Python URL处理与解析

urllib.parse 模块处理 URL 解析、编码和构建。

urlparse 解析 URL

from urllib.parse import urlparse

# 解析 URL 组件
url = 'https://example.com:8080/path?key=value#section'
result = urlparse(url)

print(result.scheme)    # https
print(result.netloc)    # example.com:8080
print(result.path)      # /path
print(result.params)    # （查询前参数）
print(result.query)     # key=value
print(result.fragment)  # section

print(result)  # ParseResult 对象

urlunparse 构建 URL

from urllib.parse import urlunparse

# 从组件构建 URL
components = ('https', 'example.com', '/path', '', 'key=value', 'section')
url = urlunparse(components)
print(url)  # https://example.com/path?key=value#section

urljoin 拼接 URL

from urllib.parse import urljoin

# 相对 URL 拼接
base = 'https://example.com/path/page.html'

# 相对路径
print(urljoin(base, 'other.html'))
# https://example.com/path/other.html

print(urljoin(base, '../up.html'))
# https://example.com/up.html

print(urljoin(base, '/absolute'))
# https://example.com/absolute

print(urljoin(base, 'https://other.com'))
# https://other.com（完整 URL 覆盖）

urlencode 编码参数

from urllib.parse import urlencode

# 字典编码为查询字符串
params = {'key': 'value', 'name': 'Alice', 'age': 25}
query = urlencode(params)
print(query)  # key=value&name=Alice&age=25

# 列表编码（多值参数）
params = [('key', 'value1'), ('key', 'value2')]
query = urlencode(params)
print(query)  # key=value1&key=value2

# 自定义分隔符
query = urlencode(params, doseq=True)

parse_qs 解析查询字符串

from urllib.parse import parse_qs, parse_qsl

# 解析查询字符串为字典
query = 'key=value&name=Alice&list=1&list=2'
result = parse_qs(query)
print(result)  # {'key': ['value'], 'name': ['Alice'], 'list': ['1', '2']}

# 解析为列表
result = parse_qsl(query)
print(result)  # [('key', 'value'), ('name', 'Alice'), ('list', '1'), ('list', '2')]

quote 编码特殊字符

from urllib.parse import quote, quote_plus

# 编码 URL 中的特殊字符
text = 'hello world/special'
encoded = quote(text)
print(encoded)  # hello%20world%2Fspecial

# quote_plus 编码空格为 +
encoded = quote_plus(text)
print(encoded)  # hello+world%2Fspecial

# safe 参数指定不编码的字符
encoded = quote(text, safe='/')
print(encoded)  # hello%20world/special

unquote 解码

from urllib.parse import unquote, unquote_plus

# 解码 URL 编码
encoded = 'hello%20world%2Fspecial'
text = unquote(encoded)
print(text)  # hello world/special

# unquote_plus 解码 +
encoded = 'hello+world%2Fspecial'
text = unquote_plus(encoded)
print(text)  # hello world/special

综合示例

from urllib.parse import urlparse, urlencode, urlunparse

def build_url(base_url, path, params=None):
    "构建完整 URL"
    parsed = urlparse(base_url)

    # 添加路径
    new_path = parsed.path + path

    # 编码参数
    query = urlencode(params) if params else parsed.query

    # 构建 URL
    new_url = urlunparse((
        parsed.scheme,
        parsed.netloc,
        new_path,
        parsed.params,
        query,
        parsed.fragment
    ))
    return new_url

url = build_url('https://api.example.com/v1', '/users', {'id': 123})
print(url)  # https://api.example.com/v1/users?id=123

URL 组件提取

from urllib.parse import urlparse

url = 'https://user:pass@example.com:8080/path?query=1#frag'
result = urlparse(url)

# 提取用户名密码
from urllib.parse import parse_qs
print(result.username)  # user
print(result.password)  # pass

# 提取主机和端口
print(result.hostname)  # example.com
print(result.port)      # 8080

函数汇总

要点总结

• urlparse() 解析 URL 为各组件
• urlunparse() 从组件构建 URL
• urljoin() 处理相对 URL 拼接
• urlencode() 编码字典为查询字符串
• parse_qs() 解析查询字符串
• quote() 编码特殊字符为 %XX
• quote_plus() 编码空格为 +
• unquote() 解码 URL 编码字符串
• urllib.parse 是 URL 处理的标准工具