用Python做50道ACM之《URLs》

17.URLs

http://acm.fzu.edu.cn/problem.php?pid=1033

利用正则表达式来处理

import sys
import re

def check_urls(url_list):
    for url in url_list:
        protocol=re.search(r'(.*)://',url).group(1)
        has_port=re.search(r':\d+',url)
        if has_port:
            port=has_port[0][1:]
        else:
            port='<default>'
        has_path=re.match('.*://.*?/(.*)',url)
        if has_path:
            path=has_path.group(1)
        else:
            path='<default>'
        if has_port:
            host=re.match(r'.*://(.*):',url).group(1)
        elif has_path:
            host=re.match(r'.*//(.*)/',url).group(1)
        else:
            host=re.match(r'.*//(.*)',url).group(1)
        print(url)
        print('URL #'+str(url_list.index(url)+1))
        print('Protocol = '+protocol)
        print('Host     = '+host)
        print('Port     = '+port)
        print('Path     = '+path)
        print()

line_left=0
for read_in in sys.stdin.readlines():
    if line_left==0:
        line_left=int(read_in.rstrip())
        url_list=[]
    else:
        url_list.append(read_in.rstrip())
        line_left-=1
        if line_left==0:
            check_urls(url_list)