sgmllib.py

在 linux平台上的网页编程的模板

        while len(self.stack) > found:
            tag = self.stack[-1]
            try:
                method = getattr(self, 'end_' + tag)
            except AttributeError:
                method = None
            if method:
                self.handle_endtag(tag, method)
            else:
                self.unknown_endtag(tag)
            del self.stack[-1]

    # Overridable -- handle start tag
    def handle_starttag(self, tag, method, attrs):
        method(attrs)

    # Overridable -- handle end tag
    def handle_endtag(self, tag, method):
        method()

    # Example -- report an unbalanced </...> tag.
    def report_unbalanced(self, tag):
        if self.verbose:
            print '*** Unbalanced </' + tag + '>'
            print '*** Stack:', self.stack

    # Example -- handle character reference, no need to override
    def handle_charref(self, name):
        try:
            n = string.atoi(name)
        except string.atoi_error:
            self.unknown_charref(name)
            return
        if not 0 <= n <= 255:
            self.unknown_charref(name)
            return
        self.handle_data(chr(n))

    # Definition of entities -- derived classes may override
    entitydefs = ENTITYDEFS

    # Example -- handle entity reference, no need to override
    def handle_entityref(self, name):
        table = self.entitydefs
        if table.has_key(name):
            self.handle_data(table[name])
        else:
            self.unknown_entityref(name)
            return

    # Example -- handle data, should be overridden
    def handle_data(self, data):
        pass

    # Example -- handle comment, could be overridden
    def handle_comment(self, data):
        pass

    # To be overridden -- handlers for unknown objects
    def unknown_starttag(self, tag, attrs): pass
    def unknown_endtag(self, tag): pass
    def unknown_charref(self, ref): pass
    def unknown_entityref(self, ref): pass


# --------------------------------------------------------------------
# accelerated SGML parser

class FastSGMLParser:

    # Interface -- initialize and reset this instance
    def __init__(self, verbose=0):
        self.verbose = verbose
        self.reset()

    # Interface -- reset this instance.  Loses all unprocessed data
    def reset(self):
        self.rawdata = ''
        self.stack = []
        self.lasttag = '???'
        self.nomoretags = 0
        self.literal = 0
        self.parser = sgmlop.SGMLParser()
        self.feed = self.parser.feed
        self.parser.register(self)

    # For derived classes only -- enter literal mode (CDATA) till EOF
    def setnomoretags(self):
        self.nomoretags = self.literal = 1 # FIXME!

    # For derived classes only -- enter literal mode (CDATA)
    def setliteral(self, *args):
        self.literal = 1 # FIXME!

    # Interface -- feed some data to the parser.  Call this as
    # often as you want, with as little or as much text as you
    # want (may include '\n').
    def feed(self, data): # overridden by reset
        self.parser.feed(data)

    # Interface -- handle the remaining data
    def close(self):
        try:
            self.parser.close()
        finally:
            self.parser = None

    # Internal -- finish parsing of <tag/data/ (same as <tag>data</tag>)
    def finish_shorttag(self, tag, data):
        self.finish_starttag(tag, [])
        self.handle_data(data)
        self.finish_endtag(tag)

    # Internal -- finish processing of start tag
    # Return -1 for unknown tag, 0 for open-only tag, 1 for balanced tag
    def finish_starttag(self, tag, attrs):
        # FIXME: should move this logic into sgmlop!
        try:
            method = getattr(self, 'start_' + tag)
        except AttributeError:
            try:
                method = getattr(self, 'do_' + tag)
            except AttributeError:
                self.unknown_starttag(tag, attrs)
                return -1
            else:
                self.handle_starttag(tag, method, attrs)
                return 0
        else:
            self.stack.append(tag)
            self.handle_starttag(tag, method, attrs)
            return 1

