Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

fix: parse quoted charset values in content-type headers

Bortlesboat6390c0af3d0a
diff --git a/scrapling/engines/toolbelt/convertor.py b/scrapling/engines/toolbelt/convertor.py
index 8d624e0..cf303c8 100644
--- a/scrapling/engines/toolbelt/convertor.py
+++ b/scrapling/engines/toolbelt/convertor.py
@@ -10,7 +10,7 @@ from scrapling.core.utils import log
from .custom import Response, StatusText
from scrapling.core._types import Dict, List, Optional
-__CHARSET_RE__ = re_compile(r"charset=([\w-]+)")
+__CHARSET_RE__ = re_compile(r"""charset=["']?([\w-]+)""")
class ResponseFactory:
diff --git a/tests/fetchers/test_utils.py b/tests/fetchers/test_utils.py
index 942835f..4679478 100644
--- a/tests/fetchers/test_utils.py
+++ b/tests/fetchers/test_utils.py
@@ -1,5 +1,6 @@
import pytest
+from scrapling.engines.toolbelt.convertor import ResponseFactory
from scrapling.engines.toolbelt.custom import StatusText, Response
from scrapling.engines.toolbelt.navigation import (
construct_proxy_dict,
@@ -139,6 +140,32 @@ def test_unknown_status_code():
assert StatusText.get(1000) == "Unknown Status Code"
+# The private classmethod is name-mangled; resolve it once for the tests below.
+_extract_encoding = getattr(ResponseFactory, "_ResponseFactory__extract_browser_encoding")
+
+
+def test_browser_encoding_unquoted_charset():
+ """A charset declared without quotes is returned verbatim."""
+ assert _extract_encoding("text/html; charset=utf-8") == "utf-8"
+ assert _extract_encoding("text/html; charset=ISO-8859-1") == "ISO-8859-1"
+ assert _extract_encoding("text/html;charset=windows-1252") == "windows-1252"
+
+
+def test_browser_encoding_quoted_charset():
+ """A quoted charset value (RFC 7231 allows quoting) is unwrapped, not dropped."""
+ assert _extract_encoding('text/html; charset="utf-8"') == "utf-8"
+ assert _extract_encoding('text/html; charset="ISO-8859-1"') == "ISO-8859-1"
+ assert _extract_encoding("text/html; charset='Shift_JIS'") == "Shift_JIS"
+ assert _extract_encoding('text/plain; charset="windows-1252"; boundary=x') == "windows-1252"
+
+
+def test_browser_encoding_defaults_when_missing():
+ """Fall back to the default when no charset is present or the header is empty."""
+ assert _extract_encoding("text/html") == "utf-8"
+ assert _extract_encoding("") == "utf-8"
+ assert _extract_encoding(None) == "utf-8"
+
+
class TestConstructProxyDict:
"""Test proxy dictionary construction"""