如何将SharePoint列表加载到TIBLE in R中？

我想将SharePoint列表加载到R中的TIBLE中

我尝试的问题是，数据的每个值都包装在一个列表中。如何展开每个值或更改数据转换以直接包含字符串，而不是列表

# A tibble: 10 x 6
   `__metadata` A          B             C                D             E
   <list>       <list>     <list>        <list>           <list>        <list>    
 1 <list [4]>   <list [1]> <chr [1]>     <list [2]>       <chr [1]>     <chr [1]> 
 2 <list [4]>   <list [1]> <chr [1]>     <list [2]>       <chr [1]>     <chr [1]> 
 3 <list [4]>   <list [1]> <chr [1]>     <list [2]>       <chr [1]>     <chr [1]> 
 4 <list [4]>   <list [1]> <chr [1]>     <list [2]>       <chr [1]>     <chr [1]> 
 5 <list [4]>   <list [1]> <chr [1]>     <list [2]>       <chr [1]>     <chr [1]> 
 6 <list [4]>   <list [1]> <chr [1]>     <list [2]>       <chr [1]>     <chr [1]> 
 7 <list [4]>   <list [1]> <chr [1]>     <list [2]>       <chr [1]>     <chr [1]>
 ...

。。。以及

map（）

、

mutate\u all（）

、

unest（）

和

unlist（）

的许多其他组合

我认为问题在于我处理数据的方式。原始JSON的格式如下：

{
    "d": {
        "results": [
        {
            "__metadata": {
            "id": "<GUID>",
            "uri": "<redacted>",
            "etag": "\"42\"",
            "type": "SP.Data.DownloadcenterItem"
            },
            "A": {
            "results": [
                {
                "__metadata": {
                    "id": "<GUID>",
                    "type": "SP.Data.UserInfoItem"
                },
                "Title": "<redacted>"
                }
            ]
            },
            "C": {
            "__metadata": {
                "id": "<GUID>",
                "type": "SP.Data.UserInfoItem"
            },
            "EMail": "<redacted>"
            },
            "B": "<redacted>",
            "D": "<redacted>",
            "E": "<redacted>"
        },
        ...
        ],
        "__next": "<redacted>"
    }
}

---

以下内容适用于您的数据。您不需要在此处使用

purrr

包

库（dplyr）
图书馆（tibble）
图书馆（tidyr）

---

酷。我认为在这里使用

map\u-dfr（~enframe（.x））

不是一个好主意。您需要后退一步，查看JSON数据。找出你需要什么，然后提取出来。现在你有一大堆嵌套的-嵌套的列表。我的建议是离这个问题稍微远一点，以一种开放的心态以一种更普遍的方式来思考它。如果您希望我们帮助您，请共享

dput（my_data$d$results）

。（@akrun自找的）。好的。让我们看看enframe的结果（未列出（当前页面$d$results））。大量的元数据、ID、类型等。现在您需要确定要保留哪些行（数据字段）。然后，您可以进入下一步，即重塑！我想扔掉所有元数据，保留其余的

$d$results%%>%map\u dfr（enframe）%%>%filter（name！=''uuu metadata'）

似乎丢弃了元数据，但

unnest（value）

产生了与之前相同的错误

enframe（unlist（当前页面$d$results））%%>%filter（！grepl（“metadata”，name，ignore.case=T））%%>%groupby（name）%%>%mutate（rid=1:n（））>%pivot\u（-rid，names\u from=“name”，values\u from=“value”）%%>%unest

这在您发布的

dput的输出中对我起了作用。
{
    "d": {
        "results": [
        {
            "__metadata": {
            "id": "<GUID>",
            "uri": "<redacted>",
            "etag": "\"42\"",
            "type": "SP.Data.DownloadcenterItem"
            },
            "A": {
            "results": [
                {
                "__metadata": {
                    "id": "<GUID>",
                    "type": "SP.Data.UserInfoItem"
                },
                "Title": "<redacted>"
                }
            ]
            },
            "C": {
            "__metadata": {
                "id": "<GUID>",
                "type": "SP.Data.UserInfoItem"
            },
            "EMail": "<redacted>"
            },
            "B": "<redacted>",
            "D": "<redacted>",
            "E": "<redacted>"
        },
        ...
        ],
        "__next": "<redacted>"
    }
}

current_page <- httr::GET('<URL>') %>% httr::content()
my_data <- current_page$d$results %>%
  map(enframe) %>%
  map(~ spread(.x, name, value))

list(list(`__metadata` = list(id = "<redacted>", 
    uri = "<redacted>", 
    etag = "<redacted>", type = "<redacted>"), dmsAuthor = list(
    results = list(list(`__metadata` = list(id = "<redacted>", 
        type = "<redacted>"), Title = "<redacted>"))), 
    dmsDocumentOwner = list(`__metadata` = list(id = "<redacted>", 
        type = "<redacted>"), EMail = "<redacted>"), 
    dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"), 
    list(`__metadata` = list(id = "<redacted>", 
        uri = "<redacted>", 
        etag = "<redacted>", type = "<redacted>"), 
        dmsAuthor = list(results = list(list(`__metadata` = list(
            id = "<redacted>", type = "<redacted>"), 
            Title = "<redacted>"))), dmsDocumentOwner = list(
            `__metadata` = list(id = "<redacted>", 
                type = "<redacted>"), EMail = "<redacted>"), 
        dmsDocumentID = "<redacted>", dmsDocVersion = "<redacted>", dmsSPTitle = "<redacted>"))

enframe(unlist(current_page$d$results)) %>% 
  filter(!grepl("metadata", name, ignore.case = T)) %>% 
  group_by(name) %>% 
  mutate(rid = 1:n()) %>% 
  pivot_wider(-rid, names_from = "name", values_from = "value") %>% 
  unnest

#> # A tibble: 10 x 5
#>    dmsAuthor.resul~ dmsDocumentOwne~ dmsDocumentID dmsDocVersion dmsSPTitle
#>    <chr>            <chr>            <chr>         <chr>         <chr>     
#>  1 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#>  2 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#>  3 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#>  4 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#>  5 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#>  6 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#>  7 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#>  8 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#>  9 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>
#> 10 <redacted>       <redacted>       <redacted>    <redacted>    <redacted>

#> Warning: Values in `value` are not uniquely identified; output will contain list-cols.
##> * Use `values_fn = list(value = list)` to suppress this warning.
##> * Use `values_fn = list(value = length)` to identify where the duplicates arise
##> * Use `values_fn = list(value = summary_fun)` to summarise duplicates
##> Warning: `cols` is now required.
##> Please use `cols = c(dmsAuthor.results.Title, dmsDocumentOwner.EMail, dmsDocumentID, 
##>     dmsDocVersion, dmsSPTitle)`