    # Internal -- finish processing of end tag
    def finish_endtag(self, tag):
        if not tag:
            found = len(self.stack) - 1
            if found < 0:
                self.unknown_endtag(tag)
                return
        else:
            if tag not in self.stack:
                try:
                    method = getattr(self, 'end_' + tag)
                except AttributeError:
                    self.unknown_endtag(tag)
                return
            found = len(self.stack)
            for i in range(found):
                if self.stack[i] == tag: found = i
        while len(self.stack) > found:
            tag = self.stack[-1]
            try:
                method = getattr(self, 'end_' + tag)
            except AttributeError:
                method = None
            if method:
                self.handle_endtag(tag, method)
            else:
                self.unknown_endtag(tag)
            del self.stack[-1]

    # Overridable -- handle start tag
    def handle_starttag(self, tag, method, attrs):
        method(attrs)

    # Overridable -- handle end tag
    def handle_endtag(self, tag, method):
        method()

    # Example -- report an unbalanced </...> tag.
    def report_unbalanced(self, tag):
        if self.verbose:
            print '*** Unbalanced </' + tag + '>'
            print '*** Stack:', self.stack

    # Example -- handle character reference, no need to override
    # def handle_charref(self, name):
    #     pass

    # Definition of entities -- derived classes may override
    entitydefs = ENTITYDEFS

    # Example -- handle entity reference, no need to override
    def handle_entityref(self, name):
        try:
            data = self.entitydefs[name]
        except KeyError:
            self.unknown_entityref(name)
        else:
            self.handle_data(data)

    # Example -- handle data, should be overridden
    def handle_data(self, data):
        pass

    # Example -- handle comment, could be overridden
    # def handle_comment(self, data):
    #   pass

    # To be overridden -- handlers for unknown objects
    def unknown_starttag(self, tag, attrs): pass
    def unknown_endtag(self, tag): pass
    def unknown_charref(self, ref): pass
    def unknown_entityref(self, ref): pass


#sgmlop = None

# pick a suitable parser
if sgmlop:
    SGMLParser = FastSGMLParser
else:
    SGMLParser = SlowSGMLParser

# --------------------------------------------------------------------
# test stuff

class TestSGMLParser(SGMLParser):

    def __init__(self, verbose=0):
        self.testdata = ""
        SGMLParser.__init__(self, verbose)

    def handle_data(self, data):
        self.testdata = self.testdata + data
        if len(`self.testdata`) >= 70:
            self.flush()

    def flush(self):
        data = self.testdata
        if data:
            self.testdata = ""
            print 'data:', `data`

    def handle_comment(self, data):
        self.flush()
        r = `data`
        if len(r) > 68:
            r = r[:32] + '...' + r[-32:]
        print 'comment:', r

    def unknown_starttag(self, tag, attrs):
        self.flush()
        if not attrs:
            print 'start tag: <' + tag + '>'
        else:
            print 'start tag: <' + tag,
            for name, value in attrs:
                print name + '=' + '"' + value + '"',
            print '>'

    def unknown_endtag(self, tag):
        self.flush()
        print 'end tag: </' + tag + '>'

    def unknown_entityref(self, ref):
        self.flush()
        print '*** unknown entity ref: &' + ref + ';'

    def unknown_charref(self, ref):
        self.flush()
        print '*** unknown char ref: &#' + ref + ';'

    def close(self):
        SGMLParser.close(self)
        self.flush()


def test(args = None):
    import sys

    if not args:
        args = sys.argv[1:]

    if args and args[0] == '-s':
        args = args[1:]
        klass = SGMLParser
    else:
        klass = TestSGMLParser

    if args:
        file = args[0]
    else:
        file = 'test.html'

    if file == '-':
        f = sys.stdin
    else:
        try:
            f = open(file, 'r')
        except IOError, msg:
            print file, ":", msg
            sys.exit(1)

    data = f.read()
    if f is not sys.stdin:
        f.close()

    x = klass()
    for c in data:
        x.feed(c)
    x.close()


if __name__ == '__main__':
    test()