diff --git a/.gitignore b/.gitignore index 74e29c78..b557314a 100644 --- a/.gitignore +++ b/.gitignore @@ -1,7 +1,10 @@ + # Compiled source # ################### *.pyc *.py~ +*.pyproj +*.sln # Logs and databases # ###################### @@ -19,3 +22,32 @@ cache/* ehthumbs.db Icon? Thumbs.db + +#ignore thumbnails created by windows +Thumbs.db +#Ignore files build by Visual Studio +*.obj +*.exe +*.pdb +*.user +*.aps +*.pch +*.vspscc +*_i.c +*_p.c +*.ncb +*.suo +*.tlb +*.tlh +*.bak +*.cache +*.ilk +*.log +[Bb]in +[Dd]ebug*/ +*.lib +*.sbr +obj/ +[Rr]elease*/ +_ReSharper*/ +[Tt]est[Rr]esult* \ No newline at end of file diff --git a/Headphones.py b/Headphones.py index 999c8d1f..18bb7970 100644 --- a/Headphones.py +++ b/Headphones.py @@ -109,6 +109,9 @@ def main(): if headphones.DAEMON: headphones.daemonize() + + #configure the connection to the musicbrainz database + headphones.mb.startmb() # Force the http port if neccessary if args.port: diff --git a/bs4/__init__.py b/bs4/__init__.py new file mode 100644 index 00000000..80f6f684 --- /dev/null +++ b/bs4/__init__.py @@ -0,0 +1,359 @@ +"""Beautiful Soup +Elixir and Tonic +"The Screen-Scraper's Friend" +http://www.crummy.com/software/BeautifulSoup/ + +Beautiful Soup uses a pluggable XML or HTML parser to parse a +(possibly invalid) document into a tree representation. Beautiful Soup +provides provides methods and Pythonic idioms that make it easy to +navigate, search, and modify the parse tree. + +Beautiful Soup works with Python 2.6 and up. It works better if lxml +and/or html5lib is installed. + +For more than you ever wanted to know about Beautiful Soup, see the +documentation: +http://www.crummy.com/software/BeautifulSoup/bs4/doc/ +""" + +__author__ = "Leonard Richardson (leonardr@segfault.org)" +__version__ = "4.1.3" +__copyright__ = "Copyright (c) 2004-2012 Leonard Richardson" +__license__ = "MIT" + +__all__ = ['BeautifulSoup'] + +import re +import warnings + +from .builder import builder_registry +from .dammit import UnicodeDammit +from .element import ( + CData, + Comment, + DEFAULT_OUTPUT_ENCODING, + Declaration, + Doctype, + NavigableString, + PageElement, + ProcessingInstruction, + ResultSet, + SoupStrainer, + Tag, + ) + +# The very first thing we do is give a useful error if someone is +# running this code under Python 3 without converting it. +syntax_error = u'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work. You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).' + +class BeautifulSoup(Tag): + """ + This class defines the basic interface called by the tree builders. + + These methods will be called by the parser: + reset() + feed(markup) + + The tree builder may call these methods from its feed() implementation: + handle_starttag(name, attrs) # See note about return value + handle_endtag(name) + handle_data(data) # Appends to the current data node + endData(containerClass=NavigableString) # Ends the current data node + + No matter how complicated the underlying parser is, you should be + able to build a tree using 'start tag' events, 'end tag' events, + 'data' events, and "done with data" events. + + If you encounter an empty-element tag (aka a self-closing tag, + like HTML's
tag), call handle_starttag and then + handle_endtag. + """ + ROOT_TAG_NAME = u'[document]' + + # If the end-user gives no indication which tree builder they + # want, look for one with these features. + DEFAULT_BUILDER_FEATURES = ['html', 'fast'] + + # Used when determining whether a text node is all whitespace and + # can be replaced with a single space. A text node that contains + # fancy Unicode spaces (usually non-breaking) should be left + # alone. + STRIP_ASCII_SPACES = {9: None, 10: None, 12: None, 13: None, 32: None, } + + def __init__(self, markup="", features=None, builder=None, + parse_only=None, from_encoding=None, **kwargs): + """The Soup object is initialized as the 'root tag', and the + provided markup (which can be a string or a file-like object) + is fed into the underlying parser.""" + + if 'convertEntities' in kwargs: + warnings.warn( + "BS4 does not respect the convertEntities argument to the " + "BeautifulSoup constructor. Entities are always converted " + "to Unicode characters.") + + if 'markupMassage' in kwargs: + del kwargs['markupMassage'] + warnings.warn( + "BS4 does not respect the markupMassage argument to the " + "BeautifulSoup constructor. The tree builder is responsible " + "for any necessary markup massage.") + + if 'smartQuotesTo' in kwargs: + del kwargs['smartQuotesTo'] + warnings.warn( + "BS4 does not respect the smartQuotesTo argument to the " + "BeautifulSoup constructor. Smart quotes are always converted " + "to Unicode characters.") + + if 'selfClosingTags' in kwargs: + del kwargs['selfClosingTags'] + warnings.warn( + "BS4 does not respect the selfClosingTags argument to the " + "BeautifulSoup constructor. The tree builder is responsible " + "for understanding self-closing tags.") + + if 'isHTML' in kwargs: + del kwargs['isHTML'] + warnings.warn( + "BS4 does not respect the isHTML argument to the " + "BeautifulSoup constructor. You can pass in features='html' " + "or features='xml' to get a builder capable of handling " + "one or the other.") + + def deprecated_argument(old_name, new_name): + if old_name in kwargs: + warnings.warn( + 'The "%s" argument to the BeautifulSoup constructor ' + 'has been renamed to "%s."' % (old_name, new_name)) + value = kwargs[old_name] + del kwargs[old_name] + return value + return None + + parse_only = parse_only or deprecated_argument( + "parseOnlyThese", "parse_only") + + from_encoding = from_encoding or deprecated_argument( + "fromEncoding", "from_encoding") + + if len(kwargs) > 0: + arg = kwargs.keys().pop() + raise TypeError( + "__init__() got an unexpected keyword argument '%s'" % arg) + + if builder is None: + if isinstance(features, basestring): + features = [features] + if features is None or len(features) == 0: + features = self.DEFAULT_BUILDER_FEATURES + builder_class = builder_registry.lookup(*features) + if builder_class is None: + raise FeatureNotFound( + "Couldn't find a tree builder with the features you " + "requested: %s. Do you need to install a parser library?" + % ",".join(features)) + builder = builder_class() + self.builder = builder + self.is_xml = builder.is_xml + self.builder.soup = self + + self.parse_only = parse_only + + self.reset() + + if hasattr(markup, 'read'): # It's a file-type object. + markup = markup.read() + (self.markup, self.original_encoding, self.declared_html_encoding, + self.contains_replacement_characters) = ( + self.builder.prepare_markup(markup, from_encoding)) + + try: + self._feed() + except StopParsing: + pass + + # Clear out the markup and remove the builder's circular + # reference to this object. + self.markup = None + self.builder.soup = None + + def _feed(self): + # Convert the document to Unicode. + self.builder.reset() + + self.builder.feed(self.markup) + # Close out any unfinished strings and close all the open tags. + self.endData() + while self.currentTag.name != self.ROOT_TAG_NAME: + self.popTag() + + def reset(self): + Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME) + self.hidden = 1 + self.builder.reset() + self.currentData = [] + self.currentTag = None + self.tagStack = [] + self.pushTag(self) + + def new_tag(self, name, namespace=None, nsprefix=None, **attrs): + """Create a new tag associated with this soup.""" + return Tag(None, self.builder, name, namespace, nsprefix, attrs) + + def new_string(self, s): + """Create a new NavigableString associated with this soup.""" + navigable = NavigableString(s) + navigable.setup() + return navigable + + def insert_before(self, successor): + raise NotImplementedError("BeautifulSoup objects don't support insert_before().") + + def insert_after(self, successor): + raise NotImplementedError("BeautifulSoup objects don't support insert_after().") + + def popTag(self): + tag = self.tagStack.pop() + #print "Pop", tag.name + if self.tagStack: + self.currentTag = self.tagStack[-1] + return self.currentTag + + def pushTag(self, tag): + #print "Push", tag.name + if self.currentTag: + self.currentTag.contents.append(tag) + self.tagStack.append(tag) + self.currentTag = self.tagStack[-1] + + def endData(self, containerClass=NavigableString): + if self.currentData: + currentData = u''.join(self.currentData) + if (currentData.translate(self.STRIP_ASCII_SPACES) == '' and + not set([tag.name for tag in self.tagStack]).intersection( + self.builder.preserve_whitespace_tags)): + if '\n' in currentData: + currentData = '\n' + else: + currentData = ' ' + self.currentData = [] + if self.parse_only and len(self.tagStack) <= 1 and \ + (not self.parse_only.text or \ + not self.parse_only.search(currentData)): + return + o = containerClass(currentData) + self.object_was_parsed(o) + + def object_was_parsed(self, o): + """Add an object to the parse tree.""" + o.setup(self.currentTag, self.previous_element) + if self.previous_element: + self.previous_element.next_element = o + self.previous_element = o + self.currentTag.contents.append(o) + + def _popToTag(self, name, nsprefix=None, inclusivePop=True): + """Pops the tag stack up to and including the most recent + instance of the given tag. If inclusivePop is false, pops the tag + stack up to but *not* including the most recent instqance of + the given tag.""" + #print "Popping to %s" % name + if name == self.ROOT_TAG_NAME: + return + + numPops = 0 + mostRecentTag = None + + for i in range(len(self.tagStack) - 1, 0, -1): + if (name == self.tagStack[i].name + and nsprefix == self.tagStack[i].prefix): + numPops = len(self.tagStack) - i + break + if not inclusivePop: + numPops = numPops - 1 + + for i in range(0, numPops): + mostRecentTag = self.popTag() + return mostRecentTag + + def handle_starttag(self, name, namespace, nsprefix, attrs): + """Push a start tag on to the stack. + + If this method returns None, the tag was rejected by the + SoupStrainer. You should proceed as if the tag had not occured + in the document. For instance, if this was a self-closing tag, + don't call handle_endtag. + """ + + # print "Start tag %s: %s" % (name, attrs) + self.endData() + + if (self.parse_only and len(self.tagStack) <= 1 + and (self.parse_only.text + or not self.parse_only.search_tag(name, attrs))): + return None + + tag = Tag(self, self.builder, name, namespace, nsprefix, attrs, + self.currentTag, self.previous_element) + if tag is None: + return tag + if self.previous_element: + self.previous_element.next_element = tag + self.previous_element = tag + self.pushTag(tag) + return tag + + def handle_endtag(self, name, nsprefix=None): + #print "End tag: " + name + self.endData() + self._popToTag(name, nsprefix) + + def handle_data(self, data): + self.currentData.append(data) + + def decode(self, pretty_print=False, + eventual_encoding=DEFAULT_OUTPUT_ENCODING, + formatter="minimal"): + """Returns a string or Unicode representation of this document. + To get Unicode, pass None for encoding.""" + + if self.is_xml: + # Print the XML declaration + encoding_part = '' + if eventual_encoding != None: + encoding_part = ' encoding="%s"' % eventual_encoding + prefix = u'\n' % encoding_part + else: + prefix = u'' + if not pretty_print: + indent_level = None + else: + indent_level = 0 + return prefix + super(BeautifulSoup, self).decode( + indent_level, eventual_encoding, formatter) + +class BeautifulStoneSoup(BeautifulSoup): + """Deprecated interface to an XML parser.""" + + def __init__(self, *args, **kwargs): + kwargs['features'] = 'xml' + warnings.warn( + 'The BeautifulStoneSoup class is deprecated. Instead of using ' + 'it, pass features="xml" into the BeautifulSoup constructor.') + super(BeautifulStoneSoup, self).__init__(*args, **kwargs) + + +class StopParsing(Exception): + pass + + +class FeatureNotFound(ValueError): + pass + + +#By default, act as an HTML pretty-printer. +if __name__ == '__main__': + import sys + soup = BeautifulSoup(sys.stdin) + print soup.prettify() diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py new file mode 100644 index 00000000..dc7deb93 --- /dev/null +++ b/bs4/builder/__init__.py @@ -0,0 +1,316 @@ +from collections import defaultdict +import itertools +import sys +from bs4.element import ( + CharsetMetaAttributeValue, + ContentMetaAttributeValue, + whitespace_re + ) + +__all__ = [ + 'HTMLTreeBuilder', + 'SAXTreeBuilder', + 'TreeBuilder', + 'TreeBuilderRegistry', + ] + +# Some useful features for a TreeBuilder to have. +FAST = 'fast' +PERMISSIVE = 'permissive' +STRICT = 'strict' +XML = 'xml' +HTML = 'html' +HTML_5 = 'html5' + + +class TreeBuilderRegistry(object): + + def __init__(self): + self.builders_for_feature = defaultdict(list) + self.builders = [] + + def register(self, treebuilder_class): + """Register a treebuilder based on its advertised features.""" + for feature in treebuilder_class.features: + self.builders_for_feature[feature].insert(0, treebuilder_class) + self.builders.insert(0, treebuilder_class) + + def lookup(self, *features): + if len(self.builders) == 0: + # There are no builders at all. + return None + + if len(features) == 0: + # They didn't ask for any features. Give them the most + # recently registered builder. + return self.builders[0] + + # Go down the list of features in order, and eliminate any builders + # that don't match every feature. + features = list(features) + features.reverse() + candidates = None + candidate_set = None + while len(features) > 0: + feature = features.pop() + we_have_the_feature = self.builders_for_feature.get(feature, []) + if len(we_have_the_feature) > 0: + if candidates is None: + candidates = we_have_the_feature + candidate_set = set(candidates) + else: + # Eliminate any candidates that don't have this feature. + candidate_set = candidate_set.intersection( + set(we_have_the_feature)) + + # The only valid candidates are the ones in candidate_set. + # Go through the original list of candidates and pick the first one + # that's in candidate_set. + if candidate_set is None: + return None + for candidate in candidates: + if candidate in candidate_set: + return candidate + return None + +# The BeautifulSoup class will take feature lists from developers and use them +# to look up builders in this registry. +builder_registry = TreeBuilderRegistry() + +class TreeBuilder(object): + """Turn a document into a Beautiful Soup object tree.""" + + features = [] + + is_xml = False + 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 = {} + + + def __init__(self): + self.soup = None + + def reset(self): + pass + + def can_be_empty_element(self, tag_name): + """Might a tag with this name be an empty-element tag? + + The final markup may or may not actually present this tag as + self-closing. + + For instance: an HTMLBuilder does not consider a

tag to be + an empty-element tag (it's not in + HTMLBuilder.empty_element_tags). This means an empty

tag + will be presented as "

", not "

