selectolax 0.3.25__cp311-cp311-win_amd64.whl → 0.3.27__cp311-cp311-win_amd64.whl

selectolax/__init__.py

@@ -3,7 +3,7 @@
 
 __author__ = """Artem Golubin"""
 __email__ = 'me@rushter.com'
-__version__ = '0.3.25'
+__version__ = '0.3.27'
 
 from . import parser
 from . import lexbor

selectolax/lexbor.c

@@ -3489,7 +3489,6 @@ static const char __pyx_k_AssertionError[] = "AssertionError";
 static const char __pyx_k_LexborNode_css[] = "LexborNode.css";
 static const char __pyx_k_LexborSelector[] = "LexborSelector";
 static const char __pyx_k_fused_sigindex[] = "_fused_sigindex";
-static const char __pyx_k_html_body_head[] = "<html|<body|<head";
 static const char __pyx_k_parse_fragment[] = "parse_fragment";
 static const char __pyx_k_LexborNode_iter[] = "LexborNode.iter";
 static const char __pyx_k_LexborNode_text[] = "LexborNode.text";
@@ -3513,6 +3512,7 @@ static const char __pyx_k_LexborNode_unwrap[] = "LexborNode.unwrap";
 static const char __pyx_k_any_text_contains[] = "any_text_contains";
 static const char __pyx_k_do_parse_fragment[] = "do_parse_fragment";
 static const char __pyx_k_get_fragment_type[] = "get_fragment_type";
+static const char __pyx_k_html_body_head_er[] = "<html|<body|<head(?!er)";
 static const char __pyx_k_selectolax_lexbor[] = "selectolax.lexbor";
 static const char __pyx_k_Can_t_extract_text[] = "Can't extract text";
 static const char __pyx_k_LexborSelector_css[] = "LexborSelector.css";
@@ -4155,7 +4155,7 @@ typedef struct {
   PyObject *__pyx_n_u_head_and_body;
   PyObject *__pyx_n_s_html;
   PyObject *__pyx_kp_u_html_2;
-  PyObject *__pyx_kp_u_html_body_head;
+  PyObject *__pyx_kp_u_html_body_head_er;
   PyObject *__pyx_n_s_html_len;
   PyObject *__pyx_n_s_html_re;
   PyObject *__pyx_n_s_i;
@@ -4719,7 +4719,7 @@ static int __pyx_m_clear(PyObject *m) {
   Py_CLEAR(clear_module_state->__pyx_n_u_head_and_body);
   Py_CLEAR(clear_module_state->__pyx_n_s_html);
   Py_CLEAR(clear_module_state->__pyx_kp_u_html_2);
-  Py_CLEAR(clear_module_state->__pyx_kp_u_html_body_head);
+  Py_CLEAR(clear_module_state->__pyx_kp_u_html_body_head_er);
   Py_CLEAR(clear_module_state->__pyx_n_s_html_len);
   Py_CLEAR(clear_module_state->__pyx_n_s_html_re);
   Py_CLEAR(clear_module_state->__pyx_n_s_i);
@@ -5261,7 +5261,7 @@ static int __pyx_m_traverse(PyObject *m, visitproc visit, void *arg) {
   Py_VISIT(traverse_module_state->__pyx_n_u_head_and_body);
   Py_VISIT(traverse_module_state->__pyx_n_s_html);
   Py_VISIT(traverse_module_state->__pyx_kp_u_html_2);
-  Py_VISIT(traverse_module_state->__pyx_kp_u_html_body_head);
+  Py_VISIT(traverse_module_state->__pyx_kp_u_html_body_head_er);
   Py_VISIT(traverse_module_state->__pyx_n_s_html_len);
   Py_VISIT(traverse_module_state->__pyx_n_s_html_re);
   Py_VISIT(traverse_module_state->__pyx_n_s_i);
@@ -5903,7 +5903,7 @@ static int __pyx_m_traverse(PyObject *m, visitproc visit, void *arg) {
 #define __pyx_n_u_head_and_body __pyx_mstate_global->__pyx_n_u_head_and_body
 #define __pyx_n_s_html __pyx_mstate_global->__pyx_n_s_html
 #define __pyx_kp_u_html_2 __pyx_mstate_global->__pyx_kp_u_html_2
-#define __pyx_kp_u_html_body_head __pyx_mstate_global->__pyx_kp_u_html_body_head
+#define __pyx_kp_u_html_body_head_er __pyx_mstate_global->__pyx_kp_u_html_body_head_er
 #define __pyx_n_s_html_len __pyx_mstate_global->__pyx_n_s_html_len
 #define __pyx_n_s_html_re __pyx_mstate_global->__pyx_n_s_html_re
 #define __pyx_n_s_i __pyx_mstate_global->__pyx_n_s_i
@@ -7293,7 +7293,7 @@ static PyObject *__pyx_pf_10selectolax_6lexbor_4get_fragment_type(CYTHON_UNUSED
  *         tree = parser_cls(html)
  * 
  *     import re             # <<<<<<<<<<<<<<
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
  * 
  */
   __pyx_t_3 = __Pyx_ImportDottedModule(__pyx_n_s_re, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 36, __pyx_L1_error)
@@ -7304,7 +7304,7 @@ static PyObject *__pyx_pf_10selectolax_6lexbor_4get_fragment_type(CYTHON_UNUSED
   /* "selectolax/utils.pxi":37
  * 
  *     import re
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)             # <<<<<<<<<<<<<<
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)             # <<<<<<<<<<<<<<
  * 
  *     has_html = False
  */
@@ -7327,7 +7327,7 @@ static PyObject *__pyx_pf_10selectolax_6lexbor_4get_fragment_type(CYTHON_UNUSED
   }
   #endif
   {
-    PyObject *__pyx_callargs[3] = {__pyx_t_7, __pyx_kp_u_html_body_head, __pyx_t_5};
+    PyObject *__pyx_callargs[3] = {__pyx_t_7, __pyx_kp_u_html_body_head_er, __pyx_t_5};
     __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_4, __pyx_callargs+1-__pyx_t_6, 2+__pyx_t_6);
     __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0;
     __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0;
@@ -7339,7 +7339,7 @@ static PyObject *__pyx_pf_10selectolax_6lexbor_4get_fragment_type(CYTHON_UNUSED
   __pyx_t_3 = 0;
 
