union["HTMLParser", "LexborHTMLParser"]
+FRAGMENT = Literal[
+    "document",
+    "fragment",
+    "head",
+    "body",
+    "head_and_body",
+    "document_no_head",
+    "document_no_body",
+    "document_no_head_no_body",
+]
 
 
 def preprocess_input(html, decode_errors='ignore'):
@@ -29,10 +39,10 @@ def get_fragment_type(
     html: str,
     parser_cls: ParserCls,
     tree: Optional[Parser] = None,
-) -> Literal["document", "fragment", "head", "body", "head_and_body", "document_no_head", "document_no_body", "document_no_head_no_body"]:
+) -> FRAGMENT:
     if not tree:
         tree = parser_cls(html)
-    
+
     import re
     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
 
@@ -49,7 +59,7 @@ def get_fragment_type(
 
         if has_html and has_head and has_body:
             break
-    
+
     if has_html and has_head and has_body:
         return "document"
     elif has_html and not has_head and has_body:

selectolax-0.3.34.dist-info/METADATA

@@ -0,0 +1,32 @@
+Metadata-Version: 2.4
+Name: selectolax
+Version: 0.3.34
+Summary: Fast HTML5 parser with CSS selectors.
+Home-page: https://github.com/rushter/selectolax
+Author: Artem Golubin
+Author-email: Artem Golubin <me@rushter.com>
+License-Expression: MIT
+Project-URL: Repository, https://github.com/rushter/selectolax
+Project-URL: Documentation, https://selectolax.readthedocs.io/en/latest/parser.html
+Project-URL: Changelog, https://github.com/rushter/selectolax/blob/main/CHANGES.md
+Keywords: selectolax,html,parser,css,fast
+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: 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
+Requires-Python: >=3.9
+Description-Content-Type: text/x-rst
+License-File: LICENSE
+Provides-Extra: cython
+Requires-Dist: Cython; extra == "cython"
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file

selectolax-0.3.34.dist-info/RECORD

@@ -0,0 +1,26 @@
+selectolax/__init__.py,sha256=iI6pQ10gimevS2gTf4K4_1cXh4NBRFj_5GjkmhrvU94,157
+selectolax/base.pxi,sha256=zOj3BrCA71xd-mJFtkMIAglP4ZybfrHVoCoy6ljTBDQ,93
+selectolax/lexbor.c,sha256=ohdT--aXa69etvB2pMZU-vBU8P0urBCVeNIsKJzIe3k,2419508
+selectolax/lexbor.cp310-win_amd64.pyd,sha256=h0bKQ_UgJiQ8nkBlSwF_woJ3to9gOZE5KwLC5XaxL68,3149312
+selectolax/lexbor.pxd,sha256=BcqAzhlUVq0GVWiJHWXNhs4jY-gi6k0BELEnQtSYJAI,21720
+selectolax/lexbor.pyi,sha256=dRNzLXJEbFRR7QcItuX8Ews9E9I6h6G4vA3X1hijzj4,28990
+selectolax/lexbor.pyx,sha256=XLZ2vGwLoWdctnmU-gfizjD6tMjehR_bzNOapDJ_YOQ,12891
+selectolax/parser.c,sha256=E6Jy4u2RriHcudgyhxtAxpEyCvwH3lPxxjPIfemuK7A,2259306
+selectolax/parser.cp310-win_amd64.pyd,sha256=MZlpP-wdrtOC8wNs18WhA8lF5IfLXn1_xGziFYR4ZMw,2105344
+selectolax/parser.pxd,sha256=T7GoQdaOkhp_W2TBlRY0tZqom97PkHrytYaXQlyVnbI,25196
+selectolax/parser.pyi,sha256=-qutpjrK1dD4rrl3SsHWQt2FT5lv6meaACkQzk1Bt6o,25612
+selectolax/parser.pyx,sha256=nIWuhaEFRwlfo64WmgrSOM0A8mUw0eWw9j_fWyLV-Ro,14127
+selectolax/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+selectolax/utils.pxi,sha256=hkzKfycdpwH1P-E_pP-9NTGsmiajt6EJNZSlkxlRapA,3623
+selectolax/lexbor/attrs.pxi,sha256=d59V77aGkpp7YsYsd6t_z4-tRnUoQTJZKsvMC8nyttM,3978
+selectolax/lexbor/node.pxi,sha256=KODqPk3yZ_owwdSxqNr2Ih6qAOhu9CJ-jrHtqQJcWmY,33407
+selectolax/lexbor/selection.pxi,sha256=BeUDypw5_P0CTmi-ACLcd7pK2NnG9ASrwWOdLdweAZY,7378
+selectolax/lexbor/util.pxi,sha256=q2EYVNdnROg9y30mWpGwlNA0W00nJ7ZRNEEDrOEG14s,584
+selectolax/modest/node.pxi,sha256=iX_yRPIPVkG0ALW7hEfmXiVperw6RjkSGATkxzLokz0,34691
+selectolax/modest/selection.pxi,sha256=PfHUN1uuNA7YfcxTu7JZjhxevVbFRP1bHd3kyyFdO7E,6703
+selectolax/modest/util.pxi,sha256=zab67Wzo8FcipA2VS8ClptaC19lZirbNqFEGQ3hW2Is,572
+selectolax-0.3.34.dist-info/licenses/LICENSE,sha256=A7Jb3WZcENcLfZRc7QPdm9zJdwfpIyPodPJu-kdMH6E,1087
+selectolax-0.3.34.dist-info/METADATA,sha256=rAqskRB9wMSn7tEZLxZswUJD4wFzN4fizyXjiBv4L4o,1318
+selectolax-0.3.34.dist-info/WHEEL,sha256=KUuBC6lxAbHCKilKua8R9W_TM71_-9Sg5uEP3uDWcoU,101
+selectolax-0.3.34.dist-info/top_level.txt,sha256=e5MuEM2PrQzoDlWetkFli9uXSlxa_ktW5jJEihhaI1c,11
+selectolax-0.3.34.dist-info/RECORD,,

