diff --git a/Doc/library/html.parser.rst b/Doc/library/html.parser.rst index 6d433b5a04f..dd67fc34e85 100644 --- a/Doc/library/html.parser.rst +++ b/Doc/library/html.parser.rst @@ -43,7 +43,9 @@ Example HTML Parser Application As a basic example, below is a simple HTML parser that uses the :class:`HTMLParser` class to print out start tags, end tags, and data -as they are encountered:: +as they are encountered: + +.. testcode:: from html.parser import HTMLParser @@ -63,7 +65,7 @@ as they are encountered:: The output will then be: -.. code-block:: none +.. testoutput:: Encountered a start tag: html Encountered a start tag: head @@ -230,7 +232,9 @@ Examples -------- The following class implements a parser that will be used to illustrate more -examples:: +examples: + +.. testcode:: from html.parser import HTMLParser from html.entities import name2codepoint @@ -266,13 +270,17 @@ examples:: parser = MyHTMLParser() -Parsing a doctype:: +Parsing a doctype: + +.. doctest:: >>> parser.feed('') Decl : DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd" -Parsing an element with a few attributes and a title:: +Parsing an element with a few attributes and a title: + +.. doctest:: >>> parser.feed('The Python logo') Start tag: img @@ -285,7 +293,9 @@ Parsing an element with a few attributes and a title:: End tag : h1 The content of ``script`` and ``style`` elements is returned as is, without -further parsing:: +further parsing: + +.. doctest:: >>> parser.feed('') Start tag: style @@ -300,16 +310,25 @@ further parsing:: Data : alert("hello!"); End tag : script -Parsing comments:: +Parsing comments: - >>> parser.feed('' +.. doctest:: + + >>> parser.feed('' ... '') - Comment : a comment + Comment : a comment Comment : [if IE 9]>IE-specific content'``):: +correct char (note: these 3 references are all equivalent to ``'>'``): +.. doctest:: + + >>> parser = MyHTMLParser() + >>> parser.feed('>>>') + Data : >>> + + >>> parser = MyHTMLParser(convert_charrefs=False) >>> parser.feed('>>>') Named ent: > Num ent : > @@ -317,18 +336,22 @@ correct char (note: these 3 references are all equivalent to ``'>'``):: Feeding incomplete chunks to :meth:`~HTMLParser.feed` works, but :meth:`~HTMLParser.handle_data` might be called more than once -(unless *convert_charrefs* is set to ``True``):: +(unless *convert_charrefs* is set to ``True``): - >>> for chunk in ['buff', 'ered ', 'text']: +.. doctest:: + + >>> for chunk in ['buff', 'ered', ' text']: ... parser.feed(chunk) ... Start tag: span Data : buff Data : ered - Data : text + Data : text End tag : span -Parsing invalid HTML (e.g. unquoted attributes) also works:: +Parsing invalid HTML (e.g. unquoted attributes) also works: + +.. doctest:: >>> parser.feed('

tag soup

') Start tag: p diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 13c95c34e50..0a1dd3b7d3b 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -12,6 +12,7 @@ import re import _markupbase from html import unescape +from html.entities import html5 as html5_entities __all__ = ['HTMLParser'] @@ -23,6 +24,7 @@ incomplete = re.compile('&[a-zA-Z#]') entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]') charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]') +attr_charref = re.compile(r'&(#[0-9]+|#[xX][0-9a-fA-F]+|[a-zA-Z][a-zA-Z0-9]*)[;=]?') starttagopen = re.compile('<[a-zA-Z]') piclose = re.compile('>') @@ -57,6 +59,22 @@ endendtag = re.compile('>') # ') +# Character reference processing logic specific to attribute values +# See: https://html.spec.whatwg.org/multipage/parsing.html#named-character-reference-state +def _replace_attr_charref(match): + ref = match.group(0) + # Numeric / hex char refs must always be unescaped + if ref.startswith('&#'): + return unescape(ref) + # Named character / entity references must only be unescaped + # if they are an exact match, and they are not followed by an equals sign + if not ref.endswith('=') and ref[1:] in html5_entities: + return unescape(ref) + # Otherwise do not unescape + return ref + +def _unescape_attrvalue(s): + return attr_charref.sub(_replace_attr_charref, s) class HTMLParser(_markupbase.ParserBase): @@ -323,7 +341,7 @@ class HTMLParser(_markupbase.ParserBase): attrvalue[:1] == '"' == attrvalue[-1:]: attrvalue = attrvalue[1:-1] if attrvalue: - attrvalue = unescape(attrvalue) + attrvalue = _unescape_attrvalue(attrvalue) attrs.append((attrname.lower(), attrvalue)) k = m.end() diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index b42a611c62c..4fdba06cf4c 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -348,18 +348,16 @@ text collector = lambda: EventCollectorCharrefs() self.assertTrue(collector().convert_charrefs) charrefs = ['"', '"', '"', '"', '"', '"'] - # check charrefs in the middle of the text/attributes - expected = [('starttag', 'a', [('href', 'foo"zar')]), - ('data', 'a"z'), ('endtag', 'a')] + # check charrefs in the middle of the text + expected = [('starttag', 'a', []), ('data', 'a"z'), ('endtag', 'a')] for charref in charrefs: - self._run_check('a{0}z'.format(charref), + self._run_check('a{0}z'.format(charref), expected, collector=collector()) - # check charrefs at the beginning/end of the text/attributes - expected = [('data', '"'), - ('starttag', 'a', [('x', '"'), ('y', '"X'), ('z', 'X"')]), + # check charrefs at the beginning/end of the text + expected = [('data', '"'), ('starttag', 'a', []), ('data', '"'), ('endtag', 'a'), ('data', '"')] for charref in charrefs: - self._run_check('{0}' + self._run_check('{0}' '{0}{0}'.format(charref), expected, collector=collector()) # check charrefs in