". + + The default implementation has no opinion about which tags are + empty-element tags, so a tag will be presented as an + empty-element tag if and only if it has no contents. + "" will become "", and "bar" will + be left alone. + """ + if self.empty_element_tags is None: + return True + return tag_name in self.empty_element_tags + + def feed(self, markup): + raise NotImplementedError() + + def prepare_markup(self, markup, user_specified_encoding=None, + document_declared_encoding=None): + return markup, None, None, False + + def test_fragment_to_document(self, fragment): + """Wrap an HTML fragment to make it look like a document. + + Different parsers do this differently. For instance, lxml + introduces an empty tag, and html5lib + doesn't. Abstracting this away lets us write simple tests + which run HTML fragments through the parser and compare the + results against other HTML fragments. + + This method should not be used outside of tests. + """ + return fragment + + def set_up_substitutions(self, tag): + return False + + def _replace_cdata_list_attribute_values(self, tag_name, attrs): + """Replaces class="foo bar" with class=["foo", "bar"] + + Modifies its input in place. + """ + if self.cdata_list_attributes: + universal = self.cdata_list_attributes.get('*', []) + tag_specific = self.cdata_list_attributes.get( + tag_name.lower(), []) + for cdata_list_attr in itertools.chain(universal, tag_specific): + if cdata_list_attr in dict(attrs): + # Basically, we have a "class" attribute whose + # value is a whitespace-separated list of CSS + # classes. Split it into a list. + value = attrs[cdata_list_attr] + if isinstance(value, basestring): + values = whitespace_re.split(value) + else: + # html5lib sometimes calls setAttributes twice + # for the same tag when rearranging the parse + # tree. On the second call the attribute value + # here is already a list. If this happens, + # leave the value alone rather than trying to + # split it again. + values = value + attrs[cdata_list_attr] = values + return attrs + +class SAXTreeBuilder(TreeBuilder): + """A Beautiful Soup treebuilder that listens for SAX events.""" + + def feed(self, markup): + raise NotImplementedError() + + def close(self): + pass + + def startElement(self, name, attrs): + attrs = dict((key[1], value) for key, value in list(attrs.items())) + #print "Start %s, %r" % (name, attrs) + self.soup.handle_starttag(name, attrs) + + def endElement(self, name): + #print "End %s" % name + self.soup.handle_endtag(name) + + def startElementNS(self, nsTuple, nodeName, attrs): + # Throw away (ns, nodeName) for now. + self.startElement(nodeName, attrs) + + def endElementNS(self, nsTuple, nodeName): + # Throw away (ns, nodeName) for now. + self.endElement(nodeName) + #handler.endElementNS((ns, node.nodeName), node.nodeName) + + def startPrefixMapping(self, prefix, nodeValue): + # Ignore the prefix for now. + pass + + def endPrefixMapping(self, prefix): + # Ignore the prefix for now. + # handler.endPrefixMapping(prefix) + pass + + def characters(self, content): + self.soup.handle_data(content) + + def startDocument(self): + pass + + def endDocument(self): + pass + + +class HTMLTreeBuilder(TreeBuilder): + """This TreeBuilder knows facts about HTML. + + Such as which tags are empty-element tags. + """ + + preserve_whitespace_tags = set(['pre', 'textarea']) + empty_element_tags = set(['br' , 'hr', 'input', 'img', 'meta', + 'spacer', 'link', 'frame', 'base']) + + # 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, + # 'foo' and 'bar', not the single value 'foo bar'. When we + # encounter one of these attributes, we will parse its value into + # a list of values if possible. Upon output, the list will be + # converted back into a string. + cdata_list_attributes = { + "*" : ['class', 'accesskey', 'dropzone'], + "a" : ['rel', 'rev'], + "link" : ['rel', 'rev'], + "td" : ["headers"], + "th" : ["headers"], + "td" : ["headers"], + "form" : ["accept-charset"], + "object" : ["archive"], + + # These are HTML5 specific, as are *.accesskey and *.dropzone above. + "area" : ["rel"], + "icon" : ["sizes"], + "iframe" : ["sandbox"], + "output" : ["for"], + } + + def set_up_substitutions(self, tag): + # We are only interested in tags + if tag.name != 'meta': + return False + + http_equiv = tag.get('http-equiv') + content = tag.get('content') + charset = tag.get('charset') + + # We are interested in tags that say what encoding the + # document was originally in. This means HTML 5-style + # tags that provide the "charset" attribute. It also means + # HTML 4-style tags that provide the "content" + # attribute and have "http-equiv" set to "content-type". + # + # In both cases we will replace the value of the appropriate + # attribute with a standin object that can take on any + # encoding. + meta_encoding = None + if charset is not None: + # HTML 5 style: + # + meta_encoding = charset + tag['charset'] = CharsetMetaAttributeValue(charset) + + elif (content is not None and http_equiv is not None + and http_equiv.lower() == 'content-type'): + # HTML 4 style: + # + tag['content'] = ContentMetaAttributeValue(content) + + return (meta_encoding is not None) + +def register_treebuilders_from(module): + """Copy TreeBuilders from the given module into this module.""" + # I'm fairly sure this is not the best way to do this. + this_module = sys.modules['bs4.builder'] + for name in module.__all__: + obj = getattr(module, name) + + if issubclass(obj, TreeBuilder): + setattr(this_module, name, obj) + this_module.__all__.append(name) + # Register the builder while we're at it. + this_module.builder_registry.register(obj) + +# 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 +# want to use HTMLParser as a last result. +from . import _htmlparser +register_treebuilders_from(_htmlparser) +try: + from . import _html5lib + register_treebuilders_from(_html5lib) +except ImportError: + # They don't have html5lib installed. + pass +try: + from . import _lxml + register_treebuilders_from(_lxml) +except ImportError: + # They don't have lxml installed. + pass diff --git a/bs4/builder/_html5lib.py b/bs4/builder/_html5lib.py new file mode 100644 index 00000000..6001e386 --- /dev/null +++ b/bs4/builder/_html5lib.py @@ -0,0 +1,222 @@ +__all__ = [ + 'HTML5TreeBuilder', + ] + +import warnings +from bs4.builder import ( + PERMISSIVE, + HTML, + HTML_5, + HTMLTreeBuilder, + ) +from bs4.element import NamespacedAttribute +import html5lib +from html5lib.constants import namespaces +from bs4.element import ( + Comment, + Doctype, + NavigableString, + Tag, + ) + +class HTML5TreeBuilder(HTMLTreeBuilder): + """Use html5lib to build a tree.""" + + features = ['html5lib', PERMISSIVE, HTML_5, HTML] + + def prepare_markup(self, markup, user_specified_encoding): + # Store the user-specified encoding for use later on. + self.user_specified_encoding = user_specified_encoding + return markup, None, None, False + + # These methods are defined by Beautiful Soup. + def feed(self, markup): + if self.soup.parse_only is not None: + warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.") + parser = html5lib.HTMLParser(tree=self.create_treebuilder) + doc = parser.parse(markup, encoding=self.user_specified_encoding) + + # Set the character encoding detected by the tokenizer. + if isinstance(markup, unicode): + # We need to special-case this because html5lib sets + # charEncoding to UTF-8 if it gets Unicode input. + doc.original_encoding = None + else: + doc.original_encoding = parser.tokenizer.stream.charEncoding[0] + + def create_treebuilder(self, namespaceHTMLElements): + self.underlying_builder = TreeBuilderForHtml5lib( + self.soup, namespaceHTMLElements) + return self.underlying_builder + + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'%s' % fragment + + +class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder): + + def __init__(self, soup, namespaceHTMLElements): + self.soup = soup + super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements) + + def documentClass(self): + self.soup.reset() + return Element(self.soup, self.soup, None) + + def insertDoctype(self, token): + name = token["name"] + publicId = token["publicId"] + systemId = token["systemId"] + + doctype = Doctype.for_name_and_ids(name, publicId, systemId) + self.soup.object_was_parsed(doctype) + + def elementClass(self, name, namespace): + tag = self.soup.new_tag(name, namespace) + return Element(tag, self.soup, namespace) + + def commentClass(self, data): + return TextNode(Comment(data), self.soup) + + def fragmentClass(self): + self.soup = BeautifulSoup("") + self.soup.name = "[document_fragment]" + return Element(self.soup, self.soup, None) + + def appendChild(self, node): + # XXX This code is not covered by the BS4 tests. + self.soup.append(node.element) + + def getDocument(self): + return self.soup + + def getFragment(self): + return html5lib.treebuilders._base.TreeBuilder.getFragment(self).element + +class AttrList(object): + def __init__(self, element): + self.element = element + self.attrs = dict(self.element.attrs) + def __iter__(self): + return list(self.attrs.items()).__iter__() + def __setitem__(self, name, value): + "set attr", name, value + self.element[name] = value + def items(self): + return list(self.attrs.items()) + def keys(self): + return list(self.attrs.keys()) + def __len__(self): + return len(self.attrs) + def __getitem__(self, name): + return self.attrs[name] + def __contains__(self, name): + return name in list(self.attrs.keys()) + + +class Element(html5lib.treebuilders._base.Node): + def __init__(self, element, soup, namespace): + html5lib.treebuilders._base.Node.__init__(self, element.name) + self.element = element + self.soup = soup + self.namespace = namespace + + def appendChild(self, node): + if (node.element.__class__ == NavigableString and self.element.contents + and self.element.contents[-1].__class__ == NavigableString): + # Concatenate new text onto old text node + # XXX This has O(n^2) performance, for input like + # "aaa..." + old_element = self.element.contents[-1] + new_element = self.soup.new_string(old_element + node.element) + old_element.replace_with(new_element) + else: + self.element.append(node.element) + node.parent = self + + def getAttributes(self): + return AttrList(self.element) + + def setAttributes(self, attributes): + if attributes is not None and len(attributes) > 0: + + converted_attributes = [] + for name, value in list(attributes.items()): + if isinstance(name, tuple): + new_name = NamespacedAttribute(*name) + del attributes[name] + attributes[new_name] = value + + self.soup.builder._replace_cdata_list_attribute_values( + self.name, attributes) + for name, value in attributes.items(): + self.element[name] = value + + # The attributes may contain variables that need substitution. + # Call set_up_substitutions manually. + # + # The Tag constructor called this method when the Tag was created, + # but we just set/changed the attributes, so call it again. + self.soup.builder.set_up_substitutions(self.element) + attributes = property(getAttributes, setAttributes) + + def insertText(self, data, insertBefore=None): + text = TextNode(self.soup.new_string(data), self.soup) + if insertBefore: + self.insertBefore(text, insertBefore) + else: + self.appendChild(text) + + def insertBefore(self, node, refNode): + index = self.element.index(refNode.element) + if (node.element.__class__ == NavigableString and self.element.contents + and self.element.contents[index-1].__class__ == NavigableString): + # (See comments in appendChild) + old_node = self.element.contents[index-1] + new_str = self.soup.new_string(old_node + node.element) + old_node.replace_with(new_str) + else: + self.element.insert(index, node.element) + node.parent = self + + def removeChild(self, node): + node.element.extract() + + def reparentChildren(self, newParent): + while self.element.contents: + child = self.element.contents[0] + child.extract() + if isinstance(child, Tag): + newParent.appendChild( + Element(child, self.soup, namespaces["html"])) + else: + newParent.appendChild( + TextNode(child, self.soup)) + + def cloneNode(self): + tag = self.soup.new_tag(self.element.name, self.namespace) + node = Element(tag, self.soup, self.namespace) + for key,value in self.attributes: + node.attributes[key] = value + return node + + def hasContent(self): + return self.element.contents + + def getNameTuple(self): + if self.namespace == None: + return namespaces["html"], self.name + else: + return self.namespace, self.name + + nameTuple = property(getNameTuple) + +class TextNode(Element): + def __init__(self, element, soup): + html5lib.treebuilders._base.Node.__init__(self, None) + self.element = element + self.soup = soup + + def cloneNode(self): + raise NotImplementedError diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py new file mode 100644 index 00000000..ede5cecb --- /dev/null +++ b/bs4/builder/_htmlparser.py @@ -0,0 +1,244 @@ +"""Use the HTMLParser library to parse HTML files that aren't too bad.""" + +__all__ = [ + 'HTMLParserTreeBuilder', + ] + +from HTMLParser import ( + HTMLParser, + HTMLParseError, + ) +import sys +import warnings + +# Starting in Python 3.2, the HTMLParser constructor takes a 'strict' +# argument, which we'd like to set to False. Unfortunately, +# http://bugs.python.org/issue13273 makes strict=True a better bet +# before Python 3.2.3. +# +# At the end of this file, we monkeypatch HTMLParser so that +# strict=True works well on Python 3.2.2. +major, minor, release = sys.version_info[:3] +CONSTRUCTOR_TAKES_STRICT = ( + major > 3 + or (major == 3 and minor > 2) + or (major == 3 and minor == 2 and release >= 3)) + +from bs4.element import ( + CData, + Comment, + Declaration, + Doctype, + ProcessingInstruction, + ) +from bs4.dammit import EntitySubstitution, UnicodeDammit + +from bs4.builder import ( + HTML, + HTMLTreeBuilder, + STRICT, + ) + + +HTMLPARSER = 'html.parser' + +class BeautifulSoupHTMLParser(HTMLParser): + def handle_starttag(self, name, attrs): + # XXX namespace + self.soup.handle_starttag(name, None, None, dict(attrs)) + + def handle_endtag(self, name): + self.soup.handle_endtag(name) + + def handle_data(self, data): + self.soup.handle_data(data) + + def handle_charref(self, name): + # XXX workaround for a bug in HTMLParser. Remove this once + # it's fixed. + if name.startswith('x'): + real_name = int(name.lstrip('x'), 16) + else: + real_name = int(name) + + try: + data = unichr(real_name) + except (ValueError, OverflowError), e: + data = u"\N{REPLACEMENT CHARACTER}" + + self.handle_data(data) + + def handle_entityref(self, name): + character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name) + if character is not None: + data = character + else: + data = "&%s;" % name + self.handle_data(data) + + def handle_comment(self, data): + self.soup.endData() + self.soup.handle_data(data) + self.soup.endData(Comment) + + def handle_decl(self, data): + self.soup.endData() + if data.startswith("DOCTYPE "): + data = data[len("DOCTYPE "):] + self.soup.handle_data(data) + self.soup.endData(Doctype) + + def unknown_decl(self, data): + if data.upper().startswith('CDATA['): + cls = CData + data = data[len('CDATA['):] + else: + cls = Declaration + self.soup.endData() + self.soup.handle_data(data) + self.soup.endData(cls) + + def handle_pi(self, data): + self.soup.endData() + if data.endswith("?") and data.lower().startswith("xml"): + # "An XHTML processing instruction using the trailing '?' + # will cause the '?' to be included in data." - HTMLParser + # docs. + # + # Strip the question mark so we don't end up with two + # question marks. + data = data[:-1] + self.soup.handle_data(data) + self.soup.endData(ProcessingInstruction) + + +class HTMLParserTreeBuilder(HTMLTreeBuilder): + + is_xml = False + features = [HTML, STRICT, HTMLPARSER] + + def __init__(self, *args, **kwargs): + if CONSTRUCTOR_TAKES_STRICT: + kwargs['strict'] = False + self.parser_args = (args, kwargs) + + def prepare_markup(self, markup, user_specified_encoding=None, + document_declared_encoding=None): + """ + :return: A 4-tuple (markup, original encoding, encoding + declared within markup, whether any characters had to be + replaced with REPLACEMENT CHARACTER). + """ + if isinstance(markup, unicode): + return markup, None, None, False + + try_encodings = [user_specified_encoding, document_declared_encoding] + dammit = UnicodeDammit(markup, try_encodings, is_html=True) + return (dammit.markup, dammit.original_encoding, + dammit.declared_html_encoding, + dammit.contains_replacement_characters) + + def feed(self, markup): + args, kwargs = self.parser_args + parser = BeautifulSoupHTMLParser(*args, **kwargs) + parser.soup = self.soup + try: + parser.feed(markup) + 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.")) + raise e + +# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some +# 3.2.3 code. This ensures they don't treat markup like

