Python sgmllib.SGMLParser() Examples

def parse_declaration(self, i):
        """Treat a bogus SGML declaration as raw data. Treat a CDATA
        declaration as a CData object."""
        j = None
        if self.rawdata[i:i+9] == '<![CDATA[':
             k = self.rawdata.find(']]>', i)
             if k == -1:
                 k = len(self.rawdata)
             data = self.rawdata[i+9:k]
             j = k+3
             self._toStringSubclass(data, CData)
        else:
            try:
                j = sgmllib.SGMLParser.parse_declaration(self, i)
            except sgmllib.SGMLParseError:
                toHandle = self.rawdata[i:]
                self.handle_data(toHandle)
                j = i + len(toHandle)
        return j 

def convert_charref(self, name):
        """This method fixes a bug in Python's SGMLParser."""
        try:
            n = int(name)
        except ValueError:
            return
        if not 0 <= n <= 127 : # ASCII ends at 127, not 255
            return
        return self.convert_codepoint(n) 

def __init__(self):
		sgmllib.SGMLParser.__init__(self) 

def feed(self, data):
        data = re.compile(r'<!((?!DOCTYPE|--|\[))', re.IGNORECASE).sub(r'&lt;!\1', data)
        data = re.sub(r'<([^<>\s]+?)\s*/>', self._shorttag_replace, data)
        data = data.replace('&#39;', "'")
        data = data.replace('&#34;', '"')
        try:
            bytes
            if bytes is str:
                raise NameError
            self.encoding = self.encoding + '_INVALID_PYTHON_3'
        except NameError:
            if self.encoding and isinstance(data, str):
                data = data.encode(self.encoding)
        sgmllib.SGMLParser.feed(self, data)
        sgmllib.SGMLParser.close(self) 

def __getattr__(self, methodName):
        """This method routes method call requests to either the SGMLParser
        superclass or the Tag superclass, depending on the method name."""
        #print "__getattr__ called on %s.%s" % (self.__class__, methodName)

        if methodName.startswith('start_') or methodName.startswith('end_') \
               or methodName.startswith('do_'):
            return sgmllib.SGMLParser.__getattr__(self, methodName)
        elif not methodName.startswith('__'):
            return Tag.__getattr__(self, methodName)
        else:
            raise AttributeError 

def reset(self):
        Tag.__init__(self, self, self.ROOT_TAG_NAME)
        self.hidden = 1
        sgmllib.SGMLParser.reset(self)
        self.currentData = []
        self.currentTag = None
        self.tagStack = []
        self.quoteStack = []
        self.pushTag(self) 

def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, text_type):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        sgmllib.SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag() 

def feed(self, data):
        try:
            sgmllib.SGMLParser.feed(self, data)
        except SGMLLIB_PARSEERROR, exc:
            raise ParseError(exc) 

def __init__(self, entitydefs=None, encoding=DEFAULT_ENCODING):
        sgmllib.SGMLParser.__init__(self)
        _AbstractFormParser.__init__(self, entitydefs, encoding) 

def __init__(self, baseuri, baselang, encoding, entities):
        sgmllib.SGMLParser.__init__(self)
        _FeedParserMixin.__init__(self, baseuri, baselang, encoding)
        _BaseHTMLProcessor.__init__(self, encoding, 'application/xhtml+xml')
        self.entities=entities 

def parse_declaration(self, i):
        try:
            return sgmllib.SGMLParser.parse_declaration(self, i)
        except sgmllib.SGMLParseError:
            # escape the doctype declaration and continue parsing
            self.handle_data('<')
            return i+1 

def close(self):
        sgmllib.SGMLParser.close(self)
        self.end_body()


# sigh, must support mechanize by allowing dynamic creation of classes based on
# its bundled copy of BeautifulSoup (which was necessary because of dependency
# problems) 

def reset(self):
        sgmllib.SGMLParser.reset(self)
        self.savedata = None
        self.isindex = 0
        self.title = None
        self.base = None
        self.anchor = None
        self.anchorlist = []
        self.nofill = 0
        self.list_stack = []

    # ------ Methods used internally; some may be overridden

    # --- Formatter interface, taking care of 'savedata' mode;
    # shouldn't need to be overridden 

def __init__(self, formatter, verbose=0):
        """Creates an instance of the HTMLParser class.

        The formatter parameter is the formatter instance associated with
        the parser.

