urlparse 类似处理操作系统路径的 os.path 模块，能够很好的处理网址路径
导入模块
python3
from urllib.parse import urlparse, urljoin
python2
from urlparse import urlparse, urljoin
使用测试
url = "https://cdn.itjuzi.com/images/51202bf56a442ba934fe15d34a3f2976.png?imageView2/0/w/58/q/100" ret = urlparse(url) print ret # ParseResult(scheme='https', netloc='cdn.itjuzi.com', # path='/images/51202bf56a442ba934fe15d34a3f2976.png', # params='', query='imageView2/0/w/58/q/100', fragment='') link = urljoin(ret.scheme+"://"+ret.netloc, ret.path) print link # https://cdn.itjuzi.com/images/51202bf56a442ba934fe15d34a3f2976.png
封装成函数
def get_clean_url(url): """ 获取干净的url链接 :param url: {str} url链接 :return: {str} 干净的url链接 """ ret = urlparse(url) link = urljoin(ret.scheme + "://" + ret.netloc, ret.path) return link print(get_clean_url(url)) # https://cdn.itjuzi.com/images/51202bf56a442ba934fe15d34a3f2976.png
