python re去除Email和url
# 去除Email
x = re.sub(r'^([\w]+\.*)([\w]+)\@[\w]+\.\w{3}(\.\w{2}|)', ' ', x)
# 去除url
x = re.sub(r'^(https:\S+)', ' ', x)
x = re.sub(r'[a-zA-Z]+://[^\s]*', '', x)
# 去除特殊符号
p_text = re.compile(u'[\u4E00-\u9FA5|\s\w]').findall(x)
x = "".join(p_text)
x = re.sub(r'[\d+___|_]', '', x)