as a +# string. +# +# XXX This code can be removed once most Python 3 users are on 3.2.3. +if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT: + import re + attrfind_tolerant = re.compile( + r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*' + r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?') + HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant + + locatestarttagend = re.compile(r""" + <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name + (?:\s+ # whitespace before attribute name + (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name + (?:\s*=\s* # value indicator + (?:'[^']*' # LITA-enclosed value + |\"[^\"]*\" # LIT-enclosed value + |[^'\">\s]+ # bare value + ) + )? + ) + )* + \s* # trailing whitespace +""", re.VERBOSE) + BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend + + from html.parser import tagfind, attrfind + + def parse_starttag(self, i): + self.__starttag_text = None + endpos = self.check_for_whole_start_tag(i) + if endpos < 0: + return endpos + rawdata = self.rawdata + self.__starttag_text = rawdata[i:endpos] + + # Now parse the data between i+1 and j into a tag and attrs + attrs = [] + match = tagfind.match(rawdata, i+1) + assert match, 'unexpected call to parse_starttag()' + k = match.end() + self.lasttag = tag = rawdata[i+1:k].lower() + while k < endpos: + if self.strict: + m = attrfind.match(rawdata, k) + else: + m = attrfind_tolerant.match(rawdata, k) + if not m: + break + attrname, rest, attrvalue = m.group(1, 2, 3) + if not rest: + attrvalue = None + elif attrvalue[:1] == '\'' == attrvalue[-1:] or \ + attrvalue[:1] == '"' == attrvalue[-1:]: + attrvalue = attrvalue[1:-1] + if attrvalue: + attrvalue = self.unescape(attrvalue) + attrs.append((attrname.lower(), attrvalue)) + k = m.end() + + end = rawdata[k:endpos].strip() + if end not in (">", "/>"): + lineno, offset = self.getpos() + if "\n" in self.__starttag_text: + lineno = lineno + self.__starttag_text.count("\n") + offset = len(self.__starttag_text) \ + - self.__starttag_text.rfind("\n") + else: + offset = offset + len(self.__starttag_text) + if self.strict: + self.error("junk characters in start tag: %r" + % (rawdata[k:endpos][:20],)) + self.handle_data(rawdata[i:endpos]) + return endpos + if end.endswith('/>'): + # XHTML-style empty tag: + self.handle_startendtag(tag, attrs) + else: + self.handle_starttag(tag, attrs) + if tag in self.CDATA_CONTENT_ELEMENTS: + self.set_cdata_mode(tag) + return endpos + + def set_cdata_mode(self, elem): + self.cdata_elem = elem.lower() + self.interesting = re.compile(r'' % self.cdata_elem, re.I) + + BeautifulSoupHTMLParser.parse_starttag = parse_starttag + BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode + + CONSTRUCTOR_TAKES_STRICT = True diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py new file mode 100644 index 00000000..f6b91ff5 --- /dev/null +++ b/bs4/builder/_lxml.py @@ -0,0 +1,199 @@ +__all__ = [ + 'LXMLTreeBuilderForXML', + 'LXMLTreeBuilder', + ] + +from StringIO import StringIO +import collections +from lxml import etree +from bs4.element import Comment, Doctype, NamespacedAttribute +from bs4.builder import ( + FAST, + HTML, + HTMLTreeBuilder, + PERMISSIVE, + TreeBuilder, + XML) +from bs4.dammit import UnicodeDammit + +LXML = 'lxml' + +class LXMLTreeBuilderForXML(TreeBuilder): + DEFAULT_PARSER_CLASS = etree.XMLParser + + is_xml = True + + # Well, it's permissive by XML parser standards. + features = [LXML, XML, FAST, PERMISSIVE] + + CHUNK_SIZE = 512 + + @property + def default_parser(self): + # This can either return a parser object or a class, which + # will be instantiated with default arguments. + return etree.XMLParser(target=self, strip_cdata=False, recover=True) + + def __init__(self, parser=None, empty_element_tags=None): + if empty_element_tags is not None: + self.empty_element_tags = set(empty_element_tags) + if parser is None: + # Use the default parser. + parser = self.default_parser + if isinstance(parser, collections.Callable): + # Instantiate the parser with default arguments + parser = parser(target=self, strip_cdata=False) + self.parser = parser + self.soup = None + self.nsmaps = None + + def _getNsTag(self, tag): + # Split the namespace URL out of a fully-qualified lxml tag + # name. Copied from lxml's src/lxml/sax.py. + if tag[0] == '{': + return tuple(tag[1:].split('}', 1)) + else: + return (None, tag) + + def prepare_markup(self, markup, user_specified_encoding=None, + document_declared_encoding=None): + """ + :return: A 3-tuple (markup, original encoding, encoding + declared within markup). + """ + if isinstance(markup, unicode): + return markup, None, None, False + + try_encodings = [user_specified_encoding, document_declared_encoding] + dammit = UnicodeDammit(markup, try_encodings, is_html=True) + return (dammit.markup, dammit.original_encoding, + dammit.declared_html_encoding, + dammit.contains_replacement_characters) + + def feed(self, markup): + if isinstance(markup, basestring): + markup = StringIO(markup) + # Call feed() at least once, even if the markup is empty, + # or the parser won't be initialized. + data = markup.read(self.CHUNK_SIZE) + self.parser.feed(data) + while data != '': + # Now call feed() on the rest of the data, chunk by chunk. + data = markup.read(self.CHUNK_SIZE) + if data != '': + self.parser.feed(data) + self.parser.close() + + def close(self): + self.nsmaps = None + + def start(self, name, attrs, nsmap={}): + # Make sure attrs is a mutable dict--lxml may send an immutable dictproxy. + attrs = dict(attrs) + + nsprefix = None + # Invert each namespace map as it comes in. + if len(nsmap) == 0 and self.nsmaps != None: + # There are no new namespaces for this tag, but namespaces + # are in play, so we need a separate tag stack to know + # when they end. + self.nsmaps.append(None) + elif len(nsmap) > 0: + # A new namespace mapping has come into play. + if self.nsmaps is None: + self.nsmaps = [] + inverted_nsmap = dict((value, key) for key, value in nsmap.items()) + self.nsmaps.append(inverted_nsmap) + # Also treat the namespace mapping as a set of attributes on the + # tag, so we can recreate it later. + attrs = attrs.copy() + for prefix, namespace in nsmap.items(): + attribute = NamespacedAttribute( + "xmlns", prefix, "http://www.w3.org/2000/xmlns/") + attrs[attribute] = namespace + + if self.nsmaps is not None and len(self.nsmaps) > 0: + # Namespaces are in play. Find any attributes that came in + # from lxml with namespaces attached to their names, and + # turn then into NamespacedAttribute objects. + new_attrs = {} + for attr, value in attrs.items(): + namespace, attr = self._getNsTag(attr) + if namespace is None: + new_attrs[attr] = value + else: + nsprefix = self._prefix_for_namespace(namespace) + attr = NamespacedAttribute(nsprefix, attr, namespace) + new_attrs[attr] = value + attrs = new_attrs + + namespace, name = self._getNsTag(name) + nsprefix = self._prefix_for_namespace(namespace) + self.soup.handle_starttag(name, namespace, nsprefix, attrs) + + def _prefix_for_namespace(self, namespace): + """Find the currently active prefix for the given namespace.""" + if namespace is None: + return None + for inverted_nsmap in reversed(self.nsmaps): + if inverted_nsmap is not None and namespace in inverted_nsmap: + return inverted_nsmap[namespace] + + def end(self, name): + self.soup.endData() + completed_tag = self.soup.tagStack[-1] + namespace, name = self._getNsTag(name) + nsprefix = None + if namespace is not None: + for inverted_nsmap in reversed(self.nsmaps): + if inverted_nsmap is not None and namespace in inverted_nsmap: + nsprefix = inverted_nsmap[namespace] + break + self.soup.handle_endtag(name, nsprefix) + if self.nsmaps != None: + # This tag, or one of its parents, introduced a namespace + # mapping, so pop it off the stack. + self.nsmaps.pop() + if len(self.nsmaps) == 0: + # Namespaces are no longer in play, so don't bother keeping + # track of the namespace stack. + self.nsmaps = None + + def pi(self, target, data): + pass + + def data(self, content): + self.soup.handle_data(content) + + def doctype(self, name, pubid, system): + self.soup.endData() + doctype = Doctype.for_name_and_ids(name, pubid, system) + self.soup.object_was_parsed(doctype) + + def comment(self, content): + "Handle comments as Comment objects." + self.soup.endData() + self.soup.handle_data(content) + self.soup.endData(Comment) + + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'\n%s' % fragment + + +class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): + + features = [LXML, HTML, FAST, PERMISSIVE] + is_xml = False + + @property + def default_parser(self): + return etree.HTMLParser + + def feed(self, markup): + self.parser.feed(markup) + self.parser.close() + + def test_fragment_to_document(self, fragment): + """See `TreeBuilder`.""" + return u'%s' % fragment diff --git a/bs4/dammit.py b/bs4/dammit.py new file mode 100644 index 00000000..983ade0f --- /dev/null +++ b/bs4/dammit.py @@ -0,0 +1,803 @@ +# -*- coding: utf-8 -*- +"""Beautiful Soup bonus library: Unicode, Dammit + +This class forces XML data into a standard format (usually to UTF-8 or +Unicode). It is heavily based on code from Mark Pilgrim's Universal +Feed Parser. It does not rewrite the XML or HTML to reflect a new +encoding; that's the tree builder's job. +""" + +import codecs +from htmlentitydefs import codepoint2name +import re +import logging + +# Import a library to autodetect character encodings. +chardet_type = None +try: + # First try the fast C implementation. + # PyPI package: cchardet + import cchardet + def chardet_dammit(s): + return cchardet.detect(s)['encoding'] +except ImportError: + try: + # Fall back to the pure Python implementation + # Debian package: python-chardet + # PyPI package: chardet + import chardet + def chardet_dammit(s): + return chardet.detect(s)['encoding'] + #import chardet.constants + #chardet.constants._debug = 1 + except ImportError: + # No chardet available. + def chardet_dammit(s): + return None + +# Available from http://cjkpython.i18n.org/. +try: + import iconv_codec +except ImportError: + pass + +xml_encoding_re = re.compile( + '^<\?.*encoding=[\'"](.*?)[\'"].*\?>'.encode(), re.I) +html_meta_re = re.compile( + '<\s*meta[^>]+charset\s*=\s*["\']?([^>]*?)[ /;\'">]'.encode(), re.I) + +class EntitySubstitution(object): + + """Substitute XML or HTML entities for the corresponding characters.""" + + def _populate_class_variables(): + lookup = {} + reverse_lookup = {} + characters_for_re = [] + for codepoint, name in list(codepoint2name.items()): + character = unichr(codepoint) + if codepoint != 34: + # There's no point in turning the quotation mark into + # ", unless it happens within an attribute value, which + # is handled elsewhere. + characters_for_re.append(character) + lookup[character] = name + # But we do want to turn " into the quotation mark. + reverse_lookup[name] = character + re_definition = "[%s]" % "".join(characters_for_re) + return lookup, reverse_lookup, re.compile(re_definition) + (CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER, + CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables() + + CHARACTER_TO_XML_ENTITY = { + "'": "apos", + '"': "quot", + "&": "amp", + "<": "lt", + ">": "gt", + } + + BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|" + "&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)" + ")") + + @classmethod + def _substitute_html_entity(cls, matchobj): + entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0)) + return "&%s;" % entity + + @classmethod + def _substitute_xml_entity(cls, matchobj): + """Used with a regular expression to substitute the + appropriate XML entity for an XML special character.""" + entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)] + return "&%s;" % entity + + @classmethod + def quoted_attribute_value(self, value): + """Make a value into a quoted XML attribute, possibly escaping it. + + Most strings will be quoted using double quotes. + + Bob's Bar -> "Bob's Bar" + + If a string contains double quotes, it will be quoted using + single quotes. + + Welcome to "my bar" -> 'Welcome to "my bar"' + + If a string contains both single and double quotes, the + double quotes will be escaped, and the string will be quoted + using double quotes. + + Welcome to "Bob's Bar" -> "Welcome to "Bob's bar" + """ + quote_with = '"' + if '"' in value: + if "'" in value: + # The string contains both single and double + # quotes. Turn the double quotes into + # entities. We quote the double quotes rather than + # the single quotes because the entity name is + # """ whether this is HTML or XML. If we + # quoted the single quotes, we'd have to decide + # between ' and &squot;. + replace_with = """ + value = value.replace('"', replace_with) + else: + # There are double quotes but no single quotes. + # We can use single quotes to quote the attribute. + quote_with = "'" + return quote_with + value + quote_with + + @classmethod + def substitute_xml(cls, value, make_quoted_attribute=False): + """Substitute XML entities for special XML characters. + + :param value: A string to be substituted. The less-than sign will + become <, the greater-than sign will become >, and any + ampersands that are not part of an entity defition will + become &. + + :param make_quoted_attribute: If True, then the string will be + quoted, as befits an attribute value. + """ + # Escape angle brackets, and ampersands that aren't part of + # entities. + value = cls.BARE_AMPERSAND_OR_BRACKET.sub( + cls._substitute_xml_entity, value) + + if make_quoted_attribute: + value = cls.quoted_attribute_value(value) + return value + + @classmethod + def substitute_html(cls, s): + """Replace certain Unicode characters with named HTML entities. + + This differs from data.encode(encoding, 'xmlcharrefreplace') + in that the goal is to make the result more readable (to those + with ASCII displays) rather than to recover from + errors. There's absolutely nothing wrong with a UTF-8 string + containg a LATIN SMALL LETTER E WITH ACUTE, but replacing that + character with "é" will make it more readable to some + people. + """ + return cls.CHARACTER_TO_HTML_ENTITY_RE.sub( + cls._substitute_html_entity, s) + + +class UnicodeDammit: + """A class for detecting the encoding of a *ML document and + converting it to a Unicode string. If the source encoding is + windows-1252, can replace MS smart quotes with their HTML or XML + equivalents.""" + + # This dictionary maps commonly seen values for "charset" in HTML + # meta tags to the corresponding Python codec names. It only covers + # values that aren't in Python's aliases and can't be determined + # by the heuristics in find_codec. + CHARSET_ALIASES = {"macintosh": "mac-roman", + "x-sjis": "shift-jis"} + + ENCODINGS_WITH_SMART_QUOTES = [ + "windows-1252", + "iso-8859-1", + "iso-8859-2", + ] + + def __init__(self, markup, override_encodings=[], + smart_quotes_to=None, is_html=False): + self.declared_html_encoding = None + self.smart_quotes_to = smart_quotes_to + self.tried_encodings = [] + self.contains_replacement_characters = False + + if markup == '' or isinstance(markup, unicode): + self.markup = markup + self.unicode_markup = unicode(markup) + self.original_encoding = None + return + + new_markup, document_encoding, sniffed_encoding = \ + self._detectEncoding(markup, is_html) + self.markup = new_markup + + u = None + if new_markup != markup: + # _detectEncoding modified the markup, then converted it to + # Unicode and then to UTF-8. So convert it from UTF-8. + u = self._convert_from("utf8") + self.original_encoding = sniffed_encoding + + if not u: + for proposed_encoding in ( + override_encodings + [document_encoding, sniffed_encoding]): + if proposed_encoding is not None: + u = self._convert_from(proposed_encoding) + if u: + break + + # If no luck and we have auto-detection library, try that: + if not u and not isinstance(self.markup, unicode): + u = self._convert_from(chardet_dammit(self.markup)) + + # As a last resort, try utf-8 and windows-1252: + if not u: + for proposed_encoding in ("utf-8", "windows-1252"): + u = self._convert_from(proposed_encoding) + if u: + break + + # As an absolute last resort, try the encodings again with + # character replacement. + if not u: + for proposed_encoding in ( + override_encodings + [ + document_encoding, sniffed_encoding, "utf-8", "windows-1252"]): + if proposed_encoding != "ascii": + u = self._convert_from(proposed_encoding, "replace") + if u is not None: + logging.warning( + "Some characters could not be decoded, and were " + "replaced with REPLACEMENT CHARACTER.") + self.contains_replacement_characters = True + break + + # We could at this point force it to ASCII, but that would + # destroy so much data that I think giving up is better + self.unicode_markup = u + if not u: + self.original_encoding = None + + def _sub_ms_char(self, match): + """Changes a MS smart quote character to an XML or HTML + entity, or an ASCII character.""" + orig = match.group(1) + if self.smart_quotes_to == 'ascii': + sub = self.MS_CHARS_TO_ASCII.get(orig).encode() + else: + sub = self.MS_CHARS.get(orig) + if type(sub) == tuple: + if self.smart_quotes_to == 'xml': + sub = '&#x'.encode() + sub[1].encode() + ';'.encode() + else: + sub = '&'.encode() + sub[0].encode() + ';'.encode() + else: + sub = sub.encode() + return sub + + def _convert_from(self, proposed, errors="strict"): + proposed = self.find_codec(proposed) + if not proposed or (proposed, errors) in self.tried_encodings: + return None + self.tried_encodings.append((proposed, errors)) + markup = self.markup + + # Convert smart quotes to HTML if coming from an encoding + # that might have them. + if (self.smart_quotes_to is not None + and proposed.lower() in self.ENCODINGS_WITH_SMART_QUOTES): + smart_quotes_re = b"([\x80-\x9f])" + smart_quotes_compiled = re.compile(smart_quotes_re) + markup = smart_quotes_compiled.sub(self._sub_ms_char, markup) + + try: + #print "Trying to convert document to %s (errors=%s)" % ( + # proposed, errors) + u = self._to_unicode(markup, proposed, errors) + self.markup = u + self.original_encoding = proposed + except Exception as e: + #print "That didn't work!" + #print e + return None + #print "Correct encoding: %s" % proposed + return self.markup + + def _to_unicode(self, data, encoding, errors="strict"): + '''Given a string and its encoding, decodes the string into Unicode. + %encoding is a string recognized by encodings.aliases''' + + # strip Byte Order Mark (if present) + if (len(data) >= 4) and (data[:2] == '\xfe\xff') \ + and (data[2:4] != '\x00\x00'): + encoding = 'utf-16be' + data = data[2:] + elif (len(data) >= 4) and (data[:2] == '\xff\xfe') \ + and (data[2:4] != '\x00\x00'): + encoding = 'utf-16le' + data = data[2:] + elif data[:3] == '\xef\xbb\xbf': + encoding = 'utf-8' + data = data[3:] + elif