本文整理匯總了Python中html5lib.__version__方法的典型用法代碼示例。如果您正苦於以下問題：Python html5lib.__version__方法的具體用法？Python html5lib.__version__怎麽用？Python html5lib.__version__使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類html5lib的用法示例。
在下文中一共展示了html5lib.__version__方法的3個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: diagnose
# 需要導入模塊: import html5lib [as 別名]
# 或者: from html5lib import __version__ [as 別名]
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print "Diagnostic running on Beautiful Soup %s" % __version__
print "Python version %s" % sys.version
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print (
"I noticed that %s is not installed. Installing it may help." %
name)
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))
except ImportError, e:
print (
"lxml is not installed or couldn't be imported.") 示例2: benchmark_parsers
# 需要導入模塊: import html5lib [as 別名]
# 或者: from html5lib import __version__ [as 別名]
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 = BeautifulSoup(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) 示例3: benchmark_parsers
# 需要導入模塊: import html5lib [as 別名]
# 或者: from html5lib import __version__ [as 別名]
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 = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as 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))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print("Raw lxml parsed the markup in %.2fs." % (b-a))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print("Raw html5lib parsed the markup in %.2fs." % (b-a))