def assertSoupEquals(self, to_parse, compare_parsed_to=None):
builder = self.default_builder
obj = ThoughtfulSoup(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))
def __init__(self, namespaceHTMLElements, soup=None):
if soup:
self.soup = soup
else:
from thoughtfulsoup import ThoughtfulSoup
self.soup = ThoughtfulSoup("", "html.parser")
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
def test_formatter_processes_script_tag_for_xml_documents(self):
doc = """
<script type="text/javascript">
</script>
"""
soup = ThoughtfulSoup(doc, "lxml-xml")
# lxml would have stripped this while parsing, but we can add
# it later.
soup.script.string = 'console.log("< < hey > > ");'
encoded = soup.encode()
self.assertTrue(b"< < hey > >" in encoded)
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = thoughtfulsoup.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
thoughtfulsoup.dammit.chardet_dammit = noop
dammit = UnicodeDammit(doc)
self.assertEqual(True, dammit.contains_replacement_characters)
self.assertTrue(u"\ufffd" in dammit.unicode_markup)
soup = ThoughtfulSoup(doc, "html.parser")
self.assertTrue(soup.contains_replacement_characters)
finally:
logging.disable(logging.NOTSET)
thoughtfulsoup.dammit.chardet_dammit = chardet
def test_thoughtfulsoup_constructor_does_lookup(self):
with warnings.catch_warnings(record=True) as w:
# This will create a warning about not explicitly
# specifying a parser, but we'll ignore it.
# You can pass in a string.
ThoughtfulSoup("", features="html")
# Or a list of strings.
ThoughtfulSoup("", features=["html", "fast"])
# You'll get an exception if BS can't find an appropriate
# builder.
self.assertRaises(ValueError,
ThoughtfulSoup,
"",
features="no-such-feature")
def run_against(self, *parser_names):
uniform_results = True
previous_output = None
for parser in parser_names:
try:
soup = ThoughtfulSoup(self.markup, parser)
if markup.startswith("<div>"):
# Extract the interesting part
output = soup.div
else:
output = soup
except Exception, e:
output = "[EXCEPTION] %s" % str(e)
self.results[parser] = output
if previous_output is None:
previous_output = output
elif previous_output != output:
uniform_results = False
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print "Comparative parser benchmark on Beautiful Soup %s" % __version__
data = rdoc(num_elements)
print "Generated a large invalid HTML document (%d bytes)." % len(data)
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = ThoughtfulSoup(data, parser)
b = time.time()
success = True
except Exception, e:
print "%s could not parse the markup." % parser
traceback.print_exc()
if success:
print "BS4+%s parsed the markup in %.2fs." % (parser, b-a)
def soup(self, markup, **kwargs):
"""Build a Beautiful Soup object from markup."""
builder = kwargs.pop('builder', self.default_builder)
return ThoughtfulSoup(markup, builder=builder, **kwargs)
def fragmentClass(self):
from thoughtfulsoup import ThoughtfulSoup
self.soup = ThoughtfulSoup("", "html.parser")
self.soup.name = "[document_fragment]"
return Element(self.soup, self.soup, None)
class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
def __init__(self, namespaceHTMLElements, soup=None):
if soup:
self.soup = soup
else:
from thoughtfulsoup import ThoughtfulSoup
self.soup = ThoughtfulSoup("", "html.parser")
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):
from thoughtfulsoup import ThoughtfulSoup
self.soup = ThoughtfulSoup("", "html.parser")
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 treebuilder_base.TreeBuilder.getFragment(self).element
def testSerializer(self, element):
from thoughtfulsoup import ThoughtfulSoup
rv = []
doctype_re = re.compile(
r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
def serializeElement(element, indent=0):
if isinstance(element, ThoughtfulSoup):
pass
if isinstance(element, Doctype):
m = doctype_re.match(element)
if m:
name = m.group(1)
if m.lastindex > 1:
publicId = m.group(2) or ""
systemId = m.group(3) or m.group(4) or ""
rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
(' ' * indent, name, publicId, systemId))
else:
rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
else:
rv.append("|%s<!DOCTYPE >" % (' ' * indent, ))
elif isinstance(element, Comment):
rv.append("|%s<!-- %s -->" % (' ' * indent, element))
elif isinstance(element, NavigableString):
rv.append("|%s\"%s\"" % (' ' * indent, element))
else:
if element.namespace:
name = "%s %s" % (prefixes[element.namespace],
element.name)
else:
name = element.name
rv.append("|%s<%s>" % (' ' * indent, name))
if element.attrs:
attributes = []
for name, value in element.attrs.items():
if isinstance(name, NamespacedAttribute):
name = "%s %s" % (prefixes[name.namespace],
name.name)
if isinstance(value, list):
value = " ".join(value)
attributes.append((name, value))
for name, value in sorted(attributes):
rv.append('|%s%s="%s"' % (' ' *
(indent + 2), name, value))
indent += 2
for child in element.children:
serializeElement(child, indent)
serializeElement(element, 0)
return "\n".join(rv)
data = data.read()
elif os.path.exists(data):
print '"%s" looks like a filename. Reading data from the file.' % data
with open(data) as fp:
data = fp.read()
elif data.startswith("http:") or data.startswith("https:"):
print '"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data
print "You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup."
return
print
for parser in basic_parsers:
print "Trying to parse your markup with %s" % parser
success = False
try:
soup = ThoughtfulSoup(data, parser)
success = True
except Exception, e:
print "%s could not parse the markup." % parser
traceback.print_exc()
if success:
print "Here's what %s did with the markup:" % parser
print soup.prettify()
print "-" * 80
def lxml_trace(data, html=True, **kwargs):
"""Print out the lxml events that occur during parsing.
This lets you see how lxml parses a document when no Beautiful
Soup code is running.