lispider.py 文件源码

def ParseHtmlContent(self, html_content):

        def _searching_helper_func(tag):
            templateVarsCache = {}
            ret = self._censorTagCandidateWithTemplate(tag, templateRootTag, templateVarsCache)

            if ret is True:
                self._mergeTemplateVariablesWithCache(templateVarsCache)

            return ret

        hitTemplateElems = self.Config.HitTemplate['Elements']

        for elem in hitTemplateElems:
            elem = self._stripWhitespaceAndReturnBeforeParsing(elem)
            templateSoup = BeautifulSoup(elem, self.bs4Parser)

            if self.bs4Parser == 'html5lib':
                templateRootTag = templateSoup.body.contents[0]
            else:
                templateRootTag = templateSoup.contents[0]

            if not type(templateRootTag) == element.Tag:
                # TODO: what do we do for this ?
                pass

            htmlContent = self._stripWhitespaceAndReturnBeforeParsing(html_content)
            htmlSoup = BeautifulSoup(htmlContent, self.bs4Parser)

            tagCandidates = htmlSoup.find_all(_searching_helper_func)
            for candiTag in tagCandidates:
                templateVarsCache = {}
                self._parseTagRecursive(candiTag, templateRootTag, templateVarsCache)

                if not len(templateVarsCache) == 0:
                    self._mergeTemplateVariablesWithCache(templateVarsCache)