方法一:(python3适用)
from urllib.parse import urlparse
def url_to_domain(url):
o = urlparse(url)
domain = o.hostname
return domain
urls = [
"http://meiwen.me/src/index.html",
"http://1000chi.com/game/index.html",
"http://see.xidian.edu.cn/cpp/html/1429.html",
"https://docs.python.org/2/howto/regex.html",
"""https://www.google.com.hk/search?client=aff-cs-360chromium&hs=TSj&q=url%E8%A7%A3%E6%9E%90%E5%9F%9F%E5%90%8Dre&oq=url%E8%A7%A3%E6%9E%90%E5%9F%9F%E5%90%8Dre&gs_l=serp.3...74418.86867.0.87673.28.25.2.0.0.0.541.2454.2-6j0j1j1.8.0....0...1c.1j4.53.serp..26.2.547.IuHTj4uoyHg""",
"file:///D:/code/echarts-2.0.3/doc/example/tooltip.html",
"http://api.mongodb.org/python/current/faq.html#is-pymongo-thread-safe",
"https://pypi.python.org/pypi/publicsuffix/",
"http://127.0.0.1:8000"
]
for url in urls:
print(url_to_domain(url))
# print(url_to_domain("http://www.baidu.com:80/index.php?id=1&uid=2"))
# --> www.baidu.com
这里也提到了几种方法,使用python3的话需要更改代码:
https://www.jb51.net/article/55693.htm