def extractAndCleanCorpus(self): files = os.path.join(self.dirCorpus, "*xml") for xmlFile in glob.glob(files): with open(xmlFile, 'r', encoding='utf-8') as content_file: content = content_file.read() striped = FormatEval.strip_tags(content, self.corpusTag) self._saveFile(striped, self.dirLabel, os.path.basename(xmlFile))
