當前位置: 首頁>>代碼示例>>Python>>正文


Python bs4.builder方法代碼示例

本文整理匯總了Python中bs4.builder方法的典型用法代碼示例。如果您正苦於以下問題:Python bs4.builder方法的具體用法?Python bs4.builder怎麽用?Python bs4.builder使用的例子?那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在bs4的用法示例。


在下文中一共展示了bs4.builder方法的3個代碼示例,這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚,您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: diagnose

# 需要導入模塊: import bs4 [as 別名]
# 或者: from bs4 import builder [as 別名]
def diagnose(data):
    """Diagnostic suite for isolating common problems."""
    print "Diagnostic running on Beautiful Soup %s" % __version__
    print "Python version %s" % sys.version

    basic_parsers = ["html.parser", "html5lib", "lxml"]
    for name in basic_parsers:
        for builder in builder_registry.builders:
            if name in builder.features:
                break
        else:
            basic_parsers.remove(name)
            print (
                "I noticed that %s is not installed. Installing it may help." %
                name)

    if 'lxml' in basic_parsers:
        basic_parsers.append(["lxml", "xml"])
        try:
            from lxml import etree
            print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))
        except ImportError, e:
            print (
                "lxml is not installed or couldn't be imported.") 
開發者ID:MarcelloLins,項目名稱:ServerlessCrawler-VancouverRealState,代碼行數:26,代碼來源:diagnose.py

示例2: diagnose

# 需要導入模塊: import bs4 [as 別名]
# 或者: from bs4 import builder [as 別名]
def diagnose(data):
    """Diagnostic suite for isolating common problems."""
    print "Diagnostic running on Beautiful Soup %s" % __version__
    print "Python version %s" % sys.version

    basic_parsers = ["html.parser", "html5lib", "lxml"]
    for name in basic_parsers:
        for builder in builder_registry.builders:
            if name in builder.features:
                break
        else:
            basic_parsers.remove(name)
            print (
                "I noticed that %s is not installed. Installing it may help." %
                name)

    if 'lxml' in basic_parsers:
        basic_parsers.append(["lxml", "xml"])
        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 
開發者ID:MayOneUS,項目名稱:pledgeservice,代碼行數:52,代碼來源:diagnose.py

示例3: diagnose

# 需要導入模塊: import bs4 [as 別名]
# 或者: from bs4 import builder [as 別名]
def diagnose(data):
    """Diagnostic suite for isolating common problems."""
    print("Diagnostic running on Beautiful Soup %s" % __version__)
    print("Python version %s" % sys.version)

    basic_parsers = ["html.parser", "html5lib", "lxml"]
    for name in basic_parsers:
        for builder in builder_registry.builders:
            if name in builder.features:
                break
        else:
            basic_parsers.remove(name)
            print((
                "I noticed that %s is not installed. Installing it may help." %
                name))

    if 'lxml' in basic_parsers:
        basic_parsers.append(["lxml", "xml"])
        try:
            from lxml import etree
            print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
        except ImportError 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) 
開發者ID:the-ethan-hunt,項目名稱:B.E.N.J.I.,代碼行數:62,代碼來源:diagnose.py


注:本文中的bs4.builder方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台,相關代碼片段篩選自各路編程大神貢獻的開源項目,源碼版權歸原作者所有,傳播和使用請參考對應項目的License;未經允許,請勿轉載。