data[:4] == '\x00\x00\xfe\xff': + encoding = 'utf-32be' + data = data[4:] + elif data[:4] == '\xff\xfe\x00\x00': + encoding = 'utf-32le' + data = data[4:] + newdata = unicode(data, encoding, errors) + return newdata + + def _detectEncoding(self, xml_data, is_html=False): + """Given a document, tries to detect its XML encoding.""" + xml_encoding = sniffed_xml_encoding = None + try: + if xml_data[:4] == b'\x4c\x6f\xa7\x94': + # EBCDIC + xml_data = self._ebcdic_to_ascii(xml_data) + elif xml_data[:4] == b'\x00\x3c\x00\x3f': + # UTF-16BE + sniffed_xml_encoding = 'utf-16be' + xml_data = unicode(xml_data, 'utf-16be').encode('utf-8') + elif (len(xml_data) >= 4) and (xml_data[:2] == b'\xfe\xff') \ + and (xml_data[2:4] != b'\x00\x00'): + # UTF-16BE with BOM + sniffed_xml_encoding = 'utf-16be' + xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8') + elif xml_data[:4] == b'\x3c\x00\x3f\x00': + # UTF-16LE + sniffed_xml_encoding = 'utf-16le' + xml_data = unicode(xml_data, 'utf-16le').encode('utf-8') + elif (len(xml_data) >= 4) and (xml_data[:2] == b'\xff\xfe') and \ + (xml_data[2:4] != b'\x00\x00'): + # UTF-16LE with BOM + sniffed_xml_encoding = 'utf-16le' + xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8') + elif xml_data[:4] == b'\x00\x00\x00\x3c': + # UTF-32BE + sniffed_xml_encoding = 'utf-32be' + xml_data = unicode(xml_data, 'utf-32be').encode('utf-8') + elif xml_data[:4] == b'\x3c\x00\x00\x00': + # UTF-32LE + sniffed_xml_encoding = 'utf-32le' + xml_data = unicode(xml_data, 'utf-32le').encode('utf-8') + elif xml_data[:4] == b'\x00\x00\xfe\xff': + # UTF-32BE with BOM + sniffed_xml_encoding = 'utf-32be' + xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8') + elif xml_data[:4] == b'\xff\xfe\x00\x00': + # UTF-32LE with BOM + sniffed_xml_encoding = 'utf-32le' + xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8') + elif xml_data[:3] == b'\xef\xbb\xbf': + # UTF-8 with BOM + sniffed_xml_encoding = 'utf-8' + xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8') + else: + sniffed_xml_encoding = 'ascii' + pass + except: + xml_encoding_match = None + xml_encoding_match = xml_encoding_re.match(xml_data) + if not xml_encoding_match and is_html: + xml_encoding_match = html_meta_re.search(xml_data) + if xml_encoding_match is not None: + xml_encoding = xml_encoding_match.groups()[0].decode( + 'ascii').lower() + if is_html: + self.declared_html_encoding = xml_encoding + if sniffed_xml_encoding and \ + (xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode', + 'iso-10646-ucs-4', 'ucs-4', 'csucs4', + 'utf-16', 'utf-32', 'utf_16', 'utf_32', + 'utf16', 'u16')): + xml_encoding = sniffed_xml_encoding + return xml_data, xml_encoding, sniffed_xml_encoding + + def find_codec(self, charset): + return self._codec(self.CHARSET_ALIASES.get(charset, charset)) \ + or (charset and self._codec(charset.replace("-", ""))) \ + or (charset and self._codec(charset.replace("-", "_"))) \ + or charset + + def _codec(self, charset): + if not charset: + return charset + codec = None + try: + codecs.lookup(charset) + codec = charset + except (LookupError, ValueError): + pass + return codec + + EBCDIC_TO_ASCII_MAP = None + + def _ebcdic_to_ascii(self, s): + c = self.__class__ + if not c.EBCDIC_TO_ASCII_MAP: + emap = (0,1,2,3,156,9,134,127,151,141,142,11,12,13,14,15, + 16,17,18,19,157,133,8,135,24,25,146,143,28,29,30,31, + 128,129,130,131,132,10,23,27,136,137,138,139,140,5,6,7, + 144,145,22,147,148,149,150,4,152,153,154,155,20,21,158,26, + 32,160,161,162,163,164,165,166,167,168,91,46,60,40,43,33, + 38,169,170,171,172,173,174,175,176,177,93,36,42,41,59,94, + 45,47,178,179,180,181,182,183,184,185,124,44,37,95,62,63, + 186,187,188,189,190,191,192,193,194,96,58,35,64,39,61,34, + 195,97,98,99,100,101,102,103,104,105,196,197,198,199,200, + 201,202,106,107,108,109,110,111,112,113,114,203,204,205, + 206,207,208,209,126,115,116,117,118,119,120,121,122,210, + 211,212,213,214,215,216,217,218,219,220,221,222,223,224, + 225,226,227,228,229,230,231,123,65,66,67,68,69,70,71,72, + 73,232,233,234,235,236,237,125,74,75,76,77,78,79,80,81, + 82,238,239,240,241,242,243,92,159,83,84,85,86,87,88,89, + 90,244,245,246,247,248,249,48,49,50,51,52,53,54,55,56,57, + 250,251,252,253,254,255) + import string + c.EBCDIC_TO_ASCII_MAP = string.maketrans( + ''.join(map(chr, list(range(256)))), ''.join(map(chr, emap))) + return s.translate(c.EBCDIC_TO_ASCII_MAP) + + # A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities. + MS_CHARS = {b'\x80': ('euro', '20AC'), + b'\x81': ' ', + b'\x82': ('sbquo', '201A'), + b'\x83': ('fnof', '192'), + b'\x84': ('bdquo', '201E'), + b'\x85': ('hellip', '2026'), + b'\x86': ('dagger', '2020'), + b'\x87': ('Dagger', '2021'), + b'\x88': ('circ', '2C6'), + b'\x89': ('permil', '2030'), + b'\x8A': ('Scaron', '160'), + b'\x8B': ('lsaquo', '2039'), + b'\x8C': ('OElig', '152'), + b'\x8D': '?', + b'\x8E': ('#x17D', '17D'), + b'\x8F': '?', + b'\x90': '?', + b'\x91': ('lsquo', '2018'), + b'\x92': ('rsquo', '2019'), + b'\x93': ('ldquo', '201C'), + b'\x94': ('rdquo', '201D'), + b'\x95': ('bull', '2022'), + b'\x96': ('ndash', '2013'), + b'\x97': ('mdash', '2014'), + b'\x98': ('tilde', '2DC'), + b'\x99': ('trade', '2122'), + b'\x9a': ('scaron', '161'), + b'\x9b': ('rsaquo', '203A'), + b'\x9c': ('oelig', '153'), + b'\x9d': '?', + b'\x9e': ('#x17E', '17E'), + b'\x9f': ('Yuml', ''),} + + # A parochial partial mapping of ISO-Latin-1 to ASCII. Contains + # horrors like stripping diacritical marks to turn á into a, but also + # contains non-horrors like turning “ into ". + MS_CHARS_TO_ASCII = { + b'\x80' : 'EUR', + b'\x81' : ' ', + b'\x82' : ',', + b'\x83' : 'f', + b'\x84' : ',,', + b'\x85' : '...', + b'\x86' : '+', + b'\x87' : '++', + b'\x88' : '^', + b'\x89' : '%', + b'\x8a' : 'S', + b'\x8b' : '<', + b'\x8c' : 'OE', + b'\x8d' : '?', + b'\x8e' : 'Z', + b'\x8f' : '?', + b'\x90' : '?', + b'\x91' : "'", + b'\x92' : "'", + b'\x93' : '"', + b'\x94' : '"', + b'\x95' : '*', + b'\x96' : '-', + b'\x97' : '--', + b'\x98' : '~', + b'\x99' : '(TM)', + b'\x9a' : 's', + b'\x9b' : '>', + b'\x9c' : 'oe', + b'\x9d' : '?', + b'\x9e' : 'z', + b'\x9f' : 'Y', + b'\xa0' : ' ', + b'\xa1' : '!', + b'\xa2' : 'c', + b'\xa3' : 'GBP', + b'\xa4' : '$', #This approximation is especially parochial--this is the + #generic currency symbol. + b'\xa5' : 'YEN', + b'\xa6' : '|', + b'\xa7' : 'S', + b'\xa8' : '..', + b'\xa9' : '', + b'\xaa' : '(th)', + b'\xab' : '<<', + b'\xac' : '!', + b'\xad' : ' ', + b'\xae' : '(R)', + b'\xaf' : '-', + b'\xb0' : 'o', + b'\xb1' : '+-', + b'\xb2' : '2', + b'\xb3' : '3', + b'\xb4' : ("'", 'acute'), + b'\xb5' : 'u', + b'\xb6' : 'P', + b'\xb7' : '*', + b'\xb8' : ',', + b'\xb9' : '1', + b'\xba' : '(th)', + b'\xbb' : '>>', + b'\xbc' : '1/4', + b'\xbd' : '1/2', + b'\xbe' : '3/4', + b'\xbf' : '?', + b'\xc0' : 'A', + b'\xc1' : 'A', + b'\xc2' : 'A', + b'\xc3' : 'A', + b'\xc4' : 'A', + b'\xc5' : 'A', + b'\xc6' : 'AE', + b'\xc7' : 'C', + b'\xc8' : 'E', + b'\xc9' : 'E', + b'\xca' : 'E', + b'\xcb' : 'E', + b'\xcc' : 'I', + b'\xcd' : 'I', + b'\xce' : 'I', + b'\xcf' : 'I', + b'\xd0' : 'D', + b'\xd1' : 'N', + b'\xd2' : 'O', + b'\xd3' : 'O', + b'\xd4' : 'O', + b'\xd5' : 'O', + b'\xd6' : 'O', + b'\xd7' : '*', + b'\xd8' : 'O', + b'\xd9' : 'U', + b'\xda' : 'U', + b'\xdb' : 'U', + b'\xdc' : 'U', + b'\xdd' : 'Y', + b'\xde' : 'b', + b'\xdf' : 'B', + b'\xe0' : 'a', + b'\xe1' : 'a', + b'\xe2' : 'a', + b'\xe3' : 'a', + b'\xe4' : 'a', + b'\xe5' : 'a', + b'\xe6' : 'ae', + b'\xe7' : 'c', + b'\xe8' : 'e', + b'\xe9' : 'e', + b'\xea' : 'e', + b'\xeb' : 'e', + b'\xec' : 'i', + b'\xed' : 'i', + b'\xee' : 'i', + b'\xef' : 'i', + b'\xf0' : 'o', + b'\xf1' : 'n', + b'\xf2' : 'o', + b'\xf3' : 'o', + b'\xf4' : 'o', + b'\xf5' : 'o', + b'\xf6' : 'o', + b'\xf7' : '/', + b'\xf8' : 'o', + b'\xf9' : 'u', + b'\xfa' : 'u', + b'\xfb' : 'u', + b'\xfc' : 'u', + b'\xfd' : 'y', + b'\xfe' : 'b', + b'\xff' : 'y', + } + + # A map used when removing rogue Windows-1252/ISO-8859-1 + # characters in otherwise UTF-8 documents. + # + # Note that \x81, \x8d, \x8f, \x90, and \x9d are undefined in + # Windows-1252. + WINDOWS_1252_TO_UTF8 = { + 0x80 : b'\xe2\x82\xac', # € + 0x82 : b'\xe2\x80\x9a', # ‚ + 0x83 : b'\xc6\x92', # Æ’ + 0x84 : b'\xe2\x80\x9e', # „ + 0x85 : b'\xe2\x80\xa6', # … + 0x86 : b'\xe2\x80\xa0', # † + 0x87 : b'\xe2\x80\xa1', # ‡ + 0x88 : b'\xcb\x86', # ˆ + 0x89 : b'\xe2\x80\xb0', # ‰ + 0x8a : b'\xc5\xa0', # Å  + 0x8b : b'\xe2\x80\xb9', # ‹ + 0x8c : b'\xc5\x92', # Å’ + 0x8e : b'\xc5\xbd', # Ž + 0x91 : b'\xe2\x80\x98', # ‘ + 0x92 : b'\xe2\x80\x99', # ’ + 0x93 : b'\xe2\x80\x9c', # “ + 0x94 : b'\xe2\x80\x9d', # †+ 0x95 : b'\xe2\x80\xa2', # • + 0x96 : b'\xe2\x80\x93', # – + 0x97 : b'\xe2\x80\x94', # — + 0x98 : b'\xcb\x9c', # Ëœ + 0x99 : b'\xe2\x84\xa2', # â„¢ + 0x9a : b'\xc5\xa1', # Å¡ + 0x9b : b'\xe2\x80\xba', # › + 0x9c : b'\xc5\x93', # Å“ + 0x9e : b'\xc5\xbe', # ž + 0x9f : b'\xc5\xb8', # Ÿ + 0xa0 : b'\xc2\xa0', #   + 0xa1 : b'\xc2\xa1', # ¡ + 0xa2 : b'\xc2\xa2', # ¢ + 0xa3 : b'\xc2\xa3', # £ + 0xa4 : b'\xc2\xa4', # ¤ + 0xa5 : b'\xc2\xa5', # Â¥ + 0xa6 : b'\xc2\xa6', # ¦ + 0xa7 : b'\xc2\xa7', # § + 0xa8 : b'\xc2\xa8', # ¨ + 0xa9 : b'\xc2\xa9', # © + 0xaa : b'\xc2\xaa', # ª + 0xab : b'\xc2\xab', # « + 0xac : b'\xc2\xac', # ¬ + 0xad : b'\xc2\xad', # ­ + 0xae : b'\xc2\xae', # ® + 0xaf : b'\xc2\xaf', # ¯ + 0xb0 : b'\xc2\xb0', # ° + 0xb1 : b'\xc2\xb1', # ± + 0xb2 : b'\xc2\xb2', # ² + 0xb3 : b'\xc2\xb3', # ³ + 0xb4 : b'\xc2\xb4', # ´ + 0xb5 : b'\xc2\xb5', # µ + 0xb6 : b'\xc2\xb6', # ¶ + 0xb7 : b'\xc2\xb7', # · + 0xb8 : b'\xc2\xb8', # ¸ + 0xb9 : b'\xc2\xb9', # ¹ + 0xba : b'\xc2\xba', # º + 0xbb : b'\xc2\xbb', # » + 0xbc : b'\xc2\xbc', # ¼ + 0xbd : b'\xc2\xbd', # ½ + 0xbe : b'\xc2\xbe', # ¾ + 0xbf : b'\xc2\xbf', # ¿ + 0xc0 : b'\xc3\x80', # À + 0xc1 : b'\xc3\x81', # à + 0xc2 : b'\xc3\x82', #  + 0xc3 : b'\xc3\x83', # à + 0xc4 : b'\xc3\x84', # Ä + 0xc5 : b'\xc3\x85', # Ã… + 0xc6 : b'\xc3\x86', # Æ + 0xc7 : b'\xc3\x87', # Ç + 0xc8 : b'\xc3\x88', # È + 0xc9 : b'\xc3\x89', # É + 0xca : b'\xc3\x8a', # Ê + 0xcb : b'\xc3\x8b', # Ë + 0xcc : b'\xc3\x8c', # ÃŒ + 0xcd : b'\xc3\x8d', # à + 0xce : b'\xc3\x8e', # ÃŽ + 0xcf : b'\xc3\x8f', # à + 0xd0 : b'\xc3\x90', # à + 0xd1 : b'\xc3\x91', # Ñ + 0xd2 : b'\xc3\x92', # Ã’ + 0xd3 : b'\xc3\x93', # Ó + 0xd4 : b'\xc3\x94', # Ô + 0xd5 : b'\xc3\x95', # Õ + 0xd6 : b'\xc3\x96', # Ö + 0xd7 : b'\xc3\x97', # × + 0xd8 : b'\xc3\x98', # Ø + 0xd9 : b'\xc3\x99', # Ù + 0xda : b'\xc3\x9a', # Ú + 0xdb : b'\xc3\x9b', # Û + 0xdc : b'\xc3\x9c', # Ãœ + 0xdd : b'\xc3\x9d', # à + 0xde : b'\xc3\x9e', # Þ + 0xdf : b'\xc3\x9f', # ß + 0xe0 : b'\xc3\xa0', # à + 0xe1 : b'\xa1', # á + 0xe2 : b'\xc3\xa2', # â + 0xe3 : b'\xc3\xa3', # ã + 0xe4 : b'\xc3\xa4', # ä + 0xe5 : b'\xc3\xa5', # Ã¥ + 0xe6 : b'\xc3\xa6', # æ + 0xe7 : b'\xc3\xa7', # ç + 0xe8 : b'\xc3\xa8', # è + 0xe9 : b'\xc3\xa9', # é + 0xea : b'\xc3\xaa', # ê + 0xeb : b'\xc3\xab', # ë + 0xec : b'\xc3\xac', # ì + 0xed : b'\xc3\xad', # í + 0xee : b'\xc3\xae', # î + 0xef : b'\xc3\xaf', # ï + 0xf0 : b'\xc3\xb0', # ð + 0xf1 : b'\xc3\xb1', # ñ + 0xf2 : b'\xc3\xb2', # ò + 0xf3 : b'\xc3\xb3', # ó + 0xf4 : b'\xc3\xb4', # ô + 0xf5 : b'\xc3\xb5', # õ + 0xf6 : b'\xc3\xb6', # ö + 0xf7 : b'\xc3\xb7', # ÷ + 0xf8 : b'\xc3\xb8', # ø + 0xf9 : b'\xc3\xb9', # ù + 0xfa : b'\xc3\xba', # ú + 0xfb : b'\xc3\xbb', # û + 0xfc : b'\xc3\xbc', # ü + 0xfd : b'\xc3\xbd', # ý + 0xfe : b'\xc3\xbe', # þ + } + + MULTIBYTE_MARKERS_AND_SIZES = [ + (0xc2, 0xdf, 2), # 2-byte characters start with a byte C2-DF + (0xe0, 0xef, 3), # 3-byte characters start with E0-EF + (0xf0, 0xf4, 4), # 4-byte characters start with F0-F4 + ] + + FIRST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[0][0] + LAST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[-1][1] + + @classmethod + def detwingle(cls, in_bytes, main_encoding="utf8", + embedded_encoding="windows-1252"): + """Fix characters from one encoding embedded in some other encoding. + + Currently the only situation supported is Windows-1252 (or its + subset ISO-8859-1), embedded in UTF-8. + + The input must be a bytestring. If you've already converted + the document to Unicode, you're too late. + + The output is a bytestring in which `embedded_encoding` + characters have been converted to their `main_encoding` + equivalents. + """ + if embedded_encoding.replace('_', '-').lower() not in ( + 'windows-1252', 'windows_1252'): + raise NotImplementedError( + "Windows-1252 and ISO-8859-1 are the only currently supported " + "embedded encodings.") + + if main_encoding.lower() not in ('utf8', 'utf-8'): + raise NotImplementedError( + "UTF-8 is the only currently supported main encoding.") + + byte_chunks = [] + + chunk_start = 0 + pos = 0 + while pos < len(in_bytes): + byte = in_bytes[pos] + if not isinstance(byte, int): + # Python 2.x + byte = ord(byte) + if (byte >= cls.FIRST_MULTIBYTE_MARKER + and byte <= cls.LAST_MULTIBYTE_MARKER): + # This is the start of a UTF-8 multibyte character. Skip + # to the end. + for start, end, size in cls.MULTIBYTE_MARKERS_AND_SIZES: + if byte >= start and byte <= end: + pos += size + break + elif byte >= 0x80 and byte in cls.WINDOWS_1252_TO_UTF8: + # We found a Windows-1252 character! + # Save the string up to this point as a chunk. + byte_chunks.append(in_bytes[chunk_start:pos]) + + # Now translate the Windows-1252 character into UTF-8 + # and add it as another, one-byte chunk. + byte_chunks.append(cls.WINDOWS_1252_TO_UTF8[byte]) + pos += 1 + chunk_start = pos + else: + # Go on to the next character. + pos += 1 + if chunk_start == 0: + # The string is unchanged. + return in_bytes + else: + # Store the final chunk. + byte_chunks.append(in_bytes[chunk_start:]) + return b''.join(byte_chunks) + diff --git a/bs4/element.py b/bs4/element.py new file mode 100644 index 00000000..26422fda --- /dev/null +++ b/bs4/element.py @@ -0,0 +1,1355 @@ +import collections +import re +import sys +import warnings +from bs4.dammit import EntitySubstitution + +DEFAULT_OUTPUT_ENCODING = "utf-8" +PY3K = (sys.version_info[0] > 2) + +whitespace_re = re.compile("\s+") + +def _alias(attr): + """Alias one attribute name to another for backward compatibility""" + @property + def alias(self): + return getattr(self, attr) + + @alias.setter + def alias(self): + return setattr(self, attr) + return alias + + +class NamespacedAttribute(unicode): + + def __new__(cls, prefix, name, namespace=None): + if name is None: + obj = unicode.__new__(cls, prefix) + else: + obj = unicode.__new__(cls, prefix + ":" + name) + obj.prefix = prefix + obj.name = name + obj.namespace = namespace + return obj + +class AttributeValueWithCharsetSubstitution(unicode): + """A stand-in object for a character encoding specified in HTML.""" + +class CharsetMetaAttributeValue(AttributeValueWithCharsetSubstitution): + """A generic stand-in for the value of a meta tag's 'charset' attribute. + + When Beautiful Soup parses the markup '', the + value of the 'charset' attribute will be one of these objects. + """ + + def __new__(cls, original_value): + obj = unicode.__new__(cls, original_value) + obj.original_value = original_value + return obj + + def encode(self, encoding): + return encoding + + +class ContentMetaAttributeValue(AttributeValueWithCharsetSubstitution): + """A generic stand-in for the value of a meta tag's 'content' attribute. + + When Beautiful Soup parses the markup: + + + The value of the 'content' attribute will be one of these objects. + """ + + CHARSET_RE = re.compile("((^|;)\s*charset=)([^;]*)", re.M) + + def __new__(cls, original_value): + match = cls.CHARSET_RE.search(original_value) + if match is None: + # No substitution necessary. + return unicode.__new__(unicode, original_value) + + obj = unicode.__new__(cls, original_value) + obj.original_value = original_value + return obj + + def encode(self, encoding): + def rewrite(match): + return match.group(1) + encoding + return self.CHARSET_RE.sub(rewrite, self.original_value) + + +class PageElement(object): + """Contains the navigational information for some part of the page + (either a tag or a piece of text)""" + + # There are five possible values for the "formatter" argument passed in + # to methods like encode() and prettify(): + # + # "html" - All Unicode characters with corresponding HTML entities + # are converted to those entities on output. + # "minimal" - Bare ampersands and angle brackets are converted to + # XML entities: & < > + # None - The null formatter. Unicode characters are never + # converted to entities. This is not recommended, but it's + # faster than "minimal". + # A function - This function will be called on every string that + # needs to undergo entity substition + FORMATTERS = { + "html" : EntitySubstitution.substitute_html, + "minimal" : EntitySubstitution.substitute_xml, + None : None + } + + @classmethod + def format_string(self, s, formatter='minimal'): + """Format the given string using the given formatter.""" + if not callable(formatter): + formatter = self.FORMATTERS.get( + formatter, EntitySubstitution.substitute_xml) + if formatter is None: + output = s + else: + output = formatter(s) + return output + + def setup(self, parent=None, previous_element=None): + """Sets up the initial relations between this element and + other elements.""" + self.parent = parent + self.previous_element = previous_element + if previous_element is not None: + self.previous_element.next_element = self + self.next_element = None + self.previous_sibling = None + self.next_sibling = None + if self.parent is not None and self.parent.contents: + self.previous_sibling = self.parent.contents[-1] + self.previous_sibling.next_sibling = self + + nextSibling = _alias("next_sibling") # BS3 + previousSibling = _alias("previous_sibling") # BS3 + + def replace_with(self, replace_with): + if replace_with is self: + return + if replace_with is self.parent: + raise ValueError("Cannot replace a Tag with its parent.") + old_parent = self.parent + my_index = self.parent.index(self) + self.extract() + old_parent.insert(my_index, replace_with) + return self + replaceWith = replace_with # BS3 + + def unwrap(self): + my_parent = self.parent + my_index = self.parent.index(self) + self.extract() + for child in reversed(self.contents[:]): + my_parent.insert(my_index, child) + return self + replace_with_children = unwrap + replaceWithChildren = unwrap # BS3 + + def wrap(self, wrap_inside): + me = self.replace_with(wrap_inside) + wrap_inside.append(me) + return wrap_inside + + def extract(self): + """Destructively rips this element out of the tree.""" + if self.parent is not None: + del self.parent.contents[self.parent.index(self)] + + #Find the two elements that would be next to each other if + #this element (and any children) hadn't been parsed. Connect + #the two. + last_child = self._last_descendant() + next_element = last_child.next_element + + if self.previous_element is not None: + self.previous_element.next_element = next_element + if next_element is not None: + next_element.previous_element = self.previous_element + self.previous_element = None + last_child.next_element = None + + self.parent = None + if self.previous_sibling is not None: + self.previous_sibling.next_sibling = self.next_sibling + if self.next_sibling is not None: + self.next_sibling.previous_sibling = self.previous_sibling + self.previous_sibling = self.next_sibling = None + return self + + def _last_descendant(self): + "Finds the last element beneath this object to be parsed." + last_child = self + while hasattr(last_child, 'contents') and last_child.contents: + last_child = last_child.contents[-1] + return last_child + # BS3: Not part of the API! + _lastRecursiveChild = _last_descendant + + def insert(self, position, new_child): + if new_child is self: + raise ValueError("Cannot insert a tag into itself.") + if (isinstance(new_child, basestring) + and not isinstance(new_child, NavigableString)): + new_child = NavigableString(new_child) + + position = min(position, len(self.contents)) + if hasattr(new_child, 'parent') and new_child.parent is not None: + # We're 'inserting' an element that's already one + # of this object's children. + if new_child.parent is self: + current_index = self.index(new_child) + if current_index < position: + # We're moving this element further down the list + # of this object's children. That means that when + # we extract this element, our target index will + # jump down one. + position -= 1 + new_child.extract() + + new_child.parent = self + previous_child = None + if position == 0: + new_child.previous_sibling = None + new_child.previous_element = self + else: + previous_child = self.contents[position - 1] + new_child.previous_sibling = previous_child + new_child.previous_sibling.next_sibling = new_child + new_child.previous_element = previous_child._last_descendant() + if new_child.previous_element is not None: + new_child.previous_element.next_element = new_child + + new_childs_last_element = new_child._last_descendant() + + if position >= len(self.contents): + new_child.next_sibling = None + + parent = self + parents_next_sibling = None + while parents_next_sibling is None and parent is not None: + parents_next_sibling = parent.next_sibling + parent = parent.parent + if parents_next_sibling is not None: + # We found the element that comes next in the document. + break + if parents_next_sibling is not None: + new_childs_last_element.next_element = parents_next_sibling + else: + # The last element of this tag is the last element in + # the document. + new_childs_last_element.next_element = None + else: + next_child = self.contents[position] + new_child.next_sibling = next_child + if new_child.next_sibling is not None: + new_child.next_sibling.previous_sibling = new_child + new_childs_last_element.next_element = next_child + + if new_childs_last_element.next_element is not None: + new_childs_last_element.next_element.previous_element = new_childs_last_element + self.contents.insert(position, new_child) + + def append(self, tag): + """Appends the given tag to the contents of this tag.""" + self.insert(len(self.contents), tag) + + def insert_before(self, predecessor): + """Makes the given element the immediate predecessor of this one. + + The two elements will have the same parent, and the given element + will be immediately before this one. + """ + if self is predecessor: + raise ValueError("Can't insert an element before itself.") + parent = self.parent + if parent is None: + raise ValueError( + "Element has no parent, so 'before' has no meaning.") + # Extract first so that the index won't be screwed up if they + # are siblings. + if isinstance(predecessor, PageElement): + predecessor.extract() + index = parent.index(self) + parent.insert(index, predecessor) + + def insert_after(self, successor): + """Makes the given element the immediate successor of this one. + + The two elements will have the same parent, and the given element + will be immediately after this one. + """ + if self is successor: + raise ValueError("Can't insert an element after itself.") + parent = self.parent + if parent is None: + raise ValueError( + "Element has no parent, so 'after' has no meaning.") + # Extract first so that the index won't be screwed up if they + # are siblings. + if isinstance(successor, PageElement): + successor.extract() + index = parent.index(self) + parent.insert(index+1, successor) + + def find_next(self, name=None, attrs={}, text=None, **kwargs): + """Returns the first item that matches the given criteria and + appears after this Tag in the document.""" + return self._find_one(self.find_all_next, name, attrs, text, **kwargs) + findNext = find_next # BS3 + + def find_all_next(self, name=None, attrs={}, text=None, limit=None, + **kwargs): + """Returns all items that match the given criteria and appear + after this Tag in the document.""" + return self._find_all(name, attrs, text, limit, self.next_elements, + **kwargs) + findAllNext = find_all_next # BS3 + + def find_next_sibling(self, name=None, attrs={}, text=None, **kwargs): + """Returns the closest sibling to this Tag that matches the + given criteria and appears after this Tag in the document.""" + return self._find_one(self.find_next_siblings, name, attrs, text, + **kwargs) + findNextSibling = find_next_sibling # BS3 + + def find_next_siblings(self, name=None, attrs={}, text=None, limit=None, + **kwargs): + """Returns the siblings of this Tag that match the given + criteria and appear after this Tag in the document.""" + return self._find_all(name, attrs, text, limit, + self.next_siblings, **kwargs) + findNextSiblings = find_next_siblings # BS3 + fetchNextSiblings = find_next_siblings # BS2 + + def find_previous(self, name=None, attrs={}, text=None, **kwargs): + """Returns the first item that matches the given criteria and + appears before this Tag in the document.""" + return self._find_one( + self.find_all_previous, name, attrs, text, **kwargs) + findPrevious = find_previous # BS3 + + def find_all_previous(self, name=None, attrs={}, text=None, limit=None, + **kwargs): + """Returns all items that match the given criteria and appear + before this Tag in the document.""" + return self._find_all(name, attrs, text, limit, self.previous_elements, + **kwargs) + findAllPrevious = find_all_previous # BS3 + fetchPrevious = find_all_previous # BS2 + + def find_previous_sibling(self, name=None, attrs={}, text=None, **kwargs): + """Returns the closest sibling to this Tag that matches the + given criteria and appears before this Tag in the document.""" + return self._find_one(self.find_previous_siblings, name, attrs, text, + **kwargs) + findPreviousSibling = find_previous_sibling # BS3 + + def find_previous_siblings(self, name=None, attrs={}, text=None, + limit=None, **kwargs): + """Returns the siblings of this Tag that match the given + criteria and appear before this Tag in the document.""" + return self._find_all(name, attrs, text, limit, + self.previous_siblings, **kwargs) + findPreviousSiblings = find_previous_siblings # BS3 + fetchPreviousSiblings = find_previous_siblings # BS2 + + def find_parent(self, name=None, attrs={}, **kwargs): + """Returns the closest parent of this Tag that matches the given + criteria.""" + # NOTE: We can't use _find_one because findParents takes a different + # set of arguments. + r = None + l = self.find_parents(name, attrs, 1) + if l: + r = l[0] + return r + findParent = find_parent # BS3 + + def find_parents(self, name=None, attrs={}, limit=None, **kwargs): + """Returns the parents of this Tag that match the given + criteria.""" + + return self._find_all(name, attrs, None, limit, self.parents, + **kwargs) + findParents = find_parents # BS3 + fetchParents = find_parents # BS2 + + @property + def next(self): + return self.next_element + + @property + def previous(self): + return self.previous_element + + #These methods do the real heavy lifting. + + def _find_one(self, method, name, attrs, text, **kwargs): + r = None + l = method(name, attrs, text, 1, **kwargs) + if l: + r = l[0] + return r + + def _find_all(self, name, attrs, text, limit, generator, **kwargs): + "Iterates over a generator looking for things that match." + + if isinstance(name, SoupStrainer): + strainer = name + elif text is None and not limit and not attrs and not kwargs: + # Optimization to find all tags. + if name is True or name is None: + return [element for element in generator + if isinstance(element, Tag)] + # Optimization to find all tags with a given name. + elif isinstance(name, basestring): + return [element for element in generator + if isinstance(element, Tag) and element.name == name] + else: + strainer = SoupStrainer(name, attrs, text, **kwargs) + else: + # Build a SoupStrainer + strainer = SoupStrainer(name, attrs, text, **kwargs) + results = ResultSet(strainer) + while True: + try: + i = next(generator) + except StopIteration: + break + if i: + found = strainer.search(i) + if found: + results.append(found) + if limit and len(results) >= limit: + break + return results + + #These generators can be used to navigate starting from both + #NavigableStrings and Tags. + @property + def next_elements(self): + i = self.next_element + while i is not None: + yield i + i = i.next_element + + @property + def next_siblings(self): + i = self.next_sibling + while i is not None: + yield i + i = i.next_sibling + + @property + def previous_elements(self): + i = self.previous_element + while i is not None: + yield i + i = i.previous_element + + @property + def previous_siblings(self): + i = self.previous_sibling + while i is not None: + yield i + i = i.previous_sibling + + @property + def parents(self): + i = self.parent + while i is not None: + yield i + i = i.parent + + # Methods for supporting CSS selectors. + + tag_name_re = re.compile('^[a-z0-9]+$') + + # /^(\w+)\[(\w+)([=~\|\^\$\*]?)=?"?([^\]"]*)"?\]$/ + # \---/ \---/\-------------/ \-------/ + # | | | | + # | | | The value + # | | ~,|,^,$,* or = + # | Attribute + # Tag + attribselect_re = re.compile( + r'^(?P\w+)?\[(?P\w+)(?P[=~\|\^\$\*]?)' + + r'=?"?(?P[^\]"]*)"?\]$' + ) + + def _attr_value_as_string(self, value, default=None): + """Force an attribute value into a string representation. + + A multi-valued attribute will be converted into a + space-separated stirng. + """ + value = self.get(value, default) + if isinstance(value, list) or isinstance(value, tuple): + value =" ".join(value) + return value + + def _attribute_checker(self, operator, attribute, value=''): + """Create a function that performs a CSS selector operation. + + Takes an operator, attribute and optional value. Returns a + function that will return True for elements that match that + combination. + """ + if operator == '=': + # string representation of `attribute` is equal to `value` + return lambda el: el._attr_value_as_string(attribute) == value + elif operator == '~': + # space-separated list representation of `attribute` + # contains `value` + def _includes_value(element): + attribute_value = element.get(attribute, []) + if not isinstance(attribute_value, list): + attribute_value = attribute_value.split() + return value in attribute_value + return _includes_value + elif operator == '^': + # string representation of `attribute` starts with `value` + return lambda el: el._attr_value_as_string( + attribute, '').startswith(value) + elif operator == '$': + # string represenation of `attribute` ends with `value` + return lambda el: el._attr_value_as_string( + attribute, '').endswith(value) + elif operator == '*': + # string representation of `attribute` contains `value` + return lambda el: value in el._attr_value_as_string(attribute, '') + elif operator == '|': + # string representation of `attribute` is either exactly + # `value` or starts with `value` and then a dash. + def _is_or_starts_with_dash(element): + attribute_value = element._attr_value_as_string(attribute, '') + return (attribute_value == value or attribute_value.startswith( + value + '-')) + return _is_or_starts_with_dash + else: + return lambda el: el.has_attr(attribute) + + def select(self, selector): + """Perform a CSS selection operation on the current element.""" + tokens = selector.split() + current_context = [self] + for index, token in enumerate(tokens): + if tokens[index - 1] == '>': + # already found direct descendants in last step. skip this + # step. + continue + m = self.attribselect_re.match(token) + if m is not None: + # Attribute selector + tag, attribute, operator, value = m.groups() + if not tag: + tag = True + checker = self._attribute_checker(operator, attribute, value) + found = [] + for context in current_context: + found.extend( + [el for el in context.find_all(tag) if checker(el)]) + current_context = found + continue + + if '#' in token: + # ID selector + tag, id = token.split('#', 1) + if tag == "": + tag = True + el = current_context[0].find(tag, {'id': id}) + if el is None: + return [] # No match + current_context = [el] + continue + + if '.' in token: + # Class selector + tag_name, klass = token.split('.', 1) + if not tag_name: + tag_name = True + classes = set(klass.split('.')) + found = [] + def classes_match(tag): + if tag_name is not True and tag.name != tag_name: + return False + if not tag.has_attr('class'): + return False + return classes.issubset(tag['class']) + for context in current_context: + found.extend(context.find_all(classes_match)) + current_context = found + continue + + if token == '*': + # Star selector + found = [] + for context in current_context: + found.extend(context.findAll(True)) + current_context = found + continue + + if token == '>': + # Child selector + tag = tokens[index + 1] + if not tag: + tag = True + + found = [] + for context in current_context: + found.extend(context.find_all(tag, recursive=False)) + current_context = found + continue + + # Here we should just have a regular tag + if not self.tag_name_re.match(token): + return [] + found = [] + for context in current_context: + found.extend(context.findAll(token)) + current_context = found + return current_context + + # Old non-property versions of the generators, for backwards + # compatibility with BS3. + def nextGenerator(self): + return self.next_elements + + def nextSiblingGenerator(self): + return self.next_siblings + + def previousGenerator(self): + return self.previous_elements + + def previousSiblingGenerator(self): + return self.previous_siblings + + def parentGenerator(self): + return self.parents + + +class NavigableString(unicode, PageElement): + + PREFIX = '' + SUFFIX = '' + + def __new__(cls, value): + """Create a new NavigableString. + + When unpickling a NavigableString, this method is called with + the string in DEFAULT_OUTPUT_ENCODING. That encoding needs to be + passed in to the superclass's __new__ or the superclass won't know + how to handle non-ASCII characters. + """ + if isinstance(value, unicode): + return unicode.__new__(cls, value) + return unicode.__new__(cls, value, DEFAULT_OUTPUT_ENCODING) + + def __getnewargs__(self): + return (unicode(self),) + + def __getattr__(self, attr): + """text.string gives you text. This is for backwards + compatibility for Navigable*String, but for CData* it lets you + get the string without the CData wrapper.""" + if attr == 'string': + return self + else: + raise AttributeError( + "'%s' object has no attribute '%s'" % ( + self.__class__.__name__, attr)) + + def output_ready(self, formatter="minimal"): + output = self.format_string(self, formatter) + return self.PREFIX + output + self.SUFFIX + + +class PreformattedString(NavigableString): + """A NavigableString not subject to the normal formatting rules. + + The string will be passed into the formatter (to trigger side effects), + but the return value will be ignored. + """ + + def output_ready(self, formatter="minimal"): + """CData strings are passed into the formatter. + But the return value is ignored.""" + self.format_string(self, formatter) + return self.PREFIX + self + self.SUFFIX + +class CData(PreformattedString): + + PREFIX = u'' + +class ProcessingInstruction(PreformattedString): + + PREFIX = u'' + +class Comment(PreformattedString): + + PREFIX = u'' + + +class Declaration(PreformattedString): + PREFIX = u'' + + +class Doctype(PreformattedString): + + @classmethod + def for_name_and_ids(cls, name, pub_id, system_id): + value = name + if pub_id is not None: + value += ' PUBLIC "%s"' % pub_id + if system_id is not None: + value += ' "%s"' % system_id + elif system_id is not None: + value += ' SYSTEM "%s"' % system_id + + return Doctype(value) + + PREFIX = u'\n' + + +class Tag(PageElement): + + """Represents a found HTML tag with its attributes and contents.""" + + def __init__(self, parser=None, builder=None, name=None, namespace=None, + prefix=None, attrs=None, parent=None, previous=None): + "Basic constructor." + + if parser is None: + self.parser_class = None + else: + # We don't actually store the parser object: that lets extracted + # chunks be garbage-collected. + self.parser_class = parser.__class__ + if name is None: + raise ValueError("No value provided for new tag's name.") + self.name = name + self.namespace = namespace + self.prefix = prefix + if attrs is None: + attrs = {} + elif builder.cdata_list_attributes: + attrs = builder._replace_cdata_list_attribute_values( + self.name, attrs) + else: + attrs = dict(attrs) + self.attrs = attrs + self.contents = [] + self.setup(parent, previous) + self.hidden = False + + # Set up any substitutions, such as the charset in a META tag. + if builder is not None: + builder.set_up_substitutions(self) + self.can_be_empty_element = builder.can_be_empty_element(name) + else: + self.can_be_empty_element = False + + parserClass = _alias("parser_class") # BS3 + + @property + def is_empty_element(self): + """Is this tag an empty-element tag? (aka a self-closing tag) + + A tag that has contents is never an empty-element tag. + + A tag that has no contents may or may not be an empty-element + tag. It depends on the builder used to create the tag. If the + builder has a designated list of empty-element tags, then only + a tag whose name shows up in that list is considered an + empty-element tag. + + If the builder has no designated list of empty-element tags, + then any tag with no contents is an empty-element tag. + """ + return len(self.contents) == 0 and self.can_be_empty_element + isSelfClosing = is_empty_element # BS3 + + @property + def string(self): + """Convenience property to get the single string within this tag. + + :Return: If this tag has a single string child, return value + is that string. If this tag has no children, or more than one + child, return value is None. If this tag has one child tag, + return value is the 'string' attribute of the child tag, + recursively. + """ + if len(self.contents) != 1: + return None + child = self.contents[0] + if isinstance(child, NavigableString): + return child + return child.string + + @string.setter + def string(self, string): + self.clear() + self.append(string.