Python-parse模块url转换

1. 拆分url

 1 from urllib.parse import urlparse
 2 
 3 result = urlparse("http://www.baidu.com/index.html;user?id=5#comment")
 4 print(result)
 5 print(list(result))
 6 print(result[0])
 7 
 8 # 结果：
 9 # ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5', fragment='comment')
10 # ['http', 'www.baidu.com', '/index.html', 'user', 'id=5', 'comment']
11 # http

View Code

2. 拼接url

 1 from urllib.parse import urlunparse
 2 
 3 data = ['http','www.baidu.com','index.html','user','a=123','commit']
 4 print(urlunparse(data))
 5 
 6 # 结果：
 7 # http://www.baidu.com/index.html;user?a=123#commit
 8 
 9 from urllib.parse import urljoin
10 
11 # 另一个拼贴url
12 
13 print(urljoin('http://www.baidu.com', 'FAQ.html'))
14 print(urljoin('http://www.baidu.com', 'https://pythonsite.com/FAQ.html'))
15 print(urljoin('http://www.baidu.com/about.html', 'https://pythonsite.com/FAQ.html'))
16 print(urljoin('http://www.baidu.com/about.html', 'https://pythonsite.com/FAQ.html?question=2'))
17 print(urljoin('http://www.baidu.com?wd=abc', 'https://pythonsite.com/index.php'))
18 print(urljoin('http://www.baidu.com', '?category=2#comment'))
19 print(urljoin('www.baidu.com', '?category=2#comment'))
20 print(urljoin('www.baidu.com#comment', '?category=2'))
21 
22 # 结果：
23 # http://www.baidu.com/FAQ.html
24 # https://pythonsite.com/FAQ.html
25 # https://pythonsite.com/FAQ.html
26 # https://pythonsite.com/FAQ.html?question=2
27 # https://pythonsite.com/index.php
28 # http://www.baidu.com?category=2#comment
29 # www.baidu.com?category=2#comment
30 # www.baidu.com?category=2

View Code

3. 另一个url拼接

 1 print(urljoin('http://www.baidu.com', 'FAQ.html'))
 2 print(urljoin('http://www.baidu.com', 'https://pythonsite.com/FAQ.html'))
 3 print(urljoin('http://www.baidu.com/about.html', 'https://pythonsite.com/FAQ.html'))
 4 print(urljoin('http://www.baidu.com/about.html', 'https://pythonsite.com/FAQ.html?question=2'))
 5 print(urljoin('http://www.baidu.com?wd=abc', 'https://pythonsite.com/index.php'))
 6 print(urljoin('http://www.baidu.com', '?category=2#comment'))
 7 print(urljoin('www.baidu.com', '?category=2#comment'))
 8 print(urljoin('www.baidu.com#comment', '?category=2'))
 9 
10 # 结果：
11 # http://www.baidu.com/FAQ.html
12 # https://pythonsite.com/FAQ.html
13 # https://pythonsite.com/FAQ.html
14 # https://pythonsite.com/FAQ.html?question=2
15 # https://pythonsite.com/index.php
16 # http://www.baidu.com?category=2#comment
17 # www.baidu.com?category=2#comment
18 # www.baidu.com?category=2

View Code

4. 字典转为参数

 1 from urllib.parse import urlencode
 2 
 3 params = {
 4     "name":"zhaofan",
 5     "age":23,
 6 }
 7 base_url = "http://www.baidu.com?"
 8 
 9 url = base_url+urlencode(params)
10 print(url)
11 
12 # 结果
13 # http://www.baidu.com?name=zhaofan&age=23

View Code

5. 参数转为字典

 1 url = '?id=1&name=xiaocai&'
 2 
 3 from urllib.parse import parse_qs
 4 
 5 url = url.split('?')
 6 
 7 aa = parse_qs(url[1])
 8 print(aa)
 9 
10 # 结果：
11 {'id': ['1'], 'name': ['xiaocai']}

View Code