lispider.py 文件源码

def _parseTagRecursive(self, candi_tag, template_tag, template_var_cache):
        for idx, tmpChild in enumerate(template_tag.contents):
            if tmpChild.name == 'lisp_pass':
                # this means <...>,
                # indicating that anything in this tag is expected to be ignored.
                continue

            if len(candi_tag.contents) <= idx:
                return False

            candiChild = candi_tag.contents[idx]

            typeCandi = type(candiChild)
            typeTmp = type(tmpChild)

            valid = False
            if typeCandi == typeTmp == element.Tag:
                if self._censorTagCandidateWithTemplate(candiChild, tmpChild, template_var_cache):
                    valid = self._parseTagRecursive(candiChild, tmpChild, template_var_cache)
            elif typeCandi == typeTmp == element.NavigableString:
                valid = self._censorNaviStrCandidateWithTemplate(
                    candiChild, tmpChild, template_var_cache)

            if valid is False and len(template_var_cache) > 0:
                self.logger.warning(template_tag)
                self.logger.warning(candi_tag)
                self.logger.warning('censor not passed. cache will be cleared')
                template_var_cache.clear()

                return False

        return True