修改插件：Doc2X插件适配文件上传功能 (#2284)

* Change to download first and check contentType

* Up to date

* Some bug fix, still some bug with img

* Update tool to read from file

* improve formatting in PDF

* Add tool of img file OCR , but meet some bug

* Bug fix for parameter passing error.

* Modification Introduction

packages/plugins/src/Doc2X/URLPDF2text/index.ts

@@ -40,9 +40,35 @@ const main = async ({ apikey, url, ocr }: Props): Response => {
     real_api_key = data.data.token;
   }
 
-  //Get the image binary from the URL
+  //Fetch the pdf and check its contene type
+  let PDFResponse;
+  try {
+    PDFResponse = await fetch(url);
+  } catch (e) {
+    return {
+      result: `Failed to fetch PDF from URL: ${url} with error: ${e}`,
+      success: false
+    };
+  }
+  if (!PDFResponse.ok) {
+    return {
+      result: `Failed to fetch PDF from URL: ${url}`,
+      success: false
+    };
+  }
+
+  const contentType = PDFResponse.headers.get('content-type');
+  if (!contentType || !contentType.startsWith('application/pdf')) {
+    return {
+      result: `The provided URL does not point to a PDF: ${contentType}`,
+      success: false
+    };
+  }
+
+  const blob = await PDFResponse.blob();
   const formData = new FormData();
-  formData.append('pdf_url', url);
+  const fileName = url.split('/').pop()?.split('?')[0] || 'pdf';
+  formData.append('file', blob, fileName);
   formData.append('ocr', ocr ? '1' : '0');
 
   let upload_url = 'https://api.doc2x.noedgeai.com/api/platform/async/pdf';

packages/plugins/src/Doc2X/URLPDF2text/template.json

@@ -3,7 +3,7 @@
   "version": "488",
   "name": "Doc2X PDF文件(URL)识别",
   "avatar": "plugins/doc2x",
-  "intro": "将传入的PDF文件(URL)发送至Doc2X进行解析，返回带LaTeX公式的markdown格式的文本",
+  "intro": "从URL下载PDF文件，并发送至Doc2X进行解析，返回带LaTeX公式的markdown格式的文本",
   "inputExplanationUrl": "https://fael3z0zfze.feishu.cn/wiki/Rkc5witXWiJoi5kORd2cofh6nDg?fromScene=spaceOverview",
   "showStatus": true,
   "weight": 10,
@@ -201,7 +201,7 @@
             "key": "system_httpJsonBody",
             "renderTypeList": ["hidden"],
             "valueType": "any",
-            "value": "{\n  \"apikey\": \"{{apikey}}\",\n  \"url\": \"{{url}}\",\n  \"ocr\": \"{{ocr}}\"\n}",
+            "value": "{\n  \"apikey\": \"{{apikey}}\",\n  \"url\": \"{{url}}\",\n  \"ocr\": {{ocr}}\n}",
             "label": "",
             "required": false
           },