diff options
Diffstat (limited to 'bs4/builder')
| -rw-r--r-- | bs4/builder/__init__.py | 15 | ||||
| -rw-r--r-- | bs4/builder/_lxml.py | 4 |
2 files changed, 13 insertions, 6 deletions
diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py index e28242b..7efbf89 100644 --- a/bs4/builder/__init__.py +++ b/bs4/builder/__init__.py @@ -175,8 +175,8 @@ class TreeBuilder(object): raise NotImplementedError() def prepare_markup(self, markup, user_specified_encoding=None, - document_declared_encoding=None): - return markup, None, None, False + document_declared_encoding=None, exclude_encodings=None): + yield markup, None, None, False def test_fragment_to_document(self, fragment): """Wrap an HTML fragment to make it look like a document. @@ -363,8 +363,15 @@ def register_treebuilders_from(module): this_module.builder_registry.register(obj) class ParserRejectedMarkup(Exception): - pass - + def __init__(self, message_or_exception): + """Explain why the parser rejected the given markup, either + with a textual explanation or another exception. + """ + if isinstance(message_or_exception, Exception): + e = message_or_exception + message_or_exception = "%s: %s" % (e.__class__.__name__, unicode(e)) + super(ParserRejectedMarkup, self).__init__(message_or_exception) + # Builders are registered in reverse order of priority, so that custom # builder registrations will take precedence. In general, we want lxml # to take precedence over html5lib, because it's faster. And we only diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index 85be1b5..ea66d8b 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -175,7 +175,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): self.parser.feed(data) self.parser.close() except (UnicodeDecodeError, LookupError, etree.ParserError), e: - raise ParserRejectedMarkup(str(e)) + raise ParserRejectedMarkup(e) def close(self): self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED] @@ -294,7 +294,7 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): self.parser.feed(markup) self.parser.close() except (UnicodeDecodeError, LookupError, etree.ParserError), e: - raise ParserRejectedMarkup(str(e)) + raise ParserRejectedMarkup(e) def test_fragment_to_document(self, fragment): |