        """
        sgmllib.SGMLParser.__init__(self, verbose)
        self.formatter = formatter 

def reset(self):
        sgmllib.SGMLParser.reset(self)
        self.savedata = None
        self.isindex = 0
        self.title = None
        self.base = None
        self.anchor = None
        self.anchorlist = []
        self.nofill = 0
        self.list_stack = []

    # ------ Methods used internally; some may be overridden

    # --- Formatter interface, taking care of 'savedata' mode;
    # shouldn't need to be overridden 

def __init__(self, formatter, verbose=0):
        """Creates an instance of the HTMLParser class.

        The formatter parameter is the formatter instance associated with
        the parser.

        """
        sgmllib.SGMLParser.__init__(self, verbose)
        self.formatter = formatter 

def __init__(self, writer):
        sgmllib.SGMLParser.__init__(self)
        self.writer = writer
        self.document_id = None
        self.in_body = False
        self.text = '' 

def reset(self):
        sgmllib.SGMLParser.reset(self)
        self.savedata = None
        self.isindex = 0
        self.title = None
        self.base = None
        self.anchor = None
        self.anchorlist = []
        self.nofill = 0
        self.list_stack = []

    # ------ Methods used internally; some may be overridden

    # --- Formatter interface, taking care of 'savedata' mode;
    # shouldn't need to be overridden 

def __init__(self, formatter, verbose=0):
        """Creates an instance of the HTMLParser class.

        The formatter parameter is the formatter instance associated with
        the parser.

        """
        sgmllib.SGMLParser.__init__(self, verbose)
        self.formatter = formatter 

def __init__(self, url, verbose=VERBOSE, checker=None):
        self.myverbose = verbose # now unused
        self.checker = checker
        self.base = None
        self.links = {}
        self.names = []
        self.url = url
        sgmllib.SGMLParser.__init__(self) 

def __init__(self, verbose=0): 
        "Initialise an object, passing 'verbose' to the superclass." 
 
        sgmllib.SGMLParser.__init__(self, verbose) 
        self.hyperlinks = [] 

def __init__(self, verbose=0):
        sgmllib.SGMLParser.__init__(self, verbose)
        self._reset() 

def __init__(self, baseuri, baselang, encoding, entities):
        sgmllib.SGMLParser.__init__(self)
        _FeedParserMixin.__init__(self, baseuri, baselang, encoding)
        _BaseHTMLProcessor.__init__(self, encoding, 'application/xhtml+xml')
        self.entities=entities 

def parse_declaration(self, i):
        try:
            return sgmllib.SGMLParser.parse_declaration(self, i)
        except sgmllib.SGMLParseError:
            # escape the doctype declaration and continue parsing
            self.handle_data('<')
            return i+1 

def feed(self, data):
        data = re.compile(r'<!((?!DOCTYPE|--|\[))', re.IGNORECASE).sub(r'&lt;!\1', data)
        data = re.sub(r'<([^<>\s]+?)\s*/>', self._shorttag_replace, data)
        data = data.replace('&#39;', "'")
        data = data.replace('&#34;', '"')
        try:
            bytes
            if bytes is str:
                raise NameError
            self.encoding = self.encoding + u'_INVALID_PYTHON_3'
        except NameError:
            if self.encoding and isinstance(data, unicode):
                data = data.encode(self.encoding)
        sgmllib.SGMLParser.feed(self, data)
        sgmllib.SGMLParser.close(self) 

def reset(self):
        self.pieces = []
        sgmllib.SGMLParser.reset(self) 

def __init__(self, encoding, _type):
        self.encoding = encoding
        self._type = _type
        sgmllib.SGMLParser.__init__(self) 

def __init__(self, baseuri, baselang, encoding):
        sgmllib.SGMLParser.__init__(self)
        _FeedParserMixin.__init__(self, baseuri, baselang, encoding) 

def feed(self, data):
        data = re.compile(r'<!((?!DOCTYPE|--|\[))', re.IGNORECASE).sub(r'&lt;!\1', data)
        #data = re.sub(r'<(\S+?)\s*?/>', self._shorttag_replace, data) # bug [ 1399464 ] Bad regexp for _shorttag_replace
        data = re.sub(r'<([^<\s]+?)\s*/>', self._shorttag_replace, data) 
        data = data.replace('&#39;', "'")
        data = data.replace('&#34;', '"')
        if self.encoding and type(data) == type(u''):
            data = data.encode(self.encoding)
        sgmllib.SGMLParser.feed(self, data) 

def reset(self):
        self.pieces = []
        sgmllib.SGMLParser.reset(self)