   /* "selectolax/utils.pxi":39
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
  * 
  *     has_html = False             # <<<<<<<<<<<<<<
  *     has_head = False
@@ -33914,7 +33914,7 @@ static PyObject *__pyx_pf_10selectolax_6lexbor_12get_fragment_type(CYTHON_UNUSED
  *         tree = parser_cls(html)
  * 
  *     import re             # <<<<<<<<<<<<<<
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
  * 
  */
   __pyx_t_3 = __Pyx_ImportDottedModule(__pyx_n_s_re, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(8, 36, __pyx_L1_error)
@@ -33925,7 +33925,7 @@ static PyObject *__pyx_pf_10selectolax_6lexbor_12get_fragment_type(CYTHON_UNUSED
   /* "selectolax/utils.pxi":37
  * 
  *     import re
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)             # <<<<<<<<<<<<<<
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)             # <<<<<<<<<<<<<<
  * 
  *     has_html = False
  */
@@ -33948,7 +33948,7 @@ static PyObject *__pyx_pf_10selectolax_6lexbor_12get_fragment_type(CYTHON_UNUSED
   }
   #endif
   {
-    PyObject *__pyx_callargs[3] = {__pyx_t_7, __pyx_kp_u_html_body_head, __pyx_t_5};
+    PyObject *__pyx_callargs[3] = {__pyx_t_7, __pyx_kp_u_html_body_head_er, __pyx_t_5};
     __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_4, __pyx_callargs+1-__pyx_t_6, 2+__pyx_t_6);
     __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0;
     __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0;
@@ -33960,7 +33960,7 @@ static PyObject *__pyx_pf_10selectolax_6lexbor_12get_fragment_type(CYTHON_UNUSED
   __pyx_t_3 = 0;
 
   /* "selectolax/utils.pxi":39
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
  * 
  *     has_html = False             # <<<<<<<<<<<<<<
  *     has_head = False
@@ -43674,7 +43674,7 @@ static int __Pyx_CreateStringTabAndInitStrings(void) {
     {&__pyx_n_u_head_and_body, __pyx_k_head_and_body, sizeof(__pyx_k_head_and_body), 0, 1, 0, 1},
     {&__pyx_n_s_html, __pyx_k_html, sizeof(__pyx_k_html), 0, 0, 1, 1},
     {&__pyx_kp_u_html_2, __pyx_k_html_2, sizeof(__pyx_k_html_2), 0, 1, 0, 0},
-    {&__pyx_kp_u_html_body_head, __pyx_k_html_body_head, sizeof(__pyx_k_html_body_head), 0, 1, 0, 0},
+    {&__pyx_kp_u_html_body_head_er, __pyx_k_html_body_head_er, sizeof(__pyx_k_html_body_head_er), 0, 1, 0, 0},
     {&__pyx_n_s_html_len, __pyx_k_html_len, sizeof(__pyx_k_html_len), 0, 0, 1, 1},
     {&__pyx_n_s_html_re, __pyx_k_html_re, sizeof(__pyx_k_html_re), 0, 0, 1, 1},
     {&__pyx_n_s_i, __pyx_k_i, sizeof(__pyx_k_i), 0, 0, 1, 1},

selectolax/lexbor.pyi

@@ -1,14 +1,27 @@
-from typing import Iterator, TypeVar, NoReturn
+from typing import Any, Iterator, Literal, TypeVar, NoReturn, overload
 
 DefaultT = TypeVar("DefaultT")
 
 class LexborAttributes:
     @staticmethod
-    def create(node: "LexborAttributes") -> "LexborAttributes": ...
+    def create(node: LexborAttributes) -> LexborAttributes: ...
     def keys(self) -> Iterator[str]: ...
-    def items(self) -> Iterator[tuple[str, str]]: ...
-    def values(self) -> Iterator[str]: ...
-    def get(self, key: str, default: DefaultT | None = None) -> str | DefaultT | None: ...
+    def items(self) -> Iterator[tuple[str, str | None]]: ...
+    def values(self) -> Iterator[str | None]: ...
+    def __iter__(self) -> Iterator[str]: ...
+    def __len__(self) -> int: ...
+    def __getitem__(self, key: str) -> str | None: ...
+    def __setitem__(self, key: str, value: str) -> None: ...
+    def __delitem__(self, key: str) -> None: ...
+    def __contains__(self, key: str) -> bool: ...
+    def __repr__(self) -> str: ...
+    @overload
+    def get(self, key: str, default: DefaultT) -> DefaultT | str | None: ...
+    @overload
+    def get(self, key: str, default: None = ...) -> str | None: ...
+    @overload
+    def sget(self, key: str, default: str | DefaultT) -> str | DefaultT: ...
+    @overload
     def sget(self, key: str, default: str = "") -> str: ...
 
