still default to iso-latin-1 if no on-page or in-header content-type is present

This commit is contained in:
jesopo 2019-09-09 14:48:26 +01:00
parent 0a67659637
commit 1df82c1cb2

View file

@ -125,7 +125,7 @@ def request(url: str, method: str="GET", get_params: dict={},
encoding = response.encoding encoding = response.encoding
if content_type and content_type in SOUP_CONTENT_TYPES: if content_type and content_type in SOUP_CONTENT_TYPES:
souped = bs4.BeautifulSoup(response_content, parser) souped = bs4.BeautifulSoup(response_content, parser)
encoding = _find_encoding(souped) or encoding encoding = _find_encoding(souped) or encoding or "iso-8859-1"
def _decode_data(): def _decode_data():
return response_content.decode(encoding) return response_content.decode(encoding)