删除csv或者tsv文件中的emoji表情符号,并保存到另外的csv文件中
参考链接码起来:
https://blog.csdn.net/okm6666/article/details/81003397?utm_source=blogxgwz6
https://stackoverflow.com/questions/33404752/removing-emojis-from-a-string-in-python
import re
import pandas as pd
def demoji(text):
emoji_pattern = re.compile("["
u"\U0001F600-\U0001F64F" # emoticons
u"\U0001F300-\U0001F5FF" # symbols & pictographs
u"\U0001F680-\U0001F6FF" # transport & map symbols
u"\U0001F1E0-\U0001F1FF" # flags (iOS)
u"\U00002702-\U000027B0"
u"\U000024C2-\U0001F251"
u"\U00010000-\U0010ffff"
"]+", flags=re.UNICODE)
return(emoji_pattern.sub(r'', text))
data = pd.read_csv('test.tsv',encoding='utf-8', sep='\t') # read tsv file
# data = pd.read_csv('test.csv',encoding='utf-8') read csv file
data[u'header'] = data[u'header'].astype(str)
data[u'header'] = data[u'header'].apply(lambda x:demoji(x))
data.to_csv('output.csv',index=False, encoding='utf-8') # save to csv file