Class EventCollector

Lib/test/test_htmlparser.py:23–84

class EventCollector(html.parser.HTMLParser):

    def __init__(self, *args, autocdata=False, **kw):
        self.autocdata = autocdata
        self.events = []
        self.append = self.events.append
        html.parser.HTMLParser.__init__(self, *args, **kw)
        if autocdata:
            self._set_support_cdata(False)

    def get_events(self):
        # Normalize the list of events so that buffer artefacts don't
        # separate runs of contiguous characters.
        L = []
        prevtype = None
        for event in self.events:
            type = event[0]
            if type == prevtype == "data":
                L[-1] = ("data", L[-1][1] + event[1])
            else:
                L.append(event)
            prevtype = type
        self.events = L
        return L

    # structure markup

    def handle_starttag(self, tag, attrs):
        self.append(("starttag", tag, attrs))
        if self.autocdata and tag == 'svg':
            self._set_support_cdata(True)

    def handle_startendtag(self, tag, attrs):
        self.append(("startendtag", tag, attrs))

    def handle_endtag(self, tag):
        self.append(("endtag", tag))
        if self.autocdata and tag == 'svg':
            self._set_support_cdata(False)

    # all other markup

    def handle_comment(self, data):
        self.append(("comment", data))

    def handle_charref(self, data):
        self.append(("charref", data))

    def handle_data(self, data):
        self.append(("data", data))

    def handle_decl(self, data):
        self.append(("decl", data))

    def handle_entityref(self, data):
        self.append(("entityref", data))

    def handle_pi(self, data):