selectolax-0.3.32.dist-info/METADATA

@@ -1,187 +0,0 @@
-Metadata-Version: 2.4
-Name: selectolax
-Version: 0.3.32
-Summary: Fast HTML5 parser with CSS selectors.
-Home-page: https://github.com/rushter/selectolax
-Author: Artem Golubin
-Author-email: Artem Golubin <me@rushter.com>
-License: MIT
-Project-URL: Repository, https://github.com/rushter/selectolax
-Project-URL: Documentation, https://selectolax.readthedocs.io/en/latest/parser.html
-Project-URL: Changelog, https://github.com/rushter/selectolax/blob/main/CHANGES.rst
-Keywords: selectolax,html,parser,css,fast
-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: 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
-Requires-Python: >=3.9
-Description-Content-Type: text/x-rst
-License-File: LICENSE
-Provides-Extra: cython
-Requires-Dist: Cython; extra == "cython"
-Dynamic: author
-Dynamic: home-page
-Dynamic: license-file
-
-.. 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 <https://selectolax.readthedocs.io/en/latest/index.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 <https://lexborisov.github.io/benchmark-html-parsers/>`_
-*  `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-0.3.32.dist-info/RECORD

@@ -1,26 +0,0 @@
-selectolax/__init__.py,sha256=-HUZIEaQkWhTkyAc3ZYkjSig-PwZhip6R_VUo5KmwKk,185
-selectolax/base.pxi,sha256=zOj3BrCA71xd-mJFtkMIAglP4ZybfrHVoCoy6ljTBDQ,93
-selectolax/lexbor.c,sha256=rvkQp6ZbkbXMmMBAZXNY8U8UBD41YbE60kwHji94CSk,2419967
-selectolax/lexbor.cp310-win_amd64.pyd,sha256=VNaCjknrMwgxtzXQu_ImIPyhw8HLm0N73i4Q64cNcuI,3144192
-selectolax/lexbor.pxd,sha256=cG264E-tFNOFTy0k5bAqV_sZnz4G6a4a21WEhqTL-NI,21516
-selectolax/lexbor.pyi,sha256=NS2pI6PL7klkk6xXThHE72Jsi8583xLUdQ6gvCAQovY,27028
-selectolax/lexbor.pyx,sha256=-O-g03mLCQKc9F19eMvo3PyoLDtF09IIuFziXJAl6Ao,11520
-selectolax/parser.c,sha256=xGQmCxrEmyQCi9I11d3py7cIcFumqhhVpdystsQ1dp0,2287084
-selectolax/parser.cp310-win_amd64.pyd,sha256=t_VCxIXCbrQmzz087ukSMGpnXUDxGWpReztFfOqrp6w,2108416
-selectolax/parser.pxd,sha256=4pM_CcZlvJlaR8EMjZCnSmnCcJbwcYOldRTBEbfwm48,25145
-selectolax/parser.pyi,sha256=5Czf63278MQC01IxY-CHzoDyTS1oHiYRD2OxEscyL1o,25584
-selectolax/parser.pyx,sha256=bS2n70o_5OPJ6JuXTBAVUTc-XhxqC4DXzPE4H3-e5Ek,13987
-selectolax/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-selectolax/utils.pxi,sha256=4rtdRcLWuemxN1qe7Eul5jvAmHZ65r7Gvf67_Wg8Bt4,3566
-selectolax/lexbor/attrs.pxi,sha256=KvQaCo0jM3Bva6_xG3TGzkCVFjNQ4kgTxWO95gsGbkw,4007
-selectolax/lexbor/node.pxi,sha256=BuJIYcTUucvHUP4w2wl90uBwjcqpv1vRyt4No2O_Quo,30921
-selectolax/lexbor/selection.pxi,sha256=4I8cjYMjC2Gz7xLrYWrl7jbnwDoVmab-GvrJKiTALTI,7017
-selectolax/lexbor/util.pxi,sha256=0I4ElWIwXxrZCfMmGCtyDU127oMsPCqC3IcUk4QmMAc,582
-selectolax/modest/node.pxi,sha256=Da2b3cdmggCX736x0htGvac51SEeGCcY5l-LA5H4HNI,34376
-selectolax/modest/selection.pxi,sha256=0elY7JwnpPVaw0QZE1T7A78s9FIph5uWIhwy4sEXGU8,6586
-selectolax/modest/util.pxi,sha256=o2nPGGGtRlLqOCa7yPk94CfBzNlVr7ull7osFy6NRX4,570
-selectolax-0.3.32.dist-info/licenses/LICENSE,sha256=A7Jb3WZcENcLfZRc7QPdm9zJdwfpIyPodPJu-kdMH6E,1087
-selectolax-0.3.32.dist-info/METADATA,sha256=mB27GyUKzOKfZK92CEHDlQ6wrwG1um9kesSgMr8yb1c,6402
-selectolax-0.3.32.dist-info/WHEEL,sha256=KUuBC6lxAbHCKilKua8R9W_TM71_-9Sg5uEP3uDWcoU,101
-selectolax-0.3.32.dist-info/top_level.txt,sha256=e5MuEM2PrQzoDlWetkFli9uXSlxa_ktW5jJEihhaI1c,11
-selectolax-0.3.32.dist-info/RECORD,,