python解析url 

 1 url = "https://www.baidu.com/a/b/c/?q=d&q=e&q=f"
 2 
 3 # 1. 先找到协议和域名
 4 # 以 "://" 分割
 5 protocol_end_index = url.find("://")
 6 if protocol_end_index != -1:
 7     protocol = url[:protocol_end_index]
 8     rest = url[protocol_end_index + 3:]
 9 else:
10     protocol = ''
11     rest = url
12 
13 # 2. 分离域名和路径+查询
14 # 找第一个 "/" 来区分域名和路径
15 # domain, pathquery = rest.split("/", 1)
16 # print(domain)
17 
18 slash_index = rest.find("/")
19 
20 if slash_index != -1:
21     domain = rest[:slash_index]
22     path_query = rest[slash_index:]
23 else:
24     domain = rest
25     path_query = ''
26 
27 # 3. 分离路径和查询参数
28 question_mark_index = path_query.find("?")
29 if question_mark_index != -1:
30     path = path_query[:question_mark_index]
31     query_str = path_query[question_mark_index + 1:]
32 else:
33     path = path_query
34     query_str = ''
35 
36 
37 # 4. 解析查询参数（可能有多个相同的键）
38 query_params = {}
39 if query_str:
40     pairs = query_str.split("&")
41     for pair in pairs:
42         if "=" in pair:
43             key, value = pair.split("=", 1)
44             if key in query_params:
45                 query_params[key].append(value)
46             else:
47                 query_params[key] = [value]
48         else:
49             # 没有 "=" 的情况
50             query_params[pair] = []
51 
52 # 输出解析结果
53 print("协议:", protocol)
54 print("域名:", domain)
55 print("路径:", path)
56 print("查询参数:", query_params)

 结果：

协议: https
域名: www.baidu.com
路径: /a/b/c/
查询参数: {'q': ['d', 'e', 'f']}

 

posted @ 2025-08-18 09:56  琵琶真的行  阅读(1)  评论(0)    收藏  举报