diff options
Diffstat (limited to 'bs4/builder')
| -rw-r--r-- | bs4/builder/__init__.py | 12 | ||||
| -rw-r--r-- | bs4/builder/_htmlparser.py | 14 | ||||
| -rw-r--r-- | bs4/builder/_lxml.py | 8 |
3 files changed, 25 insertions, 9 deletions
diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py index fdb3362..21454e6 100644 --- a/bs4/builder/__init__.py +++ b/bs4/builder/__init__.py @@ -93,7 +93,7 @@ class TreeBuilder(object): preserve_whitespace_tags = set() empty_element_tags = None # A tag will be considered an empty-element # tag when and only when it has no contents. - + # A value for these tag/attribute combinations is a space- or # comma-separated list of CDATA, rather than a single CDATA. cdata_list_attributes = {} @@ -125,7 +125,7 @@ class TreeBuilder(object): if self.empty_element_tags is None: return True return tag_name in self.empty_element_tags - + def feed(self, markup): raise NotImplementedError() @@ -235,11 +235,11 @@ class HTMLTreeBuilder(TreeBuilder): empty_element_tags = set([ # These are from HTML5. 'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr', - - # These are from HTML4, removed in HTML5. - 'spacer', 'frame' + + # These are from earlier versions of HTML and are removed in HTML5. + 'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer' ]) - + # The HTML standard defines these attributes as containing a # space-separated list of values, not a single value. That is, # class="foo bar" means that the 'class' attribute has two values, diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py index 67890b3..ef9fd1e 100644 --- a/bs4/builder/_htmlparser.py +++ b/bs4/builder/_htmlparser.py @@ -64,7 +64,18 @@ class BeautifulSoupHTMLParser(HTMLParser): # order. It's a list of closing tags we've already handled and # will ignore, assuming they ever show up. self.already_closed_empty_element = [] - + + def error(self, msg): + """In Python 3, HTMLParser subclasses must implement error(), although this + requirement doesn't appear to be documented. + + In Python 2, HTMLParser implements error() as raising an exception. + + In any event, this method is called only on very strange markup and our best strategy + is to pretend it didn't happen and keep going. + """ + warnings.warn(msg) + def handle_startendtag(self, name, attrs): # This is only called when the markup looks like # <tag/>. @@ -213,6 +224,7 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder): parser.soup = self.soup try: parser.feed(markup) + parser.close() except HTMLParseError, e: warnings.warn(RuntimeWarning( "Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help.")) diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index d2ca287..3439271 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -5,9 +5,13 @@ __all__ = [ 'LXMLTreeBuilder', ] +try: + from collections.abc import Callable # Python 3.6 +except ImportError , e: + from collections import Callable + from io import BytesIO from StringIO import StringIO -import collections from lxml import etree from bs4.element import ( Comment, @@ -58,7 +62,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): # Use the default parser. parser = self.default_parser(encoding) - if isinstance(parser, collections.Callable): + if isinstance(parser, Callable): # Instantiate the parser with default arguments parser = parser(target=self, strip_cdata=False, encoding=encoding) return parser |