From e8fea9c8e125ad105ef4f54e0a3f9072e3e67ede Mon Sep 17 00:00:00 2001
From: Matheus Felipe <matheusfelipeog@protonmail.com>
Date: Sun, 15 Oct 2023 07:16:38 -0300
Subject: [PATCH] TYP/DOC: add HTMLFlavors type to read_html and related

---
 pandas/_typing.py | 3 +++
 pandas/io/html.py | 9 +++++----
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/pandas/_typing.py b/pandas/_typing.py
index de01434c09c39..c2d51f63eb2ab 100644
--- a/pandas/_typing.py
+++ b/pandas/_typing.py
@@ -410,6 +410,9 @@ def closed(self) -> bool:
 # read_xml parsers
 XMLParsers = Literal["lxml", "etree"]
 
+# read_html flavors
+HTMLFlavors = Literal["lxml", "html5lib", "bs4"]
+
 # Interval closed type
 IntervalLeftRight = Literal["left", "right"]
 IntervalClosedType = Union[IntervalLeftRight, Literal["both", "neither"]]
diff --git a/pandas/io/html.py b/pandas/io/html.py
index 68d30fe5ba681..5d5bf079784be 100644
--- a/pandas/io/html.py
+++ b/pandas/io/html.py
@@ -57,6 +57,7 @@
         BaseBuffer,
         DtypeBackend,
         FilePath,
+        HTMLFlavors,
         ReadBuffer,
         StorageOptions,
     )
@@ -889,13 +890,13 @@ def _data_to_frame(**kwargs):
 }
 
 
-def _parser_dispatch(flavor: str | None) -> type[_HtmlFrameParser]:
+def _parser_dispatch(flavor: HTMLFlavors | None) -> type[_HtmlFrameParser]:
     """
     Choose the parser based on the input flavor.
 
     Parameters
     ----------
-    flavor : str
+    flavor : {{"lxml", "html5lib", "bs4"}} or None
         The type of parser to use. This must be a valid backend.
 
     Returns
@@ -1033,7 +1034,7 @@ def read_html(
     io: FilePath | ReadBuffer[str],
     *,
     match: str | Pattern = ".+",
-    flavor: str | Sequence[str] | None = None,
+    flavor: HTMLFlavors | Sequence[HTMLFlavors] | None = None,
     header: int | Sequence[int] | None = None,
     index_col: int | Sequence[int] | None = None,
     skiprows: int | Sequence[int] | slice | None = None,
@@ -1074,7 +1075,7 @@ def read_html(
         This value is converted to a regular expression so that there is
         consistent behavior between Beautiful Soup and lxml.
 
-    flavor : str or list-like, optional
+    flavor : {{"lxml", "html5lib", "bs4"}} or list-like, optional
         The parsing engine (or list of parsing engines) to use. 'bs4' and
         'html5lib' are synonymous with each other, they are both there for
         backwards compatibility. The default of ``None`` tries to use ``lxml``