 class LexborSelector:
@@ -20,38 +33,38 @@ class LexborSelector:
     def any_matches(self) -> bool: ...
     def text_contains(
         self, text: str, deep: bool = True, separator: str = "", strip: bool = False
-    ) -> "LexborSelector": ...
+    ) -> LexborSelector: ...
     def any_text_contains(
         self, text: str, deep: bool = True, separator: str = "", strip: bool = False
     ) -> bool: ...
     def attribute_longer_than(
         self, attribute: str, length: int, start: str | None = None
-    ) -> "LexborSelector": ...
+    ) -> LexborSelector: ...
     def any_attribute_longer_than(
         self, attribute: str, length: int, start: str | None = None
     ) -> bool: ...
 
 class LexborCSSSelector:
     def __init__(self): ...
-    def find(self, query: str, node: "LexborNode") -> list["LexborNode"]: ...
-    def any_matches(self, query: str, node: "LexborNode") -> bool: ...
+    def find(self, query: str, node: LexborNode) -> list[LexborNode]: ...
+    def any_matches(self, query: str, node: LexborNode) -> bool: ...
 
 class LexborNode:
-    parser: "LexborHTMLParser"
+    parser: LexborHTMLParser
     @property
     def mem_id(self) -> int: ...
     @property
-    def child(self) -> None | "LexborNode": ...
+    def child(self) -> LexborNode | None: ...
     @property
-    def first_child(self) -> None | "LexborNode": ...
+    def first_child(self) -> LexborNode | None: ...
     @property
-    def parent(self) -> None | "LexborNode": ...
+    def parent(self) -> LexborNode | None: ...
     @property
-    def next(self) -> None | "LexborNode": ...
+    def next(self) -> LexborNode | None: ...
     @property
-    def prev(self) -> None | "LexborNode": ...
+    def prev(self) -> LexborNode | None: ...
     @property
-    def last_child(self) -> None | "LexborNode": ...
+    def last_child(self) -> LexborNode | None: ...
     @property
     def html(self) -> str | None: ...
     def __hash__(self) -> int: ...
@@ -59,10 +72,19 @@ class LexborNode:
     def text(
         self, deep: bool = True, separator: str = "", strip: bool = False
     ) -> str: ...
-    def css(self, query: str) -> list["LexborNode"]: ...
+    def css(self, query: str) -> list[LexborNode]: ...
+    @overload
     def css_first(
-        self, query: str, default: DefaultT | None = None, strict: bool = False
-    ) -> "LexborNode" | DefaultT | None: ...
+        self, query: str, default: Any = ..., strict: Literal[True] = ...
+    ) -> LexborNode: ...
+    @overload
+    def css_first(
+        self, query: str, default: DefaultT, strict: bool = False
+    ) -> LexborNode | DefaultT: ...
+    @overload
+    def css_first(
+        self, query: str, default: None = ..., strict: bool = False
+    ) -> LexborNode | None: ...
     def any_css_matches(self, selectors: tuple[str]) -> bool: ...
     def css_matches(self, selector: str) -> bool: ...
     @property
@@ -74,23 +96,23 @@ class LexborNode:
     @property
     def attributes(self) -> dict[str, str | None]: ...
     @property
-    def attrs(self) -> "LexborAttributes": ...
+    def attrs(self) -> LexborAttributes: ...
     @property
-    def id(self) -> None | str: ...
-    def iter(self, include_text: bool = False) -> Iterator["LexborNode"]: ...
+    def id(self) -> str | None: ...
+    def iter(self, include_text: bool = False) -> Iterator[LexborNode]: ...
     def unwrap(self) -> None: ...
     def unwrap_tags(self, tags: list[str]) -> None: ...
-    def traverse(self, include_text: bool = False) -> Iterator["LexborNode"]: ...
-    def replace_with(self, value: bytes | str | "LexborNode") -> None: ...
-    def insert_before(self, value: bytes | str | "LexborNode") -> None: ...
-    def insert_after(self, value: bytes | str | "LexborNode") -> None: ...
-    def insert_child(self, value: bytes | str | "LexborNode") -> None: ...
+    def traverse(self, include_text: bool = False) -> Iterator[LexborNode]: ...
+    def replace_with(self, value: bytes | str | LexborNode) -> None: ...
+    def insert_before(self, value: bytes | str | LexborNode) -> None: ...
+    def insert_after(self, value: bytes | str | LexborNode) -> None: ...
+    def insert_child(self, value: bytes | str | LexborNode) -> None: ...
     @property
     def raw_value(self) -> NoReturn: ...
     def scripts_contain(self, query: str) -> bool: ...
     def scripts_srcs_contain(self, queries: tuple[str]) -> bool: ...
     def remove(self, recursive: bool = True) -> None: ...
-    def select(self, query: str | None = None) -> "LexborSelector": ...
+    def select(self, query: str | None = None) -> LexborSelector: ...
     @property
     def text_content(self) -> str | None: ...
 
