xpath丶BeautifulSoup丶pyquery丶jsonpath 解析html与json串

 1 import json
 2 from jsonpath import jsonpath
 3 
 4 def json_test():
 5     str1 = '{"name":"埃里克森"}'
 6     # 将字符串转为Python dict对象
 7     js_obj = json.loads(str1)
 8     print( type(js_obj) )
 9 
10     # 将dict转成,json字符串
11     json_str = json.dumps(js_obj, ensure_ascii=False)
12     print( type(json_str) )
13 
14     # 将json对象保存到文件
15     json.dump(js_obj, open('test.txt', 'w', encoding='utf-8'), ensure_ascii=False )
16 
17     # 从文件中读取json对象
18     jso = json.load(open('test.txt', 'r', encoding='utf-8'))
19     print( type(jso) )
20 
21 def jsonpath_test():
22     # JsonPath是Json版的XPath，正如XPath之于XML文档一样。
23     # XPath   JsonPath  说明
24     # | /     | $       | 文档根元素
25     # | .     | @       | 当前元素
26     # | /     | . or [] | 匹配下级元素
27     # | ..    | N/A     | 匹配上级元素,JsonPath不支持此操作符
28     # | //    | ..      | 递归匹配所有子元素
29     # | *     | *       | 通配符,匹配下级元素
30     # | @     | N/A     | 匹配属性,Jsonath不支持此操作
31     # | []    | []      | 下标运算,根据索引获取元素,XPath下标从1开始,jsonPath从0开始
32     # | |     | [,]     | 连接操作符,将多个届uo拼接成数组返回,可以使用索引或别名政局政局
33     # | N/A   | [start:end:step]| 数据切片操作
34     # | []    | ?()     | 过滤表达式
35     # | N/A   | ()      | 脚本表达式,使用底层脚本引擎,XPath不支持
36     # | ()    | N/A     | 分组,JsonPath不支持
37     str1 = '''
38         {
39             "store": {
40                 "book": [{
41                         "category": "reference",
42                         "author": "Nigel Rees",
43                         "title": "Sayings of the Century",
44                         "price": 8.95
45                     }, {
46                         "category": "fiction",
47                         "author": "Evelyn Waugh",
48                         "title": "Sword of Honour",
49                         "price": 12.99
50                     }, {
51                         "category": "fiction",
52                         "author": "Herman Melville",
53                         "title": "Moby Dick",
54                         "isbn": "0-553-21311-3",
55                         "price": 8.99
56                     }, {
57                         "category": "fiction",
58                         "author": "J. R. R. Tolkien",
59                         "title": "The Lord of the Rings",
60                         "isbn": "0-395-19395-8",
61                         "price": 22.99
62                     }
63                 ],
64                 "bicycle": {
65                     "color": "red",
66                     "price": 19.95
67                 }
68             }
69         }
70     '''
71     js_obj = json.loads(str1)
72     res1 = jsonpath(js_obj, '$.store.book[*].author') # 所有book的author节点  (对应xpath:"/store/book/author")
73     res2 = jsonpath(js_obj, '$..author') # 所有author节点   (对应xpath:"//author")
74     res3 = jsonpath(js_obj, '$.store.*') # store下的所有节点:book数组和bicycle节点  (对应xpath:"/store")
75     res4 = jsonpath(js_obj, '$.store..price') # store下的所有price节点  (对应xpath:"/store//price")
76     res5 = jsonpath(js_obj, '$..book[2]') # 匹配book第三个节点  (对应xpath:"//book[2]")
77     res6 = jsonpath(js_obj, '$..book[(@.length-1)]') # 匹配一个book节点  (对应xpath:"//book[last()]")
78     res7 = jsonpath(js_obj, '$..book[-1:]')
79     res8 = jsonpath(js_obj, '$..book[0,1]') # 匹配两个节点
80     res9 = jsonpath(js_obj, '$..book[:2]')  # (对应xpath:"//book[position()<3]")
81     res10 = jsonpath(js_obj, '$..book[?(@.price<10)]') # 过滤price<10的节点  (对应xpath:"//book[price<10]")
82     res11 = jsonpath(js_obj, '$..*') # 递归匹配所有子结点  (对应xpath:"//*")
83     print( res11 )
84 
85 if __name__ == '__main__':
86     jsonpath_test()