有些非法标签也被提取出来了,日后改进
#!/usr/bin/python
import re
import sys
fp = open(sys.argv[1],"r")
mystr = fp.read();
ans = re.findall("</?[^><]+>",mystr)
for i in ans:
print i
有些非法标签也被提取出来了,日后改进
#!/usr/bin/python
import re
import sys
fp = open(sys.argv[1],"r")
mystr = fp.read();
ans = re.findall("</?[^><]+>",mystr)
for i in ans:
print i