Python html5lib 模块，version() 实例源码

我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用html5lib.__version__()。

项目：gerador-horarios 作者：colobas | 项目源码 | 文件源码

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)

    from lxml import etree
    a = time.time()
    etree.HTML(data)
    b = time.time()
    print "Raw lxml parsed the markup in %.2fs." % (b-a)

项目：Projects 作者：it2school | 项目源码 | 文件源码

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))

项目：TACTIC-Handler 作者：listyque | 项目源码 | 文件源码

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)

    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)

项目：UPBGE-CommunityAddon 作者：elmeunick9 | 项目源码 | 文件源码

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))

项目：llk 作者：Tycx2ry | 项目源码 | 文件源码

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)

    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)

项目：harbour-sailfinder 作者：DylanVanAssche | 项目源码 | 文件源码

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))

项目：harbour-sailfinder 作者：DylanVanAssche | 项目源码 | 文件源码

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))

项目：B.E.N.J.I. 作者：the-ethan-hunt | 项目源码 | 文件源码

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))

项目：weeman 作者：evait-security | 项目源码 | 文件源码

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)

    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)

项目：flickr_downloader 作者：Denisolt | 项目源码 | 文件源码

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)

    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)

项目：isar 作者：ilbers | 项目源码 | 文件源码

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))

项目：catchup4kodi 作者：catchup4kodi | 项目源码 | 文件源码

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)

    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)

项目：ShelbySearch 作者：Agentscreech | 项目源码 | 文件源码

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))

项目：respeaker_virtualenv 作者：respeaker | 项目源码 | 文件源码

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)

    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)

项目：tellmeabout.coffee 作者：billyfung | 项目源码 | 文件源码

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)

    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)

项目：Price-Comparator 作者：Thejas-1 | 项目源码 | 文件源码

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)

    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)

项目：script.quasar.t411-rik91 作者：rik91 | 项目源码 | 文件源码

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)

    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)

项目：GUIYoutube 作者：coltking | 项目源码 | 文件源码

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))

项目：svg-animation-tools 作者：parallax | 项目源码 | 文件源码

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)

    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)

项目：svg-animation-tools 作者：parallax | 项目源码 | 文件源码

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)

    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)

项目：start 作者：argeweb | 项目源码 | 文件源码

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)

    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)

项目：django-icekit 作者：ic-labs | 项目源码 | 文件源码

def test_broken_html5lib(self):
        """
        Test againt https://github.com/html5lib/html5lib-python/issues/189
        """
        msg = "This version of html5lib is known to break relative URLs!\nUse version 0.999 instead."
        self.assertTrue(html5lib.__version__ not in ['1.0b5', '1.0b6', '0.9999', '0.99999'], msg)

项目：Alexa-Chatter 作者：ekt1701 | 项目源码 | 文件源码

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)

    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)

项目：ServerlessCrawler-VancouverRealState 作者：MarcelloLins | 项目源码 | 文件源码

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)

    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)

项目：ServerlessCrawler-VancouverRealState 作者：MarcelloLins | 项目源码 | 文件源码

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)

    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)

项目：amazon_order_history_scraper 作者：drewctate | 项目源码 | 文件源码

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)

    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)

项目：kekescan 作者：xiaoxiaoleo | 项目源码 | 文件源码

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)

    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)

项目：mibici-tools 作者：regenhans | 项目源码 | 文件源码

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)

    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)

项目：ip138-alfred 作者：nemoTyrant | 项目源码 | 文件源码

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)

    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)

项目：mit-inspire-2018 作者：pjrule | 项目源码 | 文件源码

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))

项目：slack_scholar 作者：xLeitix | 项目源码 | 文件源码

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)

    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)

项目：UAGS 作者：HoraceAndTheSpider | 项目源码 | 文件源码

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))

项目：youtube-trending-music 作者：ishan-nitj | 项目源码 | 文件源码

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)

    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)

项目：sublime-beautifulsoup4 作者：jlegewie | 项目源码 | 文件源码

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))

项目：sublime-beautifulsoup4 作者：jlegewie | 项目源码 | 文件源码

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)

    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)

项目：PortalAuth 作者：sud0nick | 项目源码 | 文件源码

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)

    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)

项目：yetanotherhoneypot 作者：juansacco | 项目源码 | 文件源码

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)

    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)

项目：EmojiTaco 作者：jeeftor | 项目源码 | 文件源码

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)

    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)

项目：alfred-smzdm 作者：MikeAfc | 项目源码 | 文件源码

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)

    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)

项目：UAEConfigMaker 作者：HoraceAndTheSpider | 项目源码 | 文件源码

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))

项目：4channer 作者：fellchase | 项目源码 | 文件源码

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))

项目：ngDownloaderAPI 作者：manishbisht | 项目源码 | 文件源码

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)

    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)

项目：youdao-alfred 作者：nemoTyrant | 项目源码 | 文件源码

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)

    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)

项目：alfred3-mweb-workflow 作者：DarryO | 项目源码 | 文件源码

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)

    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)

项目：spiderfoot 作者：ParrotSec | 项目源码 | 文件源码

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)

    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)

项目：ftcommunity-apps 作者：ftCommunity | 项目源码 | 文件源码

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))

项目：Stephanie-AI 作者：Elvargy | 项目源码 | 文件源码

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))

项目：AstroCoffee 作者：abhimat | 项目源码 | 文件源码

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)

    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)

项目：alfred-powerthesaurus 作者：clarencecastillo | 项目源码 | 文件源码

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)

    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)

项目：Codeforces-Sublime-Plugin 作者：karunk | 项目源码 | 文件源码

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))

Python html5lib 模块，__version__() 实例源码

Python html5lib 模块，version() 实例源码