Parse html with regex, fix small issues

httplib/parser.py

@@ -1,9 +1,11 @@
 import logging
 import re
 import urllib
+from typing import Dict
 from urllib.parse import urlparse, urlsplit
 
 from httplib.exceptions import InvalidStatusLine, InvalidResponse, BadRequest, InvalidRequestLine
+from httplib.httpsocket import FORMAT
 
 
 def _is_valid_http_version(http_version: str):
@@ -164,7 +166,7 @@ def get_uri(url: str):
     parsed = urlsplit(url)
 
     result = f"http://{parsed.netloc}{parsed.path}"
-    if parsed.query != '':
+    if parsed.query != "":
         result = f"{result}?{parsed.query}"
 
     return result
@@ -175,3 +177,13 @@ def urljoin(base, url):
     Join a base url and a URL to form a absolute url.
     """
     return urllib.parse.urljoin(base, url)
+
+
+def get_charset(headers: Dict[str, str]):
+    if "content-type" in headers:
+        content_type = headers["content-type"]
+        match = re.search(r"charset\s*=\s*([a-z\-0-9]*)", content_type, re.I)
+        if match:
+            return match.group(1)
+
+    return FORMAT