selectolax 0.3.33__cp313-cp313-win_amd64.whl → 0.4.0__cp313-cp313-win_amd64.whl

selectolax/lexbor.pxd

@@ -215,6 +215,8 @@ cdef extern from "lexbor/html/html.h" nogil:
 
         size_t  ref_count
 
+    ctypedef struct lxb_html_element_t
+
     # Functions
     lxb_html_document_t * lxb_html_document_create()
     lxb_status_t lxb_html_document_parse(lxb_html_document_t *document,  const lxb_char_t *html, size_t size)
@@ -223,6 +225,9 @@ cdef extern from "lexbor/html/html.h" nogil:
     lxb_dom_element_t * lxb_dom_document_element(lxb_dom_document_t *document)
 
     lxb_status_t lxb_html_serialize_tree_str(lxb_dom_node_t *node, lexbor_str_t *str)
+    lxb_status_t lxb_html_serialize_deep_str(lxb_dom_node_t *node, lexbor_str_t *str)
+    lxb_html_element_t* lxb_html_element_inner_html_set(lxb_html_element_t *element,
+                                                        const lxb_char_t *html, size_t size)
 
 cdef class LexborNode:
     cdef:
@@ -241,6 +246,8 @@ cdef class LexborCSSSelector:
     cdef public LexborNode current_node
     cdef int _create_css_parser(self) except -1
     cpdef list find(self, str query, LexborNode node)
+    cpdef list find_first(self, str query, LexborNode node)
+    cpdef list _find(self, str query, LexborNode node, bint only_first)
     cpdef int any_matches(self, str query, LexborNode node) except -1
 
 cdef class LexborHTMLParser:
@@ -318,6 +325,7 @@ cdef extern from "lexbor/dom/dom.h" nogil:
     void lxb_dom_node_insert_after(lxb_dom_node_t *to, lxb_dom_node_t *node)
     lxb_dom_text_t * lxb_dom_document_create_text_node(lxb_dom_document_t *document, const lxb_char_t *data, size_t len)
     void lxb_dom_node_simple_walk(lxb_dom_node_t *root, lxb_dom_node_simple_walker_f walker_cb, void *ctx)
+    lxb_dom_node_t* lxb_dom_node_clone(lxb_dom_node_t *node, bint deep)
 
 
 cdef extern from "lexbor/dom/interfaces/element.h" nogil:

selectolax/lexbor.pyi

@@ -71,6 +71,34 @@ class LexborSelector:
         """
         ...
 
+    @property
+    def inner_html(self) -> str | None:
+        """Return HTML representation of the child nodes.
+
+        Works similar to innerHTML in JavaScript.
+        Unlike the `.html` property, does not include the current node.
+        Can be used to set HTML as well. See the setter docstring.
+
+        Returns
+        -------
+        text : str or None
+        """
+        ...
+
+    @inner_html.setter
+    def inner_html(self, html: str):
+        """Set inner HTML to the specified HTML.
+
+        Replaces existing data inside the node.
+        Works similar to innerHTML in JavaScript.
+
+        Parameters
+        ----------
+        html : str
+
+        """
+        ...
+
 class LexborCSSSelector:
     def __init__(self): ...
     def find(self, query: str, node: LexborNode) -> list[LexborNode]: ...
@@ -84,7 +112,10 @@ class LexborNode:
     def mem_id(self) -> int: ...
     @property
     def child(self) -> LexborNode | None:
-        """Alias for the first_child property."""
+        """Alias for the `first_child` property.
+
+        **Deprecated**. Please use `first_child` instead.
+        """
         ...
     @property
     def first_child(self) -> LexborNode | None:
@@ -145,6 +176,12 @@ class LexborNode:
         Matches pattern `query` against HTML tree.
         `CSS selectors reference <https://www.w3schools.com/cssref/css_selectors.asp>`_.
 
+        Special selectors:
+
+         - parser.css('p:lexbor-contains("awesome" i)') -- case-insensitive contains
+         - parser.css('p:lexbor-contains("awesome")') -- case-sensitive contains
+
+
         Parameters
         ----------
         query : str
@@ -167,7 +204,7 @@ class LexborNode:
         query : str
         default : bool, default None
             Default value to return if there is no match.
-        strict: bool, default True
+        strict: bool, default False
             Set to True if you want to check if there is strictly only one match in the document.
 
 
@@ -188,7 +225,7 @@ class LexborNode:
         query : str
         default : bool, default None
             Default value to return if there is no match.
-        strict: bool, default True
+        strict: bool, default False
             Set to True if you want to check if there is strictly only one match in the document.
 
 
@@ -209,7 +246,7 @@ class LexborNode:
         query : str
         default : bool, default None
             Default value to return if there is no match.
-        strict: bool, default True
+        strict: bool, default False
             Set to True if you want to check if there is strictly only one match in the document.
 
 
@@ -230,6 +267,12 @@ class LexborNode:
     def tag(self) -> str | None:
         """Return the name of the current tag (e.g. div, p, img).
 
+        For for non-tag nodes, returns the following names:
+
+         * `-text` - text node
+         * `-document` - document node
+         * `-comment` - comment node
+
         Returns
         -------
         text : str
@@ -345,6 +388,8 @@ class LexborNode:
     def unwrap(self, delete_empty: bool = False) -> None:
         """Replace node with whatever is inside this node.
 
+        Does nothing if you perform unwrapping second time on the same node.
+
         Parameters
         ----------
         delete_empty : bool, default False
@@ -602,6 +647,44 @@ class LexborNode:
         """
         ...
 
+    @property
+    def inner_html(self) -> str | None:
+        """Return HTML representation of the child nodes.
+
+        Works similar to innerHTML in JavaScript.
+        Unlike the `.html` property, does not include the current node.
+        Can be used to set HTML as well. See the setter docstring.
+
+        Returns
+        -------
+        text : str or None
+        """
+        ...
+
+    @inner_html.setter
+    def inner_html(self, html: str):
+        """Set inner HTML to the specified HTML.
+
+        Replaces existing data inside the node.
+        Works similar to innerHTML in JavaScript.
+
+        Parameters
+        ----------
+        html : str
+
+        """
+        ...
+
+    def clone(self) -> LexborNode:
+        """Clone the current node.
+
+        You can use to do temporary modifications without affecting the original HTML tree.
+
+        It is tied to the current parser instance.
+        Gets destroyed when parser instance is destroyed.
+        """
+        ...
+
 class LexborHTMLParser:
     """The lexbor HTML parser.
 
@@ -665,6 +748,12 @@ class LexborHTMLParser:
         Matches pattern `query` against HTML tree.
         `CSS selectors reference <https://www.w3schools.com/cssref/css_selectors.asp>`_.
 
+        Special selectors:
+
+         - parser.css('p:lexbor-contains("awesome" i)') -- case-insensitive contains
+         - parser.css('p:lexbor-contains("awesome")') -- case-sensitive contains
+
+
         Parameters
         ----------
         query : str
@@ -687,7 +776,7 @@ class LexborHTMLParser:
         query : str
         default : bool, default None
             Default value to return if there is no match.
-        strict: bool, default True
+        strict: bool, default False
             Set to True if you want to check if there is strictly only one match in the document.
 
 
@@ -708,7 +797,7 @@ class LexborHTMLParser:
         query : str
         default : bool, default None
             Default value to return if there is no match.
-        strict: bool, default True
+        strict: bool, default False
             Set to True if you want to check if there is strictly only one match in the document.
 
 
@@ -729,7 +818,7 @@ class LexborHTMLParser:
         query : str
         default : bool, default None
             Default value to return if there is no match.
-        strict: bool, default True
+        strict: bool, default False
             Set to True if you want to check if there is strictly only one match in the document.
 
 

selectolax/lexbor.pyx

@@ -1,6 +1,7 @@
 from cpython.bool cimport bool
 from cpython.exc cimport PyErr_SetObject
 
+
 _ENCODING = 'UTF-8'
 
 include "base.pxi"
@@ -9,6 +10,7 @@ include "lexbor/attrs.pxi"
 include "lexbor/node.pxi"
 include "lexbor/selection.pxi"
 include "lexbor/util.pxi"
+include "lexbor/node_remove.pxi"
 
 # We don't inherit from HTMLParser here, because it also includes all the C code from Modest.
 
@@ -169,6 +171,11 @@ cdef class LexborHTMLParser:
         Matches pattern `query` against HTML tree.
         `CSS selectors reference <https://www.w3schools.com/cssref/css_selectors.asp>`_.
 
+        Special selectors:
+
+         - parser.css('p:lexbor-contains("awesome" i)') -- case-insensitive contains
+         - parser.css('p:lexbor-contains("awesome")') -- case-sensitive contains
+
         Parameters
         ----------
         query : str
@@ -187,9 +194,9 @@ cdef class LexborHTMLParser:
         ----------
 
         query : str
-        default : bool, default None
+        default : Any, default None
             Default value to return if there is no match.
-        strict: bool, default True
+        strict: bool, default False
             Set to True if you want to check if there is strictly only one match in the document.
 
 
@@ -206,7 +213,7 @@ cdef class LexborHTMLParser:
         ----------
         tags : list of str
             List of tags to remove.
-        recursive : bool, default True
+        recursive : bool, default False
             Whenever to delete all its child nodes
 
         Examples
@@ -329,7 +336,13 @@ cdef class LexborHTMLParser:
         return obj
 
     def clone(self):
-        """Clone the current tree."""
+        """Clone the current node.
+
+        You can use to do temporary modifications without affecting the original HTML tree.
+
+        It is tied to the current parser instance.
+        Gets destroyed when parser instance is destroyed.
+        """
         cdef lxb_html_document_t* cloned_document
         cdef lxb_dom_node_t* cloned_node
         cdef LexborHTMLParser cls
@@ -381,3 +394,31 @@ cdef class LexborHTMLParser:
         # faster to check if the document is empty which should determine if we have a root
         if self.document != NULL:
             self.root.unwrap_tags(tags, delete_empty=delete_empty)
+
+    @property
+    def inner_html(self) -> str:
+        """Return HTML representation of the child nodes.
+
+        Works similar to innerHTML in JavaScript.
+        Unlike the `.html` property, does not include the current node.
+        Can be used to set HTML as well. See the setter docstring.
+
+        Returns
+        -------
+        text : str | None
+        """
+        return self.root.inner_html
+
+    @inner_html.setter
+    def inner_html(self, str html):
+        """Set inner HTML to the specified HTML.
+
+        Replaces existing data inside the node.
+        Works similar to innerHTML in JavaScript.
+
+        Parameters
+        ----------
+        html : str
+
+        """
+        self.root.inner_html = html

selectolax/modest/node.pxi

@@ -397,7 +397,10 @@ cdef class Node:
 
     @property
     def child(self):
-        """Return the child node."""
+        """Alias for the `first_child` property.
+
+        **Deprecated**. Please use `first_child` instead.
+        """
         cdef Node node
         if self.node.child:
             node = Node.new(self.node.child, self.parser)