def _clean(text):
text = text.lower()
text = re.sub(r'RT|rt', '', text)
text = re.sub(r'&', '&', text)
text = re.sub(r'[?!.;:,#@-]', '', text)
text = re.sub(r"[$&+,:;=?#]|[0-9]|<ed>|<U\+[A-Z0-9]+>", "", text)
text = re.sub("<+[A-Z0-9]+>", "", text)
text = re.sub(r'https?|:\//\w.*', '', text)
text = re.sub(r'\//?w*', '',text)
text = re.sub(r'\ ã°â*', '' ,text)
words = text.split()
words = [w for w in words if w not in stopwords]
text = " ".join(words)
text = emoji_pattern.sub(r'', text)
return text
到目前为止,我已经使用了上面的代码。我不知道如何清理此代码
[生日快乐,上周五晚上(tgif)ððððð上周五,晚上tgif ff…
text = re.sub(r'[^\x00-\x7F]+', '', text)
另请参阅此问题:Replace non-ASCII characters with a single space
text = re.split(r'[^\w\(\)]', '', text)
吗?