@@ -99,38 +121,47 @@ class LexborHTMLParser:
     @property
     def selector(self) -> "LexborCSSSelector": ...
     @property
-    def root(self) -> "LexborNode" | None: ...
+    def root(self) -> LexborNode | None: ...
     @property
-    def body(self) -> "LexborNode" | None: ...
+    def body(self) -> LexborNode | None: ...
     @property
-    def head(self) -> None | "LexborNode": ...
-    def tags(self, name: str) -> list["LexborNode"]: ...
+    def head(self) -> LexborNode | None: ...
+    def tags(self, name: str) -> list[LexborNode]: ...
     def text(
         self, deep: bool = True, separator: str = "", strip: bool = False
     ) -> str: ...
     @property
-    def html(self) -> None | str: ...
-    def css(self, query: str) -> list["LexborNode"]: ...
+    def html(self) -> str | None: ...
+    def css(self, query: str) -> list[LexborNode]: ...
+    @overload
+    def css_first(
+        self, query: str, default: Any = ..., strict: Literal[True] = ...
+    ) -> LexborNode: ...
+    @overload
+    def css_first(
+        self, query: str, default: DefaultT, strict: bool = False
+    ) -> LexborNode | DefaultT: ...
+    @overload
     def css_first(
-        self, query: str, default: DefaultT | None = None, strict: bool = False
-    ) -> "LexborNode" | DefaultT | None : ...
+        self, query: str, default: None = ..., strict: bool = False
+    ) -> LexborNode | None: ...
     def strip_tags(self, tags: list[str], recursive: bool = False) -> None: ...
-    def select(self, query: str | None = None) -> "LexborSelector" | None: ...
+    def select(self, query: str | None = None) -> LexborSelector | None: ...
     def any_css_matches(self, selectors: tuple[str]) -> bool: ...
     def scripts_contain(self, query: str) -> bool: ...
     def scripts_srcs_contain(self, queries: tuple[str]) -> bool: ...
     def css_matches(self, selector: str) -> bool: ...
-    def clone(self) -> "LexborHTMLParser": ...
+    def clone(self) -> LexborHTMLParser: ...
     def unwrap_tags(self, tags: list[str]) -> None: ...
 
-def create_tag(tag: str) -> "LexborNode":
+def create_tag(tag: str) -> LexborNode:
     """
     Given an HTML tag name, e.g. `"div"`, create a single empty node for that tag,
     e.g. `"<div></div>"`.
     """
     ...
 
-def parse_fragment(html: str) -> list["LexborNode"]:
+def parse_fragment(html: str) -> list[LexborNode]:
     """
     Given HTML, parse it into a list of Nodes, such that the nodes
     correspond to the given HTML.

selectolax/parser.c

@@ -3476,7 +3476,6 @@ static const char __pyx_k_HTMLParser_css[] = "HTMLParser.css";
 static const char __pyx_k_Node_css_first[] = "Node.css_first";
 static const char __pyx_k_Node_decompose[] = "Node.decompose";
 static const char __pyx_k_fused_sigindex[] = "_fused_sigindex";
-static const char __pyx_k_html_body_head[] = "<html|<body|<head";
 static const char __pyx_k_parse_fragment[] = "parse_fragment";
 static const char __pyx_k_Attributes_keys[] = "_Attributes.keys";
 static const char __pyx_k_Attributes_sget[] = "_Attributes.sget";
@@ -3507,6 +3506,7 @@ static const char __pyx_k_Node_replace_with[] = "Node.replace_with";
 static const char __pyx_k_any_text_contains[] = "any_text_contains";
 static const char __pyx_k_do_parse_fragment[] = "do_parse_fragment";
 static const char __pyx_k_get_fragment_type[] = "get_fragment_type";
+static const char __pyx_k_html_body_head_er[] = "<html|<body|<head(?!er)";
 static const char __pyx_k_selectolax_parser[] = "selectolax.parser";
 static const char __pyx_k_Can_t_parse_HTML_s[] = "Can't parse HTML:\n%s";
 static const char __pyx_k_HTMLParser_chars_s[] = "<HTMLParser chars=%s>";
@@ -4113,7 +4113,7 @@ typedef struct {
   PyObject *__pyx_n_u_head_and_body;
   PyObject *__pyx_n_s_html;
   PyObject *__pyx_kp_u_html_2;
-  PyObject *__pyx_kp_u_html_body_head;
+  PyObject *__pyx_kp_u_html_body_head_er;
   PyObject *__pyx_n_s_html_len;
   PyObject *__pyx_n_s_html_re;
   PyObject *__pyx_n_s_html_tree;
@@ -4657,7 +4657,7 @@ static int __pyx_m_clear(PyObject *m) {
   Py_CLEAR(clear_module_state->__pyx_n_u_head_and_body);
   Py_CLEAR(clear_module_state->__pyx_n_s_html);
   Py_CLEAR(clear_module_state->__pyx_kp_u_html_2);
-  Py_CLEAR(clear_module_state->__pyx_kp_u_html_body_head);
+  Py_CLEAR(clear_module_state->__pyx_kp_u_html_body_head_er);
   Py_CLEAR(clear_module_state->__pyx_n_s_html_len);
   Py_CLEAR(clear_module_state->__pyx_n_s_html_re);
   Py_CLEAR(clear_module_state->__pyx_n_s_html_tree);
@@ -5179,7 +5179,7 @@ static int __pyx_m_traverse(PyObject *m, visitproc visit, void *arg) {
   Py_VISIT(traverse_module_state->__pyx_n_u_head_and_body);
   Py_VISIT(traverse_module_state->__pyx_n_s_html);
   Py_VISIT(traverse_module_state->__pyx_kp_u_html_2);
-  Py_VISIT(traverse_module_state->__pyx_kp_u_html_body_head);
+  Py_VISIT(traverse_module_state->__pyx_kp_u_html_body_head_er);
   Py_VISIT(traverse_module_state->__pyx_n_s_html_len);
   Py_VISIT(traverse_module_state->__pyx_n_s_html_re);
   Py_VISIT(traverse_module_state->__pyx_n_s_html_tree);
@@ -5801,7 +5801,7 @@ static int __pyx_m_traverse(PyObject *m, visitproc visit, void *arg) {
 #define __pyx_n_u_head_and_body __pyx_mstate_global->__pyx_n_u_head_and_body
 #define __pyx_n_s_html __pyx_mstate_global->__pyx_n_s_html
 #define __pyx_kp_u_html_2 __pyx_mstate_global->__pyx_kp_u_html_2
-#define __pyx_kp_u_html_body_head __pyx_mstate_global->__pyx_kp_u_html_body_head
+#define __pyx_kp_u_html_body_head_er __pyx_mstate_global->__pyx_kp_u_html_body_head_er
 #define __pyx_n_s_html_len __pyx_mstate_global->__pyx_n_s_html_len
 #define __pyx_n_s_html_re __pyx_mstate_global->__pyx_n_s_html_re
 #define __pyx_n_s_html_tree __pyx_mstate_global->__pyx_n_s_html_tree
@@ -29011,7 +29011,7 @@ static PyObject *__pyx_pf_10selectolax_6parser_4get_fragment_type(CYTHON_UNUSED
  *         tree = parser_cls(html)
  * 
  *     import re             # <<<<<<<<<<<<<<
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
  * 
  */
   __pyx_t_3 = __Pyx_ImportDottedModule(__pyx_n_s_re, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(5, 36, __pyx_L1_error)
@@ -29022,7 +29022,7 @@ static PyObject *__pyx_pf_10selectolax_6parser_4get_fragment_type(CYTHON_UNUSED
   /* "selectolax/utils.pxi":37
  * 
  *     import re
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)             # <<<<<<<<<<<<<<
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)             # <<<<<<<<<<<<<<
  * 
  *     has_html = False
  */
@@ -29045,7 +29045,7 @@ static PyObject *__pyx_pf_10selectolax_6parser_4get_fragment_type(CYTHON_UNUSED
   }
   #endif
   {
-    PyObject *__pyx_callargs[3] = {__pyx_t_7, __pyx_kp_u_html_body_head, __pyx_t_5};
+    PyObject *__pyx_callargs[3] = {__pyx_t_7, __pyx_kp_u_html_body_head_er, __pyx_t_5};
     __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_4, __pyx_callargs+1-__pyx_t_6, 2+__pyx_t_6);
     __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0;
     __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0;
@@ -29057,7 +29057,7 @@ static PyObject *__pyx_pf_10selectolax_6parser_4get_fragment_type(CYTHON_UNUSED
   __pyx_t_3 = 0;
 
