diff options
author | Leonard Richardson <leonard.richardson@canonical.com> | 2012-02-09 16:15:56 -0500 |
---|---|---|
committer | Leonard Richardson <leonard.richardson@canonical.com> | 2012-02-09 16:15:56 -0500 |
commit | 4aff2ee4d6f077e06159c92ab05c0f2ea527c6fa (patch) | |
tree | 40951a60046f184794a011a498187053e8ad2a92 /bs4/__init__.py | |
parent | caeb168dc47470607b3cd091e1d35db45c089385 (diff) |
As a last-ditch attempt to turn data into Unicode, use errors=replace instead of errors=strict.
Diffstat (limited to 'bs4/__init__.py')
-rw-r--r-- | bs4/__init__.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/bs4/__init__.py b/bs4/__init__.py index e6ad425..6917fa9 100644 --- a/bs4/__init__.py +++ b/bs4/__init__.py @@ -161,7 +161,8 @@ class BeautifulSoup(Tag): if hasattr(markup, 'read'): # It's a file-type object. markup = markup.read() - self.markup, self.original_encoding, self.declared_html_encoding = ( + (self.markup, self.original_encoding, self.declared_html_encoding, + self.contains_replacement_characters) = ( self.builder.prepare_markup(markup, from_encoding)) try: |