def __init__(self): """Creates a new Web Corpus Builder. """ self.urlfilter = lambda p: True self.tagfilter = filtertools.tagfilter self.probefilter = lambda t: True self.datafilter = lambda d: True self.visitor = lambda p: None self.splitter = lambda p: [p] self.writer = lambda d: print(d) self.parser = HTMLParser(self) self.crawler = CrawlerState()