Python bs4.builder.builder_registry 模块,builders() 实例源码

我们从Python开源项目中,提取了以下48个代码示例,用于说明如何使用bs4.builder.builder_registry.builders()

项目:Projects    作者:it2school    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:TACTIC-Handler    作者:listyque    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:UPBGE-CommunityAddon    作者:elmeunick9    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:llk    作者:Tycx2ry    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:harbour-sailfinder    作者:DylanVanAssche    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:harbour-sailfinder    作者:DylanVanAssche    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:B.E.N.J.I.    作者:the-ethan-hunt    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:flickr_downloader    作者:Denisolt    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:isar    作者:ilbers    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print('"%s" looks like a filename. Reading data from the file.' % data)
        data = open(data).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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:catchup4kodi    作者:catchup4kodi    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:ShelbySearch    作者:Agentscreech    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:respeaker_virtualenv    作者:respeaker    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:tellmeabout.coffee    作者:billyfung    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:Price-Comparator    作者:Thejas-1    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:script.quasar.t411-rik91    作者:rik91    | 项目源码 | 文件源码
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"])
        from lxml import etree
        print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))

    if 'html5lib' in basic_parsers:
        import html5lib
        print "Found html5lib version %s" % html5lib.__version__

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:GUIYoutube    作者:coltking    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:svg-animation-tools    作者:parallax    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:svg-animation-tools    作者:parallax    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:gerador-horarios    作者:colobas    | 项目源码 | 文件源码
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"])
        from lxml import etree
        print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))

    if 'html5lib' in basic_parsers:
        import html5lib
        print "Found html5lib version %s" % html5lib.__version__

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:Alexa-Chatter    作者:ekt1701    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:ServerlessCrawler-VancouverRealState    作者:MarcelloLins    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:ServerlessCrawler-VancouverRealState    作者:MarcelloLins    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:ServerlessCrawler-VancouverRealState    作者:MarcelloLins    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:amazon_order_history_scraper    作者:drewctate    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:kekescan    作者:xiaoxiaoleo    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:mibici-tools    作者:regenhans    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:ip138-alfred    作者:nemoTyrant    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:mit-inspire-2018    作者:pjrule    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:slack_scholar    作者:xLeitix    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:UAGS    作者:HoraceAndTheSpider    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:youtube-trending-music    作者:ishan-nitj    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:sublime-beautifulsoup4    作者:jlegewie    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:sublime-beautifulsoup4    作者:jlegewie    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:PortalAuth    作者:sud0nick    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:yetanotherhoneypot    作者:juansacco    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:EmojiTaco    作者:jeeftor    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:alfred-smzdm    作者:MikeAfc    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:UAEConfigMaker    作者:HoraceAndTheSpider    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:4channer    作者:fellchase    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:ngDownloaderAPI    作者:manishbisht    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:youdao-alfred    作者:nemoTyrant    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:alfred3-mweb-workflow    作者:DarryO    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:spiderfoot    作者:ParrotSec    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:ftcommunity-apps    作者:ftCommunity    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:Stephanie-AI    作者:Elvargy    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print('"%s" looks like a filename. Reading data from the file.' % data)
        data = open(data).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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)
项目:AstroCoffee    作者:abhimat    | 项目源码 | 文件源码
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"])
        from lxml import etree
        print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))

    if 'html5lib' in basic_parsers:
        import html5lib
        print "Found html5lib version %s" % html5lib.__version__

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print '"%s" looks like a filename. Reading data from the file.' % data
        data = open(data).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 = BeautifulSoup(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
项目:alfred-powerthesaurus    作者:clarencecastillo    | 项目源码 | 文件源码
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.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print "Found html5lib version %s" % html5lib.__version__
        except ImportError, e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        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 = BeautifulSoup(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
项目:Codeforces-Sublime-Plugin    作者:karunk    | 项目源码 | 文件源码
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 as e:
            print (
                "lxml is not installed or couldn't be imported.")


    if 'html5lib' in basic_parsers:
        try:
            import html5lib
            print("Found html5lib version %s" % html5lib.__version__)
        except ImportError as e:
            print (
                "html5lib is not installed or couldn't be imported.")

    if hasattr(data, 'read'):
        data = data.read()
    elif os.path.exists(data):
        print('"%s" looks like a filename. Reading data from the file.' % data)
        data = open(data).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 = BeautifulSoup(data, parser)
            success = True
        except Exception as 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)