Python html5lib.__version__() Examples

The following are 30 code examples of html5lib.__version__(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module html5lib , or try the search function .
Example #1
Source File: diagnose.py    From ServerlessCrawler-VancouverRealState with MIT License 6 votes vote down vote up 
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)
Example #2
Source File: diagnose.py    From moviegrabber with GNU General Public License v3.0 6 votes vote down vote up 
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)
Example #3
Source File: diagnose.py    From bazarr with GNU General Public License v3.0 6 votes vote down vote up 
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)
Example #4
Source File: diagnose.py    From bazarr with GNU General Public License v3.0 6 votes vote down vote up 
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.")
Example #5
Source File: diagnose.py    From FastWordQuery with GNU General Public License v3.0 6 votes vote down vote up 
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)
Example #6
Source File: diagnose.py    From FastWordQuery with GNU General Public License v3.0 6 votes vote down vote up 
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.")
Example #7
Source File: diagnose.py    From POC-EXP with GNU General Public License v3.0 6 votes vote down vote up 
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)
Example #8
Source File: diagnose.py    From ru with GNU General Public License v2.0 6 votes vote down vote up 
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)
Example #9
Source File: diagnose.py    From MARA_Framework with GNU Lesser General Public License v3.0 6 votes vote down vote up 
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)
Example #10
Source File: diagnose.py    From CrisisMappingToolkit with Apache License 2.0 6 votes vote down vote up 
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)
Example #11
Source File: diagnose.py    From CrisisMappingToolkit with Apache License 2.0 6 votes vote down vote up 
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.")
Example #12
Source File: diagnose.py    From nbaplus-server with Apache License 2.0 6 votes vote down vote up 
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)
Example #13
Source File: diagnose.py    From stopstalk-deployment with MIT License 6 votes vote down vote up 
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)
Example #14
Source File: diagnose.py    From stopstalk-deployment with MIT License 6 votes vote down vote up 
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.")
Example #15
Source File: diagnose.py    From nzb-subliminal with GNU General Public License v3.0 6 votes vote down vote up 
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)
Example #16
Source File: diagnose.py    From svg-animation-tools with MIT License 6 votes vote down vote up 
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)
Example #17
Source File: diagnose.py    From ServerlessCrawler-VancouverRealState with MIT License 6 votes vote down vote up 
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.")
Example #18
Source File: diagnose.py    From ServerlessCrawler-VancouverRealState with MIT License 6 votes vote down vote up 
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.")
Example #19
Source File: diagnose.py    From svg-animation-tools with MIT License 6 votes vote down vote up 
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)
Example #20
Source File: diagnose.py    From svg-animation-tools with MIT License 6 votes vote down vote up 
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.")
Example #21
Source File: diagnose.py    From weeman with GNU General Public License v3.0 6 votes vote down vote up 
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)
Example #22
Source File: diagnose.py    From pledgeservice with Apache License 2.0 6 votes vote down vote up 
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)
Example #23
Source File: diagnose.py    From weeman with GNU General Public License v3.0 6 votes vote down vote up 
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.")
Example #24
Source File: diagnose.py    From fuzzdb-collect with GNU General Public License v3.0 6 votes vote down vote up 
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)
Example #25
Source File: diagnose.py    From ServerlessCrawler-VancouverRealState with MIT License 6 votes vote down vote up 
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)
Example #26
Source File: diagnose.py    From locality-sensitive-hashing with MIT License 6 votes vote down vote up 
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)
Example #27
Source File: diagnose.py    From ServerlessCrawler-VancouverRealState with MIT License 6 votes vote down vote up 
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.")
Example #28
Source File: diagnose.py    From svg-animation-tools with MIT License 6 votes vote down vote up 
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.")
Example #29
Source File: diagnose.py    From Tautulli with GNU General Public License v3.0 5 votes vote down vote up 
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))
Example #30
Source File: diagnose.py    From MIA-Dictionary-Addon with GNU General Public License v3.0 5 votes vote down vote up 
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))