From 480d3855bab374ab59312deed79ad1185eef5782 Mon Sep 17 00:00:00 2001
From: aadityasinha-dotcom <aadityasinha009@gmail.com>
Date: Fri, 18 Mar 2022 15:54:28 +0530
Subject: [PATCH 1/2] html5

---
 parsel/selector.py | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/parsel/selector.py b/parsel/selector.py
index 45c88d09..fed6866e 100644
--- a/parsel/selector.py
+++ b/parsel/selector.py
@@ -6,6 +6,7 @@
 from typing import Any, Dict, List, Optional, Mapping, Pattern, Union
 
 from lxml import etree, html
+from lxml.html import html5parser
 
 from .utils import flatten, iflatten, extract_regex, shorten
 from .csstranslator import HTMLTranslator, GenericTranslator
@@ -38,6 +39,10 @@ def __init__(self, *args, **kwargs) -> None:
         "_csstranslator": GenericTranslator(),
         "_tostring_method": "xml",
     },
+    'html5': {'_parser': html5parser.HTMLParser,
+              '_csstranslator': HTMLTranslator(),
+              '_tostring_method': 'html',
+    },
 }
 
 
@@ -55,6 +60,13 @@ def create_root_node(text, parser_cls, base_url=None):
     body = text.strip().replace("\x00", "").encode("utf8") or b"<html/>"
     parser = parser_cls(recover=True, encoding="utf8")
     root = etree.fromstring(body, parser=parser, base_url=base_url)
+    if parser == html5parser.HTMLParser:
+        try:
+            root = parser.parse(body, useChardet=False, override_encoding='utf8').getroot()
+        except ValueError:
+            raise TypeError('HTML5parser does not support control characters')
+    else:
+        root = etree.fromstring(body, parser=parser, base_url=base_url)
     if root is None:
         root = etree.fromstring(b"<html/>", parser=parser, base_url=base_url)
     return root
@@ -225,7 +237,7 @@ class Selector:
 
     ``text`` is a `str`` object
 
-    ``type`` defines the selector type, it can be ``"html"``, ``"xml"`` or ``None`` (default).
+    ``type`` defines the selector type, it can be ``"html"``, ``"xml"``, ``"html5"`` or ``None`` (default).
     If ``type`` is ``None``, the selector defaults to ``"html"``.
 
     ``base_url`` allows setting a URL for the document. This is needed when looking up external entities with relative paths.

From 50069ac4ffa04b00706292e028604c80e6b4e390 Mon Sep 17 00:00:00 2001
From: aadityasinha-dotcom <aadityasinha009@gmail.com>
Date: Fri, 18 Mar 2022 16:03:47 +0530
Subject: [PATCH 2/2] selector for HTML5

---
 parsel/selector.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/parsel/selector.py b/parsel/selector.py
index fed6866e..d9884698 100644
--- a/parsel/selector.py
+++ b/parsel/selector.py
@@ -7,6 +7,7 @@
 
 from lxml import etree, html
 from lxml.html import html5parser
+from lxml.html.html5parser import document_fromstring
 
 from .utils import flatten, iflatten, extract_regex, shorten
 from .csstranslator import HTMLTranslator, GenericTranslator
@@ -71,6 +72,10 @@ def create_root_node(text, parser_cls, base_url=None):
         root = etree.fromstring(b"<html/>", parser=parser, base_url=base_url)
     return root
 
+def selector_for_html5(response):
+  root = document_fromstring(response.text)
+  selector = Selector(response, type='html', root=root)
+  return selector
 
 class SelectorList(List[_SelectorType]):
     """