如何解析结构未知的嵌套json文件Golang

Question

I am trying to parse and get selected data from a deep nested json data in Go Lang. I'm having issues navigating through the structure and accessing the data. The data is too deep and complex to be parsed with a-priori known structures in Go. Here is the URL of the file: -https://www.data.gouv.fr/api/1/datasets/?format=csv&page=0&page_size=20

I did some parsing with map interfaces and using a json string:

resultdata := map[string]interface {}

json.Unmarshal([]byte(inputbytestring), &resultdata) //Inputstring is the string containing the JSON data of the above URL

The problem:

• How can turn resultdata into a map (of strings), so I can use methods available for maps?
• The JSON data is nested and has several levels. How is it possible to access the lower level JSON fields? is it possible to unmarshal the data recursively?

Answer 1

Once you have data as a map[string]interface{}, you can use type assertions to get to the lower levels of data.

There's a good explanation here of how to do this at https://blog.golang.org/json-and-go

Here's an example to get you most of the way:

https://play.golang.org/p/P8cGP1mTDmD

package main

import (
    "encoding/json"
    "fmt"
    "log"
)

func main() {
    jsonData := `{
    "string": "string_value",
    "number": 123.45,
    "js_array": ["a", "b", "c"],
    "integer": 678,
    "subtype": {
        "number_array": [1, 2, 3]
      }
    }`

    m := map[string]interface{}{}
    err := json.Unmarshal([]byte(jsonData), &m)
    if err != nil {
        log.Fatal(err)
    }

    for key, value := range m {
        switch v := value.(type) {
        case int:
            fmt.Printf("Key: %s, Integer: %d
", key, v)
        case float64:
            fmt.Printf("Key: %s, Float: %v
", key, v)
        case string:
            fmt.Printf("Key: %s, String: %s
", key, v)
        case map[string]interface{}:
            fmt.Printf("Key: %s, Subtype: %+v
", key, v)
        case []interface{}:
            //TODO: Read through each item in the interface and work out what type it is.
            fmt.Printf("Key: %s, []interface: %v
", key, v)
        default:
            fmt.Printf("Key: %s, unhandled type: %+v
", key, v)
        }
    }
}

Alternatively https://mholt.github.io/json-to-go/ does a decent job of turning examples of JSON data into Go structs that can be used for marshalling.

Putting the example in, I get something that isn't too bad.

type AutoGenerated struct {
    Data []struct {
        Acronym     interface{}   `json:"acronym"`
        Badges      []interface{} `json:"badges"`
        CreatedAt   string        `json:"created_at"`
        Deleted     interface{}   `json:"deleted"`
        Description string        `json:"description"`
        Extras      struct {
        } `json:"extras"`
        Frequency     string      `json:"frequency"`
        FrequencyDate interface{} `json:"frequency_date"`
        ID            string      `json:"id"`
        LastModified  string      `json:"last_modified"`
        LastUpdate    string      `json:"last_update"`
        License       string      `json:"license"`
        Metrics       struct {
            Discussions    int `json:"discussions"`
            Followers      int `json:"followers"`
            Issues         int `json:"issues"`
            NbHits         int `json:"nb_hits"`
            NbUniqVisitors int `json:"nb_uniq_visitors"`
            NbVisits       int `json:"nb_visits"`
            Reuses         int `json:"reuses"`
            Views          int `json:"views"`
        } `json:"metrics"`
        Organization struct {
            Acronym       string `json:"acronym"`
            Class         string `json:"class"`
            ID            string `json:"id"`
            Logo          string `json:"logo"`
            LogoThumbnail string `json:"logo_thumbnail"`
            Name          string `json:"name"`
            Page          string `json:"page"`
            Slug          string `json:"slug"`
            URI           string `json:"uri"`
        } `json:"organization"`
        Owner     interface{} `json:"owner"`
        Page      string      `json:"page"`
        Private   bool        `json:"private"`
        Resources []struct {
            Checksum struct {
                Type  string `json:"type"`
                Value string `json:"value"`
            } `json:"checksum"`
            CreatedAt   string      `json:"created_at"`
            Description interface{} `json:"description"`
            Extras      struct {
            } `json:"extras"`
            Filesize     int    `json:"filesize"`
            Filetype     string `json:"filetype"`
            Format       string `json:"format"`
            ID           string `json:"id"`
            LastModified string `json:"last_modified"`
            Latest       string `json:"latest"`
            Metrics      struct {
                NbHits         int `json:"nb_hits"`
                NbUniqVisitors int `json:"nb_uniq_visitors"`
                NbVisits       int `json:"nb_visits"`
                Views          int `json:"views"`
            } `json:"metrics"`
            Mime       string `json:"mime"`
            PreviewURL string `json:"preview_url"`
            Published  string `json:"published"`
            Title      string `json:"title"`
            Type       string `json:"type"`
            URL        string `json:"url"`
        } `json:"resources"`
        Slug             string        `json:"slug"`
        Spatial          interface{}   `json:"spatial"`
        Tags             []interface{} `json:"tags"`
        TemporalCoverage interface{}   `json:"temporal_coverage"`
        Title            string        `json:"title"`
        URI              string        `json:"uri"`
    } `json:"data"`
    Facets struct {
        Format [][]interface{} `json:"format"`
    } `json:"facets"`
    NextPage     string      `json:"next_page"`
    Page         int         `json:"page"`
    PageSize     int         `json:"page_size"`
    PreviousPage interface{} `json:"previous_page"`
    Total        int         `json:"total"`
}