urllib.parse — 解析 URL

urllib.parse — Split URLs into Components

解析

# urllib_parse_urlparse.py
from urllib.parse import urlparse

url = 'http://netloc/path;param?query=arg#frag'
parsed = urlparse(url)
print(parsed)

# urllib_parse_urlparseattrs.py
from urllib.parse import urlparse

url = 'http://user:pwd@NetLoc:80/path;param?query=arg#frag'
parsed = urlparse(url)
print('scheme  :', parsed.scheme)
print('netloc  :', parsed.netloc)
print('path    :', parsed.path)
print('params  :', parsed.params)
print('query   :', parsed.query)
print('fragment:', parsed.fragment)
print('username:', parsed.username)
print('password:', parsed.password)
print('hostname:', parsed.hostname)
print('port    :', parsed.port)

# urllib_parse_urlsplit.py
from urllib.parse import urlsplit

url = 'http://user:pwd@NetLoc:80/p1;para/p2;para?query=arg#frag'
parsed = urlsplit(url)
print(parsed)
print('scheme  :', parsed.scheme)
print('netloc  :', parsed.netloc)
print('path    :', parsed.path)
print('query   :', parsed.query)
print('fragment:', parsed.fragment)
print('username:', parsed.username)
print('password:', parsed.password)
print('hostname:', parsed.hostname)
print('port    :', parsed.port)

# urllib_parse_urldefrag.py
from urllib.parse import urldefrag

original = 'http://netloc/path;param?query=arg#frag'
print('original:', original)
d = urldefrag(original)
print('url     :', d.url)
print('fragment:', d.fragment)

Unparsing

# urllib_parse_geturl.py
from urllib.parse import urlparse

original = 'http://netloc/path;param?query=arg#frag'
print('ORIG  :', original)
parsed = urlparse(original)
print('PARSED:', parsed.geturl())

# urllib_parse_urlunparse.py
from urllib.parse import urlparse, urlunparse

original = 'http://netloc/path;param?query=arg#frag'
print('ORIG  :', original)
parsed = urlparse(original)
print('PARSED:', type(parsed), parsed)
t = parsed[:]
print('TUPLE :', type(t), t)
print('NEW   :', urlunparse(t))

# urllib_parse_urlunparseextra.py
from urllib.parse import urlparse, urlunparse

original = 'http://netloc/path;?#'
print('ORIG  :', original)
parsed = urlparse(original)
print('PARSED:', type(parsed), parsed)
t = parsed[:]
print('TUPLE :', type(t), t)
print('NEW   :', urlunparse(t))

连接

# urllib_parse_urljoin.py
from urllib.parse import urljoin

print(urljoin('http://www.example.com/path/file.html',
              'anotherfile.html'))
print(urljoin('http://www.example.com/path/file.html',
              '../anotherfile.html'))

# urllib_parse_urljoin_with_path.py
from urllib.parse import urljoin

print(urljoin('http://www.example.com/path/',
              '/subpath/file.html'))
print(urljoin('http://www.example.com/path/',
              'subpath/file.html'))

编码查询参数

# urllib_parse_urlencode.py
from urllib.parse import urlencode

query_args = {
    'q': 'query string',
    'foo': 'bar',
}
encoded_args = urlencode(query_args)
print('Encoded:', encoded_args)

# urllib_parse_urlencode_doseq.py
from urllib.parse import urlencode

query_args = {
    'foo': ['foo1', 'foo2'],
}
print('Single  :', urlencode(query_args))
print('Sequence:', urlencode(query_args, doseq=True))

# urllib_parse_parse_qs.py
from urllib.parse import parse_qs, parse_qsl

encoded = 'foo=foo1&foo=foo2'

print('parse_qs :', parse_qs(encoded))
print('parse_qsl:', parse_qsl(encoded))

# urllib_parse_quote.py
from urllib.parse import quote, quote_plus, urlencode

url = 'http://localhost:8080/~hellmann/'
print('urlencode() :', urlencode({'url': url}))
print('quote()     :', quote(url))
print('quote_plus():', quote_plus(url))

# urllib_parse_unquote.py
from urllib.parse import unquote, unquote_plus

print(unquote('http%3A//localhost%3A8080/%7Ehellmann/'))
print(unquote_plus(
    'http%3A%2F%2Flocalhost%3A8080%2F%7Ehellmann%2F'
))