selectolax 0.3.25__tar.gz → 0.3.27__tar.gz

{selectolax-0.3.25 → selectolax-0.3.27}/CHANGES.rst

@@ -1,6 +1,21 @@
 selectolax Changelog
 ====================
 
+Version 0.3.27
+-------------
+
+Released
+
+- Fix: Header detected as head
+
+
+Version 0.3.26
+-------------
+
+Released
+
+- Improve type hints
+
 Version 0.3.25
 -------------
 

{selectolax-0.3.25/selectolax.egg-info → selectolax-0.3.27}/PKG-INFO

@@ -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 → selectolax-0.3.27}/docs/conf.py

@@ -49,6 +49,8 @@ extensions = [
     'sphinx.ext.autodoc',
     'sphinx.ext.viewcode',
     'numpydoc',
+    'sphinxext.opengraph',
+    'sphinx_copybutton'
 ]
 
 # Add any paths that contain templates here, relative to this directory.
@@ -65,7 +67,7 @@ master_doc = 'index'
 
 # General information about the project.
 project = u'selectolax'
-copyright = u"2018-2023, Artem Golubin"
+copyright = u"2018-2024, Artem Golubin"
 
 # The version info for the project you're documenting, acts as replacement
 # for |version| and |release|, also used in various other places throughout
@@ -121,12 +123,16 @@ pygments_style = 'sphinx'
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 # html_theme = 'default'
-html_theme = 'sphinx_rtd_theme'
+html_theme = 'furo'
 
 # Theme options are theme-specific and customize the look and feel of a
 # theme further.  For a list of options available for each theme, see the
 # documentation.
-# html_theme_options = {}
+html_theme_options = {
+    "source_repository": "https://github.com/rushter/selectolax",
+    "source_branch": "master",
+    "source_directory": "docs/",
+}
 
 # Add any paths that contain custom themes here, relative to this directory.
 # html_theme_path = []
@@ -141,7 +147,7 @@ html_theme = 'sphinx_rtd_theme'
 
 # The name of an image file (relative to this directory) to place at the
 # top of the sidebar.
-# html_logo = None
+html_logo = "logo.png"
 
 # The name of an image file (within the static path) to use as favicon
 # of the docs.  This file should be a Windows icon file (.ico) being

{selectolax-0.3.25 → selectolax-0.3.27}/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-0.3.25 → selectolax-0.3.27}/selectolax/lexbor.c

@@ -3494,7 +3494,6 @@ 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";
@@ -3518,6 +3517,7 @@ 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";
@@ -4160,7 +4160,7 @@ 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;
@@ -4724,7 +4724,7 @@ 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);
@@ -5266,7 +5266,7 @@ 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);
@@ -5908,7 +5908,7 @@ 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
@@ -7298,7 +7298,7 @@ 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)
@@ -7309,7 +7309,7 @@ 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
  */
@@ -7332,7 +7332,7 @@ 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;
@@ -7344,7 +7344,7 @@ 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
@@ -33919,7 +33919,7 @@ 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)
@@ -33930,7 +33930,7 @@ 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
  */
@@ -33953,7 +33953,7 @@ 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;
@@ -33965,7 +33965,7 @@ 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
@@ -43679,7 +43679,7 @@ 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-0.3.27/selectolax/lexbor.pyi

@@ -0,0 +1,172 @@
+from typing import Any, Iterator, Literal, TypeVar, NoReturn, overload
+
+DefaultT = TypeVar("DefaultT")
+
+class LexborAttributes:
+    @staticmethod
+    def create(node: LexborAttributes) -> LexborAttributes: ...
+    def keys(self) -> Iterator[str]: ...
+    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:
+    def __init__(self, node: LexborNode, query: str): ...
+    def css(self, query: str) -> NoReturn: ...
+    @property
+    def matches(self) -> list[LexborNode]: ...
+    @property
+    def any_matches(self) -> bool: ...
+    def text_contains(
+        self, text: str, deep: bool = True, separator: str = "", strip: bool = False
+    ) -> 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: ...
+    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: ...
+
+class LexborNode:
+    parser: LexborHTMLParser
+    @property
+    def mem_id(self) -> int: ...
+    @property
+    def child(self) -> LexborNode | None: ...
+    @property
+    def first_child(self) -> LexborNode | None: ...
+    @property
+    def parent(self) -> LexborNode | None: ...
+    @property
+    def next(self) -> LexborNode | None: ...
+    @property
+    def prev(self) -> LexborNode | None: ...
+    @property
+    def last_child(self) -> LexborNode | None: ...
+    @property
+    def html(self) -> str | None: ...
+    def __hash__(self) -> int: ...
+    def text_lexbor(self) -> str: ...
+    def text(
+        self, deep: bool = True, separator: str = "", strip: bool = False
+    ) -> str: ...
+    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: None = ..., strict: bool = False
+    ) -> LexborNode | None: ...
+    def any_css_matches(self, selectors: tuple[str]) -> bool: ...
+    def css_matches(self, selector: str) -> bool: ...
+    @property
+    def tag_id(self) -> int: ...
+    @property
+    def tag(self) -> str | None: ...
+    def decompose(self, recursive: bool = True) -> None: ...
+    def strip_tags(self, tags: list[str], recursive: bool = False) -> None: ...
+    @property
+    def attributes(self) -> dict[str, str | None]: ...
+    @property
+    def attrs(self) -> LexborAttributes: ...
+    @property
+    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: ...
+    @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: ...
+    @property
+    def text_content(self) -> str | None: ...
+
+class LexborHTMLParser:
+    def __init__(self, html: str): ...
+    @property
+    def selector(self) -> "LexborCSSSelector": ...
+    @property
+    def root(self) -> LexborNode | None: ...
+    @property
+    def body(self) -> LexborNode | None: ...
+    @property
+    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) -> 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: 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 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 unwrap_tags(self, tags: list[str]) -> None: ...
+
+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]:
+    """
+    Given HTML, parse it into a list of Nodes, such that the nodes
+    correspond to the given HTML.
+
+    For contrast, HTMLParser adds `<html>`, `<head>`, and `<body>` tags
+    if they are missing. This function does not add these tags.
+    """
+    ...

{selectolax-0.3.25 → selectolax-0.3.27}/selectolax/parser.c

@@ -3482,7 +3482,6 @@ 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";
@@ -3513,6 +3512,7 @@ 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>";
@@ -4119,7 +4119,7 @@ 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;
@@ -4663,7 +4663,7 @@ 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);
@@ -5185,7 +5185,7 @@ 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);
@@ -5807,7 +5807,7 @@ 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
@@ -29017,7 +29017,7 @@ 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)
@@ -29028,7 +29028,7 @@ 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
  */
@@ -29051,7 +29051,7 @@ 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;
@@ -29063,7 +29063,7 @@ 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
@@ -31536,7 +31536,7 @@ 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)
@@ -31547,7 +31547,7 @@ 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
  */
@@ -31570,7 +31570,7 @@ 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;
@@ -31582,7 +31582,7 @@ 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
@@ -41216,7 +41216,7 @@ 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},