diff options
| author | Leonard Richardson <leonardr@segfault.org> | 2015-06-27 09:55:40 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonardr@segfault.org> | 2015-06-27 09:55:40 -0400 |
| commit | feffc5a1146e2520c90682bc2c33f5fa7d3943f0 (patch) | |
| tree | 6dce892919c201b629628647f86843382b29a60a /bs4/builder/_lxml.py | |
| parent | d728b9cbd6cd5954acf7c9c32fe2f1878809d6e8 (diff) | |
Added an exclude_encodings argument to UnicodeDammit and to the
Beautiful Soup constructor, which lets you prohibit the detection of
an encoding that you know is wrong. [bug=1469408]
Diffstat (limited to 'bs4/builder/_lxml.py')
| -rw-r--r-- | bs4/builder/_lxml.py | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index b0bc8a0..2e33386 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -77,6 +77,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): return (None, tag) def prepare_markup(self, markup, user_specified_encoding=None, + exclude_encodings=None, document_declared_encoding=None): """ :yield: A series of 4-tuples. @@ -102,7 +103,8 @@ class LXMLTreeBuilderForXML(TreeBuilder): # the document as each one in turn. is_html = not self.is_xml try_encodings = [user_specified_encoding, document_declared_encoding] - detector = EncodingDetector(markup, try_encodings, is_html) + detector = EncodingDetector( + markup, try_encodings, is_html, exclude_encodings) for encoding in detector.encodings: yield (detector.markup, encoding, document_declared_encoding, False) |