   /* "selectolax/utils.pxi":39
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
  * 
  *     has_html = False             # <<<<<<<<<<<<<<
  *     has_head = False
@@ -31530,7 +31530,7 @@ static PyObject *__pyx_pf_10selectolax_6parser_16get_fragment_type(CYTHON_UNUSED
  *         tree = parser_cls(html)
  * 
  *     import re             # <<<<<<<<<<<<<<
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
  * 
  */
   __pyx_t_3 = __Pyx_ImportDottedModule(__pyx_n_s_re, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(7, 36, __pyx_L1_error)
@@ -31541,7 +31541,7 @@ static PyObject *__pyx_pf_10selectolax_6parser_16get_fragment_type(CYTHON_UNUSED
   /* "selectolax/utils.pxi":37
  * 
  *     import re
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)             # <<<<<<<<<<<<<<
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)             # <<<<<<<<<<<<<<
  * 
  *     has_html = False
  */
@@ -31564,7 +31564,7 @@ static PyObject *__pyx_pf_10selectolax_6parser_16get_fragment_type(CYTHON_UNUSED
   }
   #endif
   {
-    PyObject *__pyx_callargs[3] = {__pyx_t_7, __pyx_kp_u_html_body_head, __pyx_t_5};
+    PyObject *__pyx_callargs[3] = {__pyx_t_7, __pyx_kp_u_html_body_head_er, __pyx_t_5};
     __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_4, __pyx_callargs+1-__pyx_t_6, 2+__pyx_t_6);
     __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0;
     __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0;
@@ -31576,7 +31576,7 @@ static PyObject *__pyx_pf_10selectolax_6parser_16get_fragment_type(CYTHON_UNUSED
   __pyx_t_3 = 0;
 
   /* "selectolax/utils.pxi":39
- *     html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+ *     html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
  * 
  *     has_html = False             # <<<<<<<<<<<<<<
  *     has_head = False
@@ -41210,7 +41210,7 @@ static int __Pyx_CreateStringTabAndInitStrings(void) {
     {&__pyx_n_u_head_and_body, __pyx_k_head_and_body, sizeof(__pyx_k_head_and_body), 0, 1, 0, 1},
     {&__pyx_n_s_html, __pyx_k_html, sizeof(__pyx_k_html), 0, 0, 1, 1},
     {&__pyx_kp_u_html_2, __pyx_k_html_2, sizeof(__pyx_k_html_2), 0, 1, 0, 0},
-    {&__pyx_kp_u_html_body_head, __pyx_k_html_body_head, sizeof(__pyx_k_html_body_head), 0, 1, 0, 0},
+    {&__pyx_kp_u_html_body_head_er, __pyx_k_html_body_head_er, sizeof(__pyx_k_html_body_head_er), 0, 1, 0, 0},
     {&__pyx_n_s_html_len, __pyx_k_html_len, sizeof(__pyx_k_html_len), 0, 0, 1, 1},
     {&__pyx_n_s_html_re, __pyx_k_html_re, sizeof(__pyx_k_html_re), 0, 0, 1, 1},
     {&__pyx_n_s_html_tree, __pyx_k_html_tree, sizeof(__pyx_k_html_tree), 0, 0, 1, 1},

selectolax/parser.pyi

@@ -1,15 +1,28 @@
-from typing import Iterator, TypeVar, Literal
+from typing import Any, Iterator, TypeVar, Literal, overload
 
