import re
x = '"<ENAMEX TYPE="PERSON">Edward R. Kimmel</ENAMEX>, one of Admiral <ENAMEX TYPE="PERSON">Jack</ENAMEX>"'
mac = []
mac = re.findall("TYPE=\"PERSON\">(.+?)<",x)
for i in mac:
print "PERSON "+i
from bs4 import BeautifulSoup
txt = """<ENAMEX TYPE="PERSON">Edward R. Kimmel</ENAMEX>, one of Admiral <ENAMEX TYPE="PERSON">Jack</ENAMEX>'s twosurviving sons and..."""
soup = BeautifulSoup(txt,"html.parser")
for i in soup.findAll(attrs={'type' : 'PERSON'}):
print(i.text)
只需使用
.findall
你有没有试过“美苏”?你知道吗
相关问题 更多 >
编程相关推荐