__class__(string)) + + def _all_strings(self, strip=False): + """Yield all child strings, possibly stripping them.""" + for descendant in self.descendants: + if not isinstance(descendant, NavigableString): + continue + if strip: + descendant = descendant.strip() + if len(descendant) == 0: + continue + yield descendant + strings = property(_all_strings) + + @property + def stripped_strings(self): + for string in self._all_strings(True): + yield string + + def get_text(self, separator=u"", strip=False): + """ + Get all child strings, concatenated using the given separator. + """ + return separator.join([s for s in self._all_strings(strip)]) + getText = get_text + text = property(get_text) + + def decompose(self): + """Recursively destroys the contents of this tree.""" + self.extract() + i = self + while i is not None: + next = i.next_element + i.__dict__.clear() + i = next + + def clear(self, decompose=False): + """ + Extract all children. If decompose is True, decompose instead. + """ + if decompose: + for element in self.contents[:]: + if isinstance(element, Tag): + element.decompose() + else: + element.extract() + else: + for element in self.contents[:]: + element.extract() + + def index(self, element): + """ + Find the index of a child by identity, not value. Avoids issues with + tag.contents.index(element) getting the index of equal elements. + """ + for i, child in enumerate(self.contents): + if child is element: + return i + raise ValueError("Tag.index: element not in tag") + + def get(self, key, default=None): + """Returns the value of the 'key' attribute for the tag, or + the value given for 'default' if it doesn't have that + attribute.""" + return self.attrs.get(key, default) + + def has_attr(self, key): + return key in self.attrs + + def __hash__(self): + return str(self).__hash__() + + def __getitem__(self, key): + """tag[key] returns the value of the 'key' attribute for the tag, + and throws an exception if it's not there.""" + return self.attrs[key] + + def __iter__(self): + "Iterating over a tag iterates over its contents." + return iter(self.contents) + + def __len__(self): + "The length of a tag is the length of its list of contents." + return len(self.contents) + + def __contains__(self, x): + return x in self.contents + + def __nonzero__(self): + "A tag is non-None even if it has no contents." + return True + + def __setitem__(self, key, value): + """Setting tag[key] sets the value of the 'key' attribute for the + tag.""" + self.attrs[key] = value + + def __delitem__(self, key): + "Deleting tag[key] deletes all 'key' attributes for the tag." + self.attrs.pop(key, None) + + def __call__(self, *args, **kwargs): + """Calling a tag like a function is the same as calling its + find_all() method. Eg. tag('a') returns a list of all the A tags + found within this tag.""" + return self.find_all(*args, **kwargs) + + def __getattr__(self, tag): + #print "Getattr %s.%s" % (self.__class__, tag) + if len(tag) > 3 and tag.endswith('Tag'): + # BS3: soup.aTag -> "soup.find("a") + tag_name = tag[:-3] + warnings.warn( + '.%sTag is deprecated, use .find("%s") instead.' % ( + tag_name, tag_name)) + return self.find(tag_name) + # We special case contents to avoid recursion. + elif not tag.startswith("__") and not tag=="contents": + return self.find(tag) + raise AttributeError( + "'%s' object has no attribute '%s'" % (self.__class__, tag)) + + def __eq__(self, other): + """Returns true iff this tag has the same name, the same attributes, + and the same contents (recursively) as the given tag.""" + if self is other: + return True + if (not hasattr(other, 'name') or + not hasattr(other, 'attrs') or + not hasattr(other, 'contents') or + self.name != other.name or + self.attrs != other.attrs or + len(self) != len(other)): + return False + for i, my_child in enumerate(self.contents): + if my_child != other.contents[i]: + return False + return True + + def __ne__(self, other): + """Returns true iff this tag is not identical to the other tag, + as defined in __eq__.""" + return not self == other + + def __repr__(self, encoding=DEFAULT_OUTPUT_ENCODING): + """Renders this tag as a string.""" + return self.encode(encoding) + + def __unicode__(self): + return self.decode() + + def __str__(self): + return self.encode() + + if PY3K: + __str__ = __repr__ = __unicode__ + + def encode(self, encoding=DEFAULT_OUTPUT_ENCODING, + indent_level=None, formatter="minimal", + errors="xmlcharrefreplace"): + # Turn the data structure into Unicode, then encode the + # Unicode. + u = self.decode(indent_level, encoding, formatter) + return u.encode(encoding, errors) + + def decode(self, indent_level=None, + eventual_encoding=DEFAULT_OUTPUT_ENCODING, + formatter="minimal"): + """Returns a Unicode representation of this tag and its contents. + + :param eventual_encoding: The tag is destined to be + encoded into this encoding. This method is _not_ + responsible for performing that encoding. This information + is passed in so that it can be substituted in if the + document contains a tag that mentions the document's + encoding. + """ + attrs = [] + if self.attrs: + for key, val in sorted(self.attrs.items()): + if val is None: + decoded = key + else: + if isinstance(val, list) or isinstance(val, tuple): + val = ' '.join(val) + elif not isinstance(val, basestring): + val = unicode(val) + elif ( + isinstance(val, AttributeValueWithCharsetSubstitution) + and eventual_encoding is not None): + val = val.encode(eventual_encoding) + + text = self.format_string(val, formatter) + decoded = ( + unicode(key) + '=' + + EntitySubstitution.quoted_attribute_value(text)) + attrs.append(decoded) + close = '' + closeTag = '' + + prefix = '' + if self.prefix: + prefix = self.prefix + ":" + + if self.is_empty_element: + close = '/' + else: + closeTag = '' % (prefix, self.name) + + pretty_print = (indent_level is not None) + if pretty_print: + space = (' ' * (indent_level - 1)) + indent_contents = indent_level + 1 + else: + space = '' + indent_contents = None + contents = self.decode_contents( + indent_contents, eventual_encoding, formatter) + + if self.hidden: + # This is the 'document root' object. + s = contents + else: + s = [] + attribute_string = '' + if attrs: + attribute_string = ' ' + ' '.join(attrs) + if pretty_print: + s.append(space) + s.append('<%s%s%s%s>' % ( + prefix, self.name, attribute_string, close)) + if pretty_print: + s.append("\n") + s.append(contents) + if pretty_print and contents and contents[-1] != "\n": + s.append("\n") + if pretty_print and closeTag: + s.append(space) + s.append(closeTag) + if pretty_print and closeTag and self.next_sibling: + s.append("\n") + s = ''.join(s) + return s + + def prettify(self, encoding=None, formatter="minimal"): + if encoding is None: + return self.decode(True, formatter=formatter) + else: + return self.encode(encoding, True, formatter=formatter) + + def decode_contents(self, indent_level=None, + eventual_encoding=DEFAULT_OUTPUT_ENCODING, + formatter="minimal"): + """Renders the contents of this tag as a Unicode string. + + :param eventual_encoding: The tag is destined to be + encoded into this encoding. This method is _not_ + responsible for performing that encoding. This information + is passed in so that it can be substituted in if the + document contains a tag that mentions the document's + encoding. + """ + pretty_print = (indent_level is not None) + s = [] + for c in self: + text = None + if isinstance(c, NavigableString): + text = c.output_ready(formatter) + elif isinstance(c, Tag): + s.append(c.decode(indent_level, eventual_encoding, + formatter)) + if text and indent_level: + text = text.strip() + if text: + if pretty_print: + s.append(" " * (indent_level - 1)) + s.append(text) + if pretty_print: + s.append("\n") + return ''.join(s) + + def encode_contents( + self, indent_level=None, encoding=DEFAULT_OUTPUT_ENCODING, + formatter="minimal"): + """Renders the contents of this tag as a bytestring.""" + contents = self.decode_contents(indent_level, encoding, formatter) + return contents.encode(encoding) + + # Old method for BS3 compatibility + def renderContents(self, encoding=DEFAULT_OUTPUT_ENCODING, + prettyPrint=False, indentLevel=0): + if not prettyPrint: + indentLevel = None + return self.encode_contents( + indent_level=indentLevel, encoding=encoding) + + #Soup methods + + def find(self, name=None, attrs={}, recursive=True, text=None, + **kwargs): + """Return only the first child of this Tag matching the given + criteria.""" + r = None + l = self.find_all(name, attrs, recursive, text, 1, **kwargs) + if l: + r = l[0] + return r + findChild = find + + def find_all(self, name=None, attrs={}, recursive=True, text=None, + limit=None, **kwargs): + """Extracts a list of Tag objects that match the given + criteria. You can specify the name of the Tag and any + attributes you want the Tag to have. + + The value of a key-value pair in the 'attrs' map can be a + string, a list of strings, a regular expression object, or a + callable that takes a string and returns whether or not the + string matches for some custom definition of 'matches'. The + same is true of the tag name.""" + + generator = self.descendants + if not recursive: + generator = self.children + return self._find_all(name, attrs, text, limit, generator, **kwargs) + findAll = find_all # BS3 + findChildren = find_all # BS2 + + #Generator methods + @property + def children(self): + # return iter() to make the purpose of the method clear + return iter(self.contents) # XXX This seems to be untested. + + @property + def descendants(self): + if not len(self.contents): + return + stopNode = self._last_descendant().next_element + current = self.contents[0] + while current is not stopNode: + yield current + current = current.next_element + + # Old names for backwards compatibility + def childGenerator(self): + return self.children + + def recursiveChildGenerator(self): + return self.descendants + + # This was kind of misleading because has_key() (attributes) was + # different from __in__ (contents). has_key() is gone in Python 3, + # anyway. + has_key = has_attr + +# Next, a couple classes to represent queries and their results. +class SoupStrainer(object): + """Encapsulates a number of ways of matching a markup element (tag or + text).""" + + def __init__(self, name=None, attrs={}, text=None, **kwargs): + self.name = self._normalize_search_value(name) + if not isinstance(attrs, dict): + # Treat a non-dict value for attrs as a search for the 'class' + # attribute. + kwargs['class'] = attrs + attrs = None + + if 'class_' in kwargs: + # Treat class_="foo" as a search for the 'class' + # attribute, overriding any non-dict value for attrs. + kwargs['class'] = kwargs['class_'] + del kwargs['class_'] + + if kwargs: + if attrs: + attrs = attrs.copy() + attrs.update(kwargs) + else: + attrs = kwargs + normalized_attrs = {} + for key, value in attrs.items(): + normalized_attrs[key] = self._normalize_search_value(value) + + self.attrs = normalized_attrs + self.text = self._normalize_search_value(text) + + def _normalize_search_value(self, value): + # Leave it alone if it's a Unicode string, a callable, a + # regular expression, a boolean, or None. + if (isinstance(value, unicode) or callable(value) or hasattr(value, 'match') + or isinstance(value, bool) or value is None): + return value + + # If it's a bytestring, convert it to Unicode, treating it as UTF-8. + if isinstance(value, bytes): + return value.decode("utf8") + + # If it's listlike, convert it into a list of strings. + if hasattr(value, '__iter__'): + new_value = [] + for v in value: + if (hasattr(v, '__iter__') and not isinstance(v, bytes) + and not isinstance(v, unicode)): + # This is almost certainly the user's mistake. In the + # interests of avoiding infinite loops, we'll let + # it through as-is rather than doing a recursive call. + new_value.append(v) + else: + new_value.append(self._normalize_search_value(v)) + return new_value + + # Otherwise, convert it into a Unicode string. + # The unicode(str()) thing is so this will do the same thing on Python 2 + # and Python 3. + return unicode(str(value)) + + def __str__(self): + if self.text: + return self.text + else: + return "%s|%s" % (self.name, self.attrs) + + def search_tag(self, markup_name=None, markup_attrs={}): + found = None + markup = None + if isinstance(markup_name, Tag): + markup = markup_name + markup_attrs = markup + call_function_with_tag_data = ( + isinstance(self.name, collections.Callable) + and not isinstance(markup_name, Tag)) + + if ((not self.name) + or call_function_with_tag_data + or (markup and self._matches(markup, self.name)) + or (not markup and self._matches(markup_name, self.name))): + if call_function_with_tag_data: + match = self.name(markup_name, markup_attrs) + else: + match = True + markup_attr_map = None + for attr, match_against in list(self.attrs.items()): + if not markup_attr_map: + if hasattr(markup_attrs, 'get'): + markup_attr_map = markup_attrs + else: + markup_attr_map = {} + for k, v in markup_attrs: + markup_attr_map[k] = v + attr_value = markup_attr_map.get(attr) + if not self._matches(attr_value, match_against): + match = False + break + if match: + if markup: + found = markup + else: + found = markup_name + if found and self.text and not self._matches(found.string, self.text): + found = None + return found + searchTag = search_tag + + def search(self, markup): + # print 'looking for %s in %s' % (self, markup) + found = None + # If given a list of items, scan it for a text element that + # matches. + if hasattr(markup, '__iter__') and not isinstance(markup, (Tag, basestring)): + for element in markup: + if isinstance(element, NavigableString) \ + and self.search(element): + found = element + break + # If it's a Tag, make sure its name or attributes match. + # Don't bother with Tags if we're searching for text. + elif isinstance(markup, Tag): + if not self.text or self.name or self.attrs: + found = self.search_tag(markup) + # If it's text, make sure the text matches. + elif isinstance(markup, NavigableString) or \ + isinstance(markup, basestring): + if not self.name and not self.attrs and self._matches(markup, self.text): + found = markup + else: + raise Exception( + "I don't know how to match against a %s" % markup.__class__) + return found + + def _matches(self, markup, match_against): + # print u"Matching %s against %s" % (markup, match_against) + result = False + if isinstance(markup, list) or isinstance(markup, tuple): + # This should only happen when searching a multi-valued attribute + # like 'class'. + if (isinstance(match_against, unicode) + and ' ' in match_against): + # A bit of a special case. If they try to match "foo + # bar" on a multivalue attribute's value, only accept + # the literal value "foo bar" + # + # XXX This is going to be pretty slow because we keep + # splitting match_against. But it shouldn't come up + # too often. + return (whitespace_re.split(match_against) == markup) + else: + for item in markup: + if self._matches(item, match_against): + return True + return False + + if match_against is True: + # True matches any non-None value. + return markup is not None + + if isinstance(match_against, collections.Callable): + return match_against(markup) + + # Custom callables take the tag as an argument, but all + # other ways of matching match the tag name as a string. + if isinstance(markup, Tag): + markup = markup.name + + # Ensure that `markup` is either a Unicode string, or None. + markup = self._normalize_search_value(markup) + + if markup is None: + # None matches None, False, an empty string, an empty list, and so on. + return not match_against + + if isinstance(match_against, unicode): + # Exact string match + return markup == match_against + + if hasattr(match_against, 'match'): + # Regexp match + return match_against.search(markup) + + if hasattr(match_against, '__iter__'): + # The markup must be an exact match against something + # in the iterable. + return markup in match_against + + +class ResultSet(list): + """A ResultSet is just a list that keeps track of the SoupStrainer + that created it.""" + def __init__(self, source): + list.__init__([]) + self.source = source diff --git a/bs4/testing.py b/bs4/testing.py new file mode 100644 index 00000000..30e74f42 --- /dev/null +++ b/bs4/testing.py @@ -0,0 +1,537 @@ +"""Helper classes for tests.""" + +import copy +import functools +import unittest +from unittest import TestCase +from bs4 import BeautifulSoup +from bs4.element import ( + CharsetMetaAttributeValue, + Comment, + ContentMetaAttributeValue, + Doctype, + SoupStrainer, +) + +from bs4.builder import HTMLParserTreeBuilder +default_builder = HTMLParserTreeBuilder + + +class SoupTest(unittest.TestCase): + + @property + def default_builder(self): + return default_builder() + + def soup(self, markup, **kwargs): + """Build a Beautiful Soup object from markup.""" + builder = kwargs.pop('builder', self.default_builder) + return BeautifulSoup(markup, builder=builder, **kwargs) + + def document_for(self, markup): + """Turn an HTML fragment into a document. + + The details depend on the builder. + """ + return self.default_builder.test_fragment_to_document(markup) + + def assertSoupEquals(self, to_parse, compare_parsed_to=None): + builder = self.default_builder + obj = BeautifulSoup(to_parse, builder=builder) + if compare_parsed_to is None: + compare_parsed_to = to_parse + + self.assertEqual(obj.decode(), self.document_for(compare_parsed_to)) + + +class HTMLTreeBuilderSmokeTest(object): + + """A basic test of a treebuilder's competence. + + Any HTML treebuilder, present or future, should be able to pass + these tests. With invalid markup, there's room for interpretation, + and different parsers can handle it differently. But with the + markup in these tests, there's not much room for interpretation. + """ + + def assertDoctypeHandled(self, doctype_fragment): + """Assert that a given doctype string is handled correctly.""" + doctype_str, soup = self._document_with_doctype(doctype_fragment) + + # Make sure a Doctype object was created. + doctype = soup.contents[0] + self.assertEqual(doctype.__class__, Doctype) + self.assertEqual(doctype, doctype_fragment) + self.assertEqual(str(soup)[:len(doctype_str)], doctype_str) + + # Make sure that the doctype was correctly associated with the + # parse tree and that the rest of the document parsed. + self.assertEqual(soup.p.contents[0], 'foo') + + def _document_with_doctype(self, doctype_fragment): + """Generate and parse a document with the given doctype.""" + doctype = '' % doctype_fragment + markup = doctype + '\n