 DefaultT = TypeVar("DefaultT")
 
 class _Attributes:
     @staticmethod
-    def create(node: "Node", decode_errors: str) -> "_Attributes": ...
+    def create(node: Node, decode_errors: str) -> _Attributes: ...
     def keys(self) -> Iterator[str]: ...
-    def items(self) -> Iterator[tuple[str, str]]: ...
-    def values(self) -> Iterator[str]: ...
-    def get(self, key, default: DefaultT | None = None) -> str | DefaultT: ...
-    def sget(self, key, default: str = "") -> str | DefaultT: ...
+    def items(self) -> Iterator[tuple[str, str | None]]: ...
+    def values(self) -> Iterator[str | None]: ...
+    def __iter__(self) -> Iterator[str]: ...
+    def __len__(self) -> int: ...
+    def __getitem__(self, key: str) -> str | None: ...
+    def __setitem__(self, key: str, value: str) -> None: ...
+    def __delitem__(self, key: str) -> None: ...
+    def __contains__(self, key: str) -> bool: ...
+    def __repr__(self) -> str: ...
+    @overload
+    def get(self, key: str, default: DefaultT) -> DefaultT | str | None: ...
+    @overload
+    def get(self, key: str, default: None = ...) -> str | None: ...
+    @overload
+    def sget(self, key: str, default: str | DefaultT) -> str | DefaultT: ...
+    @overload
+    def sget(self, key: str, default: str = "") -> str: ...
 
 class Selector:
     """An advanced CSS selector that supports additional operations.
@@ -18,12 +31,12 @@ class Selector:
 
     Please note, this is an experimental feature that can change in the future."""
 
-    def __init__(self, node: "Node", query: str): ...
-    def css(self, query: str) -> "Node":
+    def __init__(self, node: Node, query: str): ...
+    def css(self, query: str) -> Node:
         """Evaluate CSS selector against current scope."""
         ...
     @property
-    def matches(self) -> list["Node"]:
+    def matches(self) -> list[Node]:
         """Returns all possible selector matches"""
         ...
     @property
@@ -32,7 +45,7 @@ class Selector:
         ...
     def text_contains(
         self, text: str, deep: bool = True, separator: str = "", strip: bool = False
-    ) -> "Selector":
+    ) -> Selector:
         """Filter all current matches given text."""
         ...
     def any_text_contains(
@@ -42,7 +55,7 @@ class Selector:
         ...
     def attribute_long_than(
         self, text: str, length: int, start: str | None = None
-    ) -> "Selector":
+    ) -> Selector:
         """Filter all current matches by attribute length.
 
         Similar to string-length in XPath."""
@@ -56,15 +69,15 @@ class Selector:
         ...
 
 class Node:
-    parser: "HTMLParser"
+    parser: HTMLParser
     @property
-    def attributes(self) -> dict[str, None | str]:
+    def attributes(self) -> dict[str, str | None]:
         """Get all attributes that belong to the current node.
 
         The value of empty attributes is None."""
         ...
     @property
-    def attrs(self) -> "_Attributes":
+    def attrs(self) -> _Attributes:
         """A dict-like object that is similar to the attributes property, but operates directly on the Node data."""
         ...
     @property
@@ -88,10 +101,10 @@ class Node:
     def text(self, deep: bool = True, separator: str = "", strip: bool = False) -> str:
         """Returns the text of the node including text of all its child nodes."""
         ...
-    def iter(self, include_text: bool = False) -> Iterator["Node"]:
+    def iter(self, include_text: bool = False) -> Iterator[Node]:
         """Iterate over nodes on the current level."""
         ...
-    def traverse(self, include_text: bool = False) -> Iterator["Node"]:
+    def traverse(self, include_text: bool = False) -> Iterator[Node]:
         """Iterate over all child and next nodes starting from the current level."""
         ...
     @property
@@ -99,30 +112,30 @@ class Node:
         """Return the name of the current tag (e.g. div, p, img)."""
         ...
     @property
-    def child(self) -> None | "Node":
+    def child(self) -> Node | None:
         """Return the child node."""
         ...
     @property
-    def parent(self) -> None | "Node":
+    def parent(self) -> Node | None:
         """Return the parent node."""
         ...
     @property
-    def next(self) -> None | "Node":
+    def next(self) -> Node | None:
         """Return next node."""
         ...
     @property
-    def prev(self) -> None | "Node":
+    def prev(self) -> Node | None:
         """Return previous node."""
         ...
     @property
-    def last_child(self) -> None | "Node":
+    def last_child(self) -> Node | None:
         """Return last child node."""
         ...
     @property
-    def html(self) -> None | str:
+    def html(self) -> str | None:
         """Return HTML representation of the current node including all its child nodes."""
         ...
-    def css(self, query: str) -> list["Node"]:
+    def css(self, query: str) -> list[Node]:
         """Evaluate CSS selector against current node and its child nodes."""
         ...
     def any_css_matches(self, selectors: tuple[str]) -> bool:
@@ -131,9 +144,18 @@ class Node:
     def css_matches(self, selector: str) -> bool:
         """Returns True if CSS selector matches a node."""
         ...
+    @overload
     def css_first(
-        self, query: str, default: DefaultT | None = None, strict: bool = False
-    ) -> "Node" | DefaultT:
+        self, query: str, default: Any = ..., strict: Literal[True] = ...
+    ) -> Node: ...
+    @overload
+    def css_first(
+        self, query: str, default: DefaultT, strict: bool = False
+    ) -> Node | DefaultT: ...
+    @overload
+    def css_first(
+        self, query: str, default: None = ..., strict: bool = False
+    ) -> Node | None:
         """Evaluate CSS selector against current node and its child nodes."""
         ...
     def decompose(self, recursive: bool = True) -> None:
@@ -171,7 +193,7 @@ class Node:
 
