python url lib.parse 解析 url

import urllib.parse

url = "https://baijiahao.baidu.com/s?id=1775292027675766993"
u = urllib.parse.urlparse(url)

print(u) # ParseResult(scheme='https', netloc='baijiahao.baidu.com', path='/s', params='', query='id=1775292027675766993', fragment='')

# 获取域名
print(u.netloc) # baijiahao.baidu.com

# 替换域名
nu = u._replace(netloc='www.google.com')
print(nu)  # ParseResult(scheme='https', netloc='www.google.com', path='/s', params='', query='id=1775292027675766993', fragment='')

# 获取新的 url
nurl = urllib.parse.urlunparse(nu)
print(nurl) # https://www.google.com/s?id=1775292027675766993

来源：https://docs.python.org/3/library/urllib.parse.html

• urllib.parse.urlparse(urlstring, scheme='', allow_fragments=True)

• urllib.parse.parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', max_num_fields=None, separator='&')

• urllib.parse.parse_qsl(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', max_num_fields=None, separator='&')

• urllib.parse.urlunparse(parts)

• urllib.parse.urlsplit(urlstring, scheme='', allow_fragments=True)

• urllib.parse.urlunsplit(parts)

• urllib.parse.urljoin(base, url, allow_fragments=True)

• urllib.parse.urldefrag(url)

• urllib.parse.unwrap(url)