foo

' + soup = self.soup(markup) + return doctype, soup + + def test_normal_doctypes(self): + """Make sure normal, everyday HTML doctypes are handled correctly.""" + self.assertDoctypeHandled("html") + self.assertDoctypeHandled( + 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"') + + def test_public_doctype_with_url(self): + doctype = 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"' + self.assertDoctypeHandled(doctype) + + def test_system_doctype(self): + self.assertDoctypeHandled('foo SYSTEM "http://www.example.com/"') + + def test_namespaced_system_doctype(self): + # We can handle a namespaced doctype with a system ID. + self.assertDoctypeHandled('xsl:stylesheet SYSTEM "htmlent.dtd"') + + def test_namespaced_public_doctype(self): + # Test a namespaced doctype with a public id. + self.assertDoctypeHandled('xsl:stylesheet PUBLIC "htmlent.dtd"') + + def test_real_xhtml_document(self): + """A real XHTML document should come out more or less the same as it went in.""" + markup = b""" + + +Hello. +Goodbye. +""" + soup = self.soup(markup) + self.assertEqual( + soup.encode("utf-8").replace(b"\n", b""), + markup.replace(b"\n", b"")) + + def test_deepcopy(self): + """Make sure you can copy the tree builder. + + This is important because the builder is part of a + BeautifulSoup object, and we want to be able to copy that. + """ + copy.deepcopy(self.default_builder) + + def test_p_tag_is_never_empty_element(self): + """A

tag is never designated as an empty-element tag. + + Even if the markup shows it as an empty-element tag, it + shouldn't be presented that way. + """ + soup = self.soup("