         Currently, works on text nodes only."""
         ...
-    def select(self, query: str | None = None) -> "Selector":
+    def select(self, query: str | None = None) -> Selector:
         """Select nodes given a CSS selector.
 
         Works similarly to the css method, but supports chained filtering and extra features.
@@ -208,14 +230,23 @@ class HTMLParser:
         use_meta_tags: bool = True,
         decode_errors: Literal["strict", "ignore", "replace"] = "ignore",
     ): ...
-    def css(self, query: str) -> list["Node"]:
+    def css(self, query: str) -> list[Node]:
         """A CSS selector.
 
         Matches pattern query against HTML tree."""
         ...
+    @overload
+    def css_first(
+        self, query: str, default: Any = ..., strict: Literal[True] = ...
+    ) -> Node: ...
+    @overload
+    def css_first(
+        self, query: str, default: DefaultT, strict: bool = False
+    ) -> Node | DefaultT: ...
+    @overload
     def css_first(
-        self, query: str, default: DefaultT | None = None, strict: bool = False
-    ) -> DefaultT | "Node":
+        self, query: str, default: None = ..., strict: bool = False
+    ) -> Node | None:
         """Same as css but returns only the first match."""
         ...
     @property
@@ -225,18 +256,18 @@ class HTMLParser:
         Returns unknown in case the encoding is not determined."""
         ...
     @property
-    def root(self) -> "Node" | None:
+    def root(self) -> Node | None:
         """Returns root node."""
         ...
     @property
-    def head(self) -> "Node" | None:
+    def head(self) -> Node | None:
         """Returns head node."""
         ...
     @property
-    def body(self) -> "Node" | None:
+    def body(self) -> Node | None:
         """Returns document body."""
         ...
-    def tags(self, name: str) -> list["Node"]:
+    def tags(self, name: str) -> list[Node]:
         """Returns a list of tags that match specified name."""
         ...
     def text(self, deep: bool = True, separator: str = "", strip: bool = False) -> str:
@@ -249,10 +280,10 @@ class HTMLParser:
         Works the same as th unwrap method, but applied to a list of tags."""
         ...
     @property
-    def html(self) -> None | str:
+    def html(self) -> str | None:
         """Return HTML representation of the page."""
         ...
-    def select(self, query: str | None = None) -> "Selector" | None:
+    def select(self, query: str | None = None) -> Selector | None:
         """Select nodes given a CSS selector.
 
         Works similarly to the css method, but supports chained filtering and extra features.
@@ -272,7 +303,7 @@ class HTMLParser:
         Caches values on the first call to improve performance."""
         ...
     def css_matches(self, selector: str) -> bool: ...
-    def clone(self) -> "HTMLParser":
+    def clone(self) -> HTMLParser:
         """Clone the current tree."""
         ...
     def merge_text_nodes(self):
@@ -281,14 +312,14 @@ class HTMLParser:
         This is useful for text extraction."""
         ...
 
-def create_tag(tag: str) -> "Node":
+def create_tag(tag: str) -> Node:
     """
     Given an HTML tag name, e.g. `"div"`, create a single empty node for that tag,
     e.g. `"<div></div>"`.
     """
     ...
 
-def parse_fragment(html: str) -> list["Node"]:
+def parse_fragment(html: str) -> list[Node]:
     """
     Given HTML, parse it into a list of Nodes, such that the nodes
     correspond to the given HTML.

selectolax/utils.pxi

@@ -34,7 +34,7 @@ def get_fragment_type(
         tree = parser_cls(html)
     
     import re
-    html_re = re.compile(r"<html|<body|<head", re.IGNORECASE)
+    html_re = re.compile(r"<html|<body|<head(?!er)", re.IGNORECASE)
 
     has_html = False
     has_head = False

{selectolax-0.3.25.dist-info → selectolax-0.3.27.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: selectolax
-Version: 0.3.25
+Version: 0.3.27
 Summary: Fast HTML5 parser with CSS selectors.
 Home-page: https://github.com/rushter/selectolax
 Author: Artem Golubin

