Python-parse模块url转换

1. 拆分url

from urllib.parse import urlparse

result = urlparse("http://www.baidu.com/index.html;user?id=5#comment")
print(result)
print(list(result))
print(result[0])

# 结果：
# ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5', fragment='comment')
# ['http', 'www.baidu.com', '/index.html', 'user', 'id=5', 'comment']
# http

2. 拼接url

from urllib.parse import urlunparse

data = ['http','www.baidu.com','index.html','user','a=123','commit']
print(urlunparse(data))

# 结果：
# http://www.baidu.com/index.html;user?a=123#commit

from urllib.parse import urljoin

# 另一个拼贴url

print(urljoin('http://www.baidu.com', 'FAQ.html'))
print(urljoin('http://www.baidu.com', 'https://pythonsite.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://pythonsite.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://pythonsite.com/FAQ.html?question=2'))
print(urljoin('http://www.baidu.com?wd=abc', 'https://pythonsite.com/index.php'))
print(urljoin('http://www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com#comment', '?category=2'))

# 结果：
# http://www.baidu.com/FAQ.html
# https://pythonsite.com/FAQ.html
# https://pythonsite.com/FAQ.html
# https://pythonsite.com/FAQ.html?question=2
# https://pythonsite.com/index.php
# http://www.baidu.com?category=2#comment
# www.baidu.com?category=2#comment
# www.baidu.com?category=2

3. 另一个url拼接

print(urljoin('http://www.baidu.com', 'FAQ.html'))
print(urljoin('http://www.baidu.com', 'https://pythonsite.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://pythonsite.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://pythonsite.com/FAQ.html?question=2'))
print(urljoin('http://www.baidu.com?wd=abc', 'https://pythonsite.com/index.php'))
print(urljoin('http://www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com#comment', '?category=2'))

# 结果：
# http://www.baidu.com/FAQ.html
# https://pythonsite.com/FAQ.html
# https://pythonsite.com/FAQ.html
# https://pythonsite.com/FAQ.html?question=2
# https://pythonsite.com/index.php
# http://www.baidu.com?category=2#comment
# www.baidu.com?category=2#comment
# www.baidu.com?category=2

4. 字典转为参数

from urllib.parse import urlencode

params = {
    "name":"zhaofan",
    "age":23,
}
base_url = "http://www.baidu.com?"

url = base_url+urlencode(params)
print(url)

# 结果
# http://www.baidu.com?name=zhaofan&age=23

5. 参数转为字典

url = '?id=1&name=xiaocai&'

from urllib.parse import parse_qs

url = url.split('?')

aa = parse_qs(url[1])
print(aa)

# 结果：
{'id': ['1'], 'name': ['xiaocai']}