待切分句子:
s = "12、China's Legend Holdings will split its several business arms to go public on stock markets, the group's president Zhu Linan said on Tuesday.該集團總裁朱利安週二表示,haha中國聯想控股將分拆其多個業務部門在股市上市,。"
切分結果:
['12', 'china', 's', 'legend', 'holdings', 'will', 'split', 'its', 'several', 'business', 'arms', 'to', 'go', 'public', 'on', 'stock', 'markets', 'the', 'group', 's', 'president', 'zhu', 'linan', 'said', 'on', 'tuesday', '該', '集', '團', '總', '裁', '朱', '利', '安', '周', '二', '表', '示', 'haha', '中', '國', '聯', '想', '控', '股', '將', '分', '拆', '其', '多', '個', '業', '務', '部', '門', '在', '股', '市', '上', '市']
代碼:
import re
def get_word_list(s1):
# 把句子按字分開,中文按字分,英文按單詞,數字按空格
regEx = re.compile('[\\W]*') # 我們可以使用正則表達式來切分句子,切分的規則是除單詞,數字外的任意字符串
res = re.compile(r"([\u4e00-\u9fa5])") # [\u4e00-\u9fa5]中文範圍
p1 = regEx.split(s1.lower())
str1_list = []
for str in p1:
if res.split(str) == None:
str1_list.append(str)
else:
ret = res.split(str)
for ch in ret:
str1_list.append(ch)
list_word1 = [w for w in str1_list if len(w.strip()) > 0] # 去掉爲空的字符
return list_word1
if __name__ == '__main__':
s = "12、China's Legend Holdings will split its several business arms to go public on stock markets, the group's president Zhu Linan said on Tuesday.該集團總裁朱利安週二表示,haha中國聯想控股將分拆其多個業務部門在股市上市。"
list_word1=get_word_list(s)
print(list_word1)