{selectolax-0.3.25.dist-info → selectolax-0.3.27.dist-info}/RECORD

@@ -1,17 +1,17 @@
-selectolax/__init__.py,sha256=bnh02Y32fkV7Y_ibTNnzgBjLMKlZDKhtxELxiRpL-JU,185
+selectolax/__init__.py,sha256=H6D0G54OTy7vXxMudUXEbzIw-3rU9JcnyuRxJEv1L18,185
 selectolax/base.pxi,sha256=zOj3BrCA71xd-mJFtkMIAglP4ZybfrHVoCoy6ljTBDQ,93
-selectolax/lexbor.c,sha256=OXp79KKhS3Zg5JY0cbv05VGROvfgFOnFZAmPs-JdQyY,2354322
-selectolax/lexbor.cp311-win_amd64.pyd,sha256=b4lm9PsCv_glqZCx_fTkw-GNmF9ucE5WzsIlWz26hb0,6929408
+selectolax/lexbor.c,sha256=X-GrSY8qlNpnL0EHpftD_zn8QrfPVEwpj4IByZAb61c,2354397
+selectolax/lexbor.cp311-win_amd64.pyd,sha256=cro4QUNxWLGZ4FnZN_Hif_iuEyhQ6AdKPx2jWUki8fU,6928896
 selectolax/lexbor.pxd,sha256=1d9nvZd9rZl27gwPwVV5BlbR2LAi6jDK69Xm9Guz5Kk,21538
-selectolax/lexbor.pyi,sha256=VvVQ1HwZlDK2oXByWE2zFPozRgLL8nyhoXGrNLmwk5Q,5684
+selectolax/lexbor.pyi,sha256=DXQejzmWT7FbWCXcakLzOYGEs-rOMMdaLIZaNSu2uiM,6716
 selectolax/lexbor.pyx,sha256=H3-Y78orz2Hop0Qqf8JulJo6f3yBR0kbHRqNPyDOsAc,11097
-selectolax/parser.c,sha256=Y96r4R41n15eztCveImVl1zFJId6TERe9HQp9GFJD04,2215023
-selectolax/parser.cp311-win_amd64.pyd,sha256=CbOGIz4nleRZegZJWavcqd4-kmEafFw0S-7T78Qd9TE,2140672
+selectolax/parser.c,sha256=rGXXnE3kJJDElEps9cQMYaIfXCCxVpDk5ELR-RQF5nk,2215098
+selectolax/parser.cp311-win_amd64.pyd,sha256=IjKKkozl9w9yJ-gnzz_5Fu7uRz38n_4-GMsA_NLxTeQ,2139648
 selectolax/parser.pxd,sha256=4pM_CcZlvJlaR8EMjZCnSmnCcJbwcYOldRTBEbfwm48,25145
-selectolax/parser.pyi,sha256=FFpUXXVatpajijEXN2WpKKsesuJv82aE3TZKz_oyY2o,10857
+selectolax/parser.pyi,sha256=Ud_hBY54PJEVJX6WZ07L7s0uzs3u1FLD7TAGhES1y7Q,11887
 selectolax/parser.pyx,sha256=lQW4qJ6nCDraCupvcT61zUkgo-S-KIzl9JIGV6hh6hA,13386
 selectolax/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-selectolax/utils.pxi,sha256=GFDsBSjUCNh_Zmi7mKvWN-ww2meWKe955DqXlDqhNHc,3560
+selectolax/utils.pxi,sha256=4rtdRcLWuemxN1qe7Eul5jvAmHZ65r7Gvf67_Wg8Bt4,3566
 selectolax/lexbor/attrs.pxi,sha256=TEJUCGAkFwb14Emecyx4yljKSJMRmFbq8mOcNs35G_c,3204
 selectolax/lexbor/node.pxi,sha256=P-KXzAk6fOo8ilEKAm0yjFQa90xkAXhWhSdce-YDauo,30213
 selectolax/lexbor/selection.pxi,sha256=nRGiDYvpSAQcsWQ_2Z9-4kqebahIJmKWXQBtd3MPsis,6626
@@ -19,8 +19,8 @@ selectolax/lexbor/util.pxi,sha256=0I4ElWIwXxrZCfMmGCtyDU127oMsPCqC3IcUk4QmMAc,58
 selectolax/modest/node.pxi,sha256=xDJTFhcvkF7FGSObnCftZJSIBj7wV1--IdLJbFoIItw,33519
 selectolax/modest/selection.pxi,sha256=0elY7JwnpPVaw0QZE1T7A78s9FIph5uWIhwy4sEXGU8,6586
 selectolax/modest/util.pxi,sha256=o2nPGGGtRlLqOCa7yPk94CfBzNlVr7ull7osFy6NRX4,570
-selectolax-0.3.25.dist-info/LICENSE,sha256=Gy4WGsmAwV9QtqH0HaBHJQ35bt_0irn77fIt1iBncUo,1087
-selectolax-0.3.25.dist-info/METADATA,sha256=sOZWvfD77Qj0NZcS83InlhhHCfhJlvadw2PYrZu2ScQ,6105
-selectolax-0.3.25.dist-info/WHEEL,sha256=tE2EWZPEv-G0fjAlUUz7IGM64246YKD9fpv4HcsDMkk,101
-selectolax-0.3.25.dist-info/top_level.txt,sha256=e5MuEM2PrQzoDlWetkFli9uXSlxa_ktW5jJEihhaI1c,11
-selectolax-0.3.25.dist-info/RECORD,,
+selectolax-0.3.27.dist-info/LICENSE,sha256=Gy4WGsmAwV9QtqH0HaBHJQ35bt_0irn77fIt1iBncUo,1087
+selectolax-0.3.27.dist-info/METADATA,sha256=g5nfZhPsJ3nCoIEH4W-fnujzcB2-SchMCeC0U1oPSXw,6105
+selectolax-0.3.27.dist-info/WHEEL,sha256=nkBcd8Ko0v5sEcSagm2-x_RVrb8gBSkTa8VFFZ0Mr1o,101
+selectolax-0.3.27.dist-info/top_level.txt,sha256=e5MuEM2PrQzoDlWetkFli9uXSlxa_ktW5jJEihhaI1c,11
+selectolax-0.3.27.dist-info/RECORD,,

{selectolax-0.3.25.dist-info → selectolax-0.3.27.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.2.0)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: false
 Tag: cp311-cp311-win_amd64