This commit is contained in:
Miroslav Stampar
2018-04-22 01:12:56 +02:00
parent 509bb41b06
commit 1822cc05f6
3 changed files with 4 additions and 4 deletions

View File

@@ -334,7 +334,7 @@ def decodePage(page, contentEncoding, contentType):
kb.pageEncoding = kb.pageEncoding or checkCharEncoding(getHeuristicCharEncoding(page))
if kb.pageEncoding and kb.pageEncoding.lower() == "utf-8-sig":
if (kb.pageEncoding or "").lower() == "utf-8-sig":
kb.pageEncoding = "utf-8"
if page and page.startswith("\xef\xbb\xbf"): # Reference: https://docs.python.org/2/library/codecs.html (Note: noticed problems when "utf-8-sig" is left to Python for handling)
page = page[3:]