diff options
Diffstat (limited to 'bs4/builder/_htmlparser.py')
| -rw-r--r-- | bs4/builder/_htmlparser.py | 19 |
1 files changed, 17 insertions, 2 deletions
diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py index 96a7b7d..2f2bf1e 100644 --- a/bs4/builder/_htmlparser.py +++ b/bs4/builder/_htmlparser.py @@ -359,9 +359,24 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder): return # Ask UnicodeDammit to sniff the most likely encoding. + + # This was provided by the end-user; treat it as a known + # definite encoding per the algorithm laid out in the HTML5 + # spec. (See the EncodingDetector class for details.) + known_definite_encodings = [user_specified_encoding] + + # This was found in the document; treat it as a slightly lower-priority + # user encoding. + user_encodings = [document_declared_encoding] + try_encodings = [user_specified_encoding, document_declared_encoding] - dammit = UnicodeDammit(markup, try_encodings, is_html=True, - exclude_encodings=exclude_encodings) + dammit = UnicodeDammit( + markup, + known_definite_encodings=known_definite_encodings, + user_encodings=user_encodings, + is_html=True, + exclude_encodings=exclude_encodings + ) yield (dammit.markup, dammit.original_encoding, dammit.declared_html_encoding, dammit.contains_replacement_characters) |