") + self.assertFalse(soup.p.is_empty_element) + self.assertEqual(str(soup.p), "

") + + def test_unclosed_tags_get_closed(self): + """A tag that's not closed by the end of the document should be closed. + + This applies to all tags except empty-element tags. + """ + self.assertSoupEquals("

", "

") + self.assertSoupEquals("", "") + + self.assertSoupEquals("
", "
") + + def test_br_is_always_empty_element_tag(self): + """A
tag is designated as an empty-element tag. + + Some parsers treat

as one
tag, some parsers as + two tags, but it should always be an empty-element tag. + """ + soup = self.soup("

") + self.assertTrue(soup.br.is_empty_element) + self.assertEqual(str(soup.br), "
") + + def test_nested_formatting_elements(self): + self.assertSoupEquals("") + + def test_comment(self): + # Comments are represented as Comment objects. + markup = "

foobaz

" + self.assertSoupEquals(markup) + + soup = self.soup(markup) + comment = soup.find(text="foobar") + self.assertEqual(comment.__class__, Comment) + + def test_preserved_whitespace_in_pre_and_textarea(self): + """Whitespace must be preserved in 
 and ")
+
+    def test_nested_inline_elements(self):
+        """Inline elements can be nested indefinitely."""
+        b_tag = "Inside a B tag"
+        self.assertSoupEquals(b_tag)
+
+        nested_b_tag = "
A nested tag
"
+        self.assertSoupEquals(nested_b_tag)
+
+        double_nested_b_tag = "
A doubly nested tag
"
+        self.assertSoupEquals(nested_b_tag)
+
+    def test_nested_block_level_elements(self):
+        """Block elements can be nested."""
+        soup = self.soup('
Foo
')
+        blockquote = soup.blockquote
+        self.assertEqual(blockquote.p.b.string, 'Foo')
+        self.assertEqual(blockquote.b.string, 'Foo')
+
+    def test_correctly_nested_tables(self):
+        """One table can go inside another one."""
+        markup = (''
+                  ''
+                  "')
+
+        self.assertSoupEquals(
+            markup,
+            '
Here's another table:"
+                  ''
+                  ''
+                  '
foo
Here\'s another table:'
+            '
foo
'
+            '
')
+
+        self.assertSoupEquals(
+            ""
+            ""
+            "
Foo
Bar
Baz
")
+
+    def test_deeply_nested_multivalued_attribute(self):
+        # html5lib can set the attributes of the same tag many times
+        # as it rearranges the tree. This has caused problems with
+        # multivalued attributes.
+        markup = '
'
+        soup = self.soup(markup)
+        self.assertEqual(["css"], soup.div.div['class'])
+
+    def test_angle_brackets_in_attribute_values_are_escaped(self):
+        self.assertSoupEquals('', '')
+
+    def test_entities_in_attributes_converted_to_unicode(self):
+        expect = u'
'
+        self.assertSoupEquals('
', expect)
+        self.assertSoupEquals('
', expect)
+        self.assertSoupEquals('
', expect)
+
+    def test_entities_in_text_converted_to_unicode(self):
+        expect = u'
pi\N{LATIN SMALL LETTER N WITH TILDE}ata
'
+        self.assertSoupEquals("
piñata
", expect)
+        self.assertSoupEquals("
piñata
", expect)
+        self.assertSoupEquals("
piñata
", expect)
+
+    def test_quot_entity_converted_to_quotation_mark(self):
+        self.assertSoupEquals("
I said "good day!"
",
+                              '
I said "good day!"
')
+
+    def test_out_of_range_entity(self):
+        expect = u"\N{REPLACEMENT CHARACTER}"
+        self.assertSoupEquals("�", expect)
+        self.assertSoupEquals("�", expect)
+        self.assertSoupEquals("�", expect)
+
+    def test_basic_namespaces(self):
+        """Parsers don't need to *understand* namespaces, but at the
+        very least they should not choke on namespaces or lose
+        data."""
+
+        markup = b'4'
+        soup = self.soup(markup)
+        self.assertEqual(markup, soup.encode())
+        html = soup.html
+        self.assertEqual('http://www.w3.org/1999/xhtml', soup.html['xmlns'])
+        self.assertEqual(
+            'http://www.w3.org/1998/Math/MathML', soup.html['xmlns:mathml'])
+        self.assertEqual(
+            'http://www.w3.org/2000/svg', soup.html['xmlns:svg'])
+
+    def test_multivalued_attribute_value_becomes_list(self):
+        markup = b''
+        soup = self.soup(markup)
+        self.assertEqual(['foo', 'bar'], soup.a['class'])
+
+    #
+    # Generally speaking, tests below this point are more tests of
+    # Beautiful Soup than tests of the tree builders. But parsers are
+    # weird, so we run these tests separately for every tree builder
+    # to detect any differences between them.
+    #
+
+    def test_soupstrainer(self):
+        """Parsers should be able to work with SoupStrainers."""
+        strainer = SoupStrainer("b")
+        soup = self.soup("A bold  statement",
+                         parse_only=strainer)
+        self.assertEqual(soup.decode(), "bold")
+
+    def test_single_quote_attribute_values_become_double_quotes(self):
+        self.assertSoupEquals("",
+                              '')
+
+    def test_attribute_values_with_nested_quotes_are_left_alone(self):
+        text = """a"""
+        self.assertSoupEquals(text)
+
+    def test_attribute_values_with_double_nested_quotes_get_quoted(self):
+        text = """a"""
+        soup = self.soup(text)
+        soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
+        self.assertSoupEquals(
+            soup.foo.decode(),
+            """a""")
+
+    def test_ampersand_in_attribute_value_gets_escaped(self):
+        self.assertSoupEquals('',
+                              '')
+
+        self.assertSoupEquals(
+            'foo',
+            'foo')
+
+    def test_escaped_ampersand_in_attribute_value_is_left_alone(self):
+        self.assertSoupEquals('')
+
+    def test_entities_in_strings_converted_during_parsing(self):
+        # Both XML and HTML entities are converted to Unicode characters
+        # during parsing.
+        text = "
<<sacré bleu!>>
"
+        expected = u"
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
"
+        self.assertSoupEquals(text, expected)
+
+    def test_smart_quotes_converted_on_the_way_in(self):
+        # Microsoft smart quotes are converted to Unicode characters during
+        # parsing.
+        quote = b"
\x91Foo\x92
"
+        soup = self.soup(quote)
+        self.assertEqual(
+            soup.p.string,
+            u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
+
+    def test_non_breaking_spaces_converted_on_the_way_in(self):
+        soup = self.soup("  ")
+        self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2)
+
+    def test_entities_converted_on_the_way_out(self):
+        text = "
<<sacré bleu!>>
"
+        expected = u"
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
".encode("utf-8")
+        soup = self.soup(text)
+        self.assertEqual(soup.p.encode("utf-8"), expected)
+
+    def test_real_iso_latin_document(self):
+        # Smoke test of interrelated functionality, using an
+        # easy-to-understand document.
+
+        # Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
+        unicode_html = u'
Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!
'
+
+        # That's because we're going to encode it into ISO-Latin-1, and use
+        # that to test.
+        iso_latin_html = unicode_html.encode("iso-8859-1")
+
+        # Parse the ISO-Latin-1 HTML.
+        soup = self.soup(iso_latin_html)
+        # Encode it to UTF-8.
+        result = soup.encode("utf-8")
+
+        # What do we expect the result to look like? Well, it would
+        # look like unicode_html, except that the META tag would say
+        # UTF-8 instead of ISO-Latin-1.
+        expected = unicode_html.replace("ISO-Latin-1", "utf-8")
+
+        # And, of course, it would be in UTF-8, not Unicode.
+        expected = expected.encode("utf-8")
+
+        # Ta-da!
+        self.assertEqual(result, expected)
+
+    def test_real_shift_jis_document(self):
+        # Smoke test to make sure the parser can handle a document in
+        # Shift-JIS encoding, without choking.
+        shift_jis_html = (
+            b'
'
+            b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
+            b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
+            b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B'
+            b'
')
+        unicode_html = shift_jis_html.decode("shift-jis")
+        soup = self.soup(unicode_html)
+
+        # Make sure the parse tree is correctly encoded to various
+        # encodings.
+        self.assertEqual(soup.encode("utf-8"), unicode_html.encode("utf-8"))
+        self.assertEqual(soup.encode("euc_jp"), unicode_html.encode("euc_jp"))
+
+    def test_real_hebrew_document(self):
+        # A real-world test to make sure we can convert ISO-8859-9 (a
+        # Hebrew encoding) to UTF-8.
+        hebrew_document = b'Hebrew (ISO 8859-8) in Visual Directionality
Hebrew (ISO 8859-8) in Visual Directionality
\xed\xe5\xec\xf9'
+        soup = self.soup(
+            hebrew_document, from_encoding="iso8859-8")
+        self.assertEqual(soup.original_encoding, 'iso8859-8')
+        self.assertEqual(
+            soup.encode('utf-8'),
+            hebrew_document.decode("iso8859-8").encode("utf-8"))
+
+    def test_meta_tag_reflects_current_encoding(self):
+        # Here's the  tag saying that a document is
+        # encoded in Shift-JIS.
+        meta_tag = ('')
+
+        # Here's a document incorporating that meta tag.
+        shift_jis_html = (
+            '\n%s\n'
+            ''
+            'Shift-JIS markup goes here.') % meta_tag
+        soup = self.soup(shift_jis_html)
+
+        # Parse the document, and the charset is seemingly unaffected.
+        parsed_meta = soup.find('meta', {'http-equiv': 'Content-type'})
+        content = parsed_meta['content']
+        self.assertEqual('text/html; charset=x-sjis', content)
+
+        # But that value is actually a ContentMetaAttributeValue object.
+        self.assertTrue(isinstance(content, ContentMetaAttributeValue))
+
+        # And it will take on a value that reflects its current
+        # encoding.
+        self.assertEqual('text/html; charset=utf8', content.encode("utf8"))
+
+        # For the rest of the story, see TestSubstitutions in
+        # test_tree.py.
+
+    def test_html5_style_meta_tag_reflects_current_encoding(self):
+        # Here's the  tag saying that a document is
+        # encoded in Shift-JIS.
+        meta_tag = ('')
+
+        # Here's a document incorporating that meta tag.
+        shift_jis_html = (
+            '\n%s\n'
+            ''
+            'Shift-JIS markup goes here.') % meta_tag
+        soup = self.soup(shift_jis_html)
+
+        # Parse the document, and the charset is seemingly unaffected.
+        parsed_meta = soup.find('meta', id="encoding")
+        charset = parsed_meta['charset']
+        self.assertEqual('x-sjis', charset)
+
+        # But that value is actually a CharsetMetaAttributeValue object.
+        self.assertTrue(isinstance(charset, CharsetMetaAttributeValue))
+
+        # And it will take on a value that reflects its current
+        # encoding.
+        self.assertEqual('utf8', charset.encode("utf8"))
+
+    def test_tag_with_no_attributes_can_have_attributes_added(self):
+        data = self.soup("text")
+        data.a['foo'] = 'bar'
+        self.assertEqual('text', data.a.decode())
+
+class XMLTreeBuilderSmokeTest(object):
+
+    def test_docstring_generated(self):
+        soup = self.soup("")
+        self.assertEqual(
+            soup.encode(), b'\n')
+
+    def test_real_xhtml_document(self):
+        """A real XHTML document should come out *exactly* the same as it went in."""
+        markup = b"""
+
+
+Hello.
+Goodbye.
+"""
+        soup = self.soup(markup)
+        self.assertEqual(
+            soup.encode("utf-8"), markup)
+
+    def test_popping_namespaced_tag(self):
+        markup = 'b2012-07-02T20:33:42Zcd'
+        soup = self.soup(markup)
+        self.assertEqual(
+            unicode(soup.rss), markup)
+
+    def test_docstring_includes_correct_encoding(self):
+        soup = self.soup("")
+        self.assertEqual(
+            soup.encode("latin1"),
+            b'\n')
+
+    def test_large_xml_document(self):
+        """A large XML document should come out the same as it went in."""
+        markup = (b'\n'
+                  + b'0' * (2**12)
+                  + b'')
+        soup = self.soup(markup)
+        self.assertEqual(soup.encode("utf-8"), markup)
+
+
+    def test_tags_are_empty_element_if_and_only_if_they_are_empty(self):
+        self.assertSoupEquals("
", "
")
+        self.assertSoupEquals("
foo
")
+
+    def test_namespaces_are_preserved(self):
+        markup = 'This tag is in the a namespaceThis tag is in the b namespace'
+        soup = self.soup(markup)
+        root = soup.root
+        self.assertEqual("http://example.com/", root['xmlns:a'])
+        self.assertEqual("http://example.net/", root['xmlns:b'])
+
+    def test_closing_namespaced_tag(self):
+        markup = '
20010504
'
+        soup = self.soup(markup)
+        self.assertEqual(unicode(soup.p), markup)
+
+    def test_namespaced_attributes(self):
+        markup = ''
+        soup = self.soup(markup)
+        self.assertEqual(unicode(soup.foo), markup)
+
+class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
+    """Smoke test for a tree builder that supports HTML5."""
+
+    def test_real_xhtml_document(self):
+        # Since XHTML is not HTML5, HTML5 parsers are not tested to handle
+        # XHTML documents in any particular way.
+        pass
+
+    def test_html_tags_have_namespace(self):
+        markup = ""
+        soup = self.soup(markup)
+        self.assertEqual("http://www.w3.org/1999/xhtml", soup.a.namespace)
+
+    def test_svg_tags_have_namespace(self):
+        markup = ''
+        soup = self.soup(markup)
+        namespace = "http://www.w3.org/2000/svg"
+        self.assertEqual(namespace, soup.svg.namespace)
+        self.assertEqual(namespace, soup.circle.namespace)
+
+
+    def test_mathml_tags_have_namespace(self):
+        markup = '5'
+        soup = self.soup(markup)
+        namespace = 'http://www.w3.org/1998/Math/MathML'
+        self.assertEqual(namespace, soup.math.namespace)
+        self.assertEqual(namespace, soup.msqrt.namespace)
+
+
+def skipIf(condition, reason):
+   def nothing(test, *args, **kwargs):
+       return None
+
+   def decorator(test_item):
+       if condition:
+           return nothing
+       else:
+           return test_item
+
+   return decorator
diff --git a/data/interfaces/brink/Images/no-artist-art.png b/data/interfaces/brink/Images/no-artist-art.png
new file mode 100644
index 00000000..3c373f8e
Binary files /dev/null and b/data/interfaces/brink/Images/no-artist-art.png differ
diff --git a/data/interfaces/brink/artist.html b/data/interfaces/brink/artist.html
index 7201357b..d2ddac43 100644
--- a/data/interfaces/brink/artist.html
+++ b/data/interfaces/brink/artist.html
@@ -8,22 +8,23 @@
 <%def name="body()">
 	
 
-