Created
December 7, 2014 02:07
-
-
Save pierre3/05b5522794c0d10d6bed to your computer and use it in GitHub Desktop.
https://labs.goo.ne.jp/ の固有表現抽出APIを使用して、文字列から固有表現を取得する PowerShell function
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<# | |
.Synopsis | |
文字列から固有表現の抽出 | |
.DESCRIPTION | |
https://labs.goo.ne.jp/ の固有表現抽出APIを使用して、文字列から固有表現を取得します | |
https://labs.goo.ne.jp/apiusage/ で取得したアプリケーションIDを $AppId パラメータに指定する必要があります。 | |
.EXAMPLE | |
Get-GooLabsEntity "今日、田中君と山本君に渋谷で待ち合わせをしています。" -AppId $app_id | |
.EXAMPLE | |
Get-Content ".\data.txt" | Get-GooLabsEntity -AppId $app_id | |
#> | |
function Get-GooLabsEntity | |
{ | |
[CmdletBinding()] | |
Param( | |
# 検索ワード | |
[Parameter(Mandatory=$true, | |
ValueFromPipeline=$true, | |
Position=0)] | |
[string[]] | |
$InputStrings, | |
[Parameter(Position=1)] | |
[string] | |
$AppId = $goo_labs_app_id | |
) | |
Begin | |
{ | |
$sentence = "" | |
function doRequest | |
{ | |
Param([string]$sentence) | |
Write-Verbose ">>> Invoke-WebRequest <<<" | |
$response = Invoke-WebRequest -Method Post -Uri https://labs.goo.ne.jp/api/entity ` | |
-Body @{ app_id = $AppId; sentence = $sentence; } | |
[Text.Encoding]::GetEncoding("utf-8").GetString($response.RawContentStream.GetBuffer()) | | |
ConvertFrom-Json | % { | |
foreach($item in $_.ne_list){ | |
[PSCustomObject]@{ Type = $item[1]; Value=$item[0] } | |
} | |
}; | |
}; | |
} | |
Process | |
{ | |
foreach($text in $InputStrings) | |
{ | |
Write-Verbose "input>> $text" | |
$sentence = "$sentence,$text" | |
if($sentence.Length -le 300) | |
{ | |
continue | |
} | |
doRequest $sentence | |
$sentence = "" | |
} | |
} | |
End | |
{ | |
if($sentence -ne "") | |
{ | |
doRequest $sentence | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment