☰

OCR Image Content Display

Displays the text content of the image in the clipboard using OCR and displays it in an alert when the script is run.

  1. // ==UserScript==
  2. // @name         OCR Image Content Display
  3. // @namespace    http://tampermonkey.net/
  4. // @version      1.1.1
  5. // @description  Displays the text content of the image in the clipboard using OCR and displays it in an alert when the script is run.
  6. // @match        *://*/*
  7. // @grant        none
  8. // @license      MIT
  9. // ==/UserScript==
  10.  
  11. (function() {
  12.     'use strict';
  13.  
  14.        async function displayImageContent() {
  15.  
  16.         const clipboardItems = await navigator.clipboard.read();
  17.         for (const clipboardItem of clipboardItems) {
  18.             for (const type of clipboardItem.types) {
  19.                 if (type.startsWith('image/')) {
  20.                     const blob = await clipboardItem.getType(type);
  21.                     const formData = new FormData();
  22.                     formData.append('apikey', '你自己的 api');
  23.                     formData.append('language', 'eng');
  24.                     formData.append('isOverlayRequired', 'false');
  25.                     formData.append('file', blob, 'image.png');
  26.                     const response = await fetch('https://api.ocr.space/parse/image', {
  27.                         method: 'POST',
  28.                         body: formData
  29.                     });
  30.                     const data = await response.json();
  31.                     if (data && data.ParsedResults && data.ParsedResults.length > 0) {
  32.                         const text = data.ParsedResults[0].ParsedText;
  33.                         // 将识别结果显示在一个提示框中
  34.                         // 调用 OpenAI 的翻译服务将识别结果翻译成中文
  35.  const audio = new Audio(`https://tsn.baidu.com/text2audio?tex=${text}&lan=zh&cuid=abcdefg1234567&ctp=1&per=5003&tok=你自己的 tok`);
  36.                         const apiKey = "你自己的 api";
  37.                         const openaiResponse = await fetch('https://api.openai.com/v1/engines/text-davinci-003/completions', {
  38.                             method: 'POST',
  39.                             headers: {
  40.                                 'Content-Type': 'application/json',
  41.                                 'Authorization': `Bearer ${apiKey}`
  42.                             },
  43.                             body: JSON.stringify({
  44.                                 prompt: `Translate the following English text into Chinese:\n\n${text}.`,
  45.                                 max_tokens: 1000,
  46.                                 n: 1,
  47.                                 temperature: 0.9
  48.                             })
  49.                         });
  50.                         const openaiData = await openaiResponse.json();
  51.                         const translation = openaiData.choices[0].text;
  52.                         // 将识别结果和翻译结果显示在一个提示框中
  53.                         alert(`${text}${translation}`);
  54. audio.play();
  55.                     }
  56.                 }
  57.             }
  58.         }
  59.  
  60.  
  61.        }
  62.  
  63.     const cursor = document.createElement('button');
  64.     cursor.style.position = 'fixed';
  65.     cursor.style.top = '10%';
  66.     cursor.style.right = '10%';
  67.     cursor.style.width = '50px';
  68.     cursor.style.height = '50px';
  69.     cursor.style.backgroundColor = '#b1c5b4';
  70.     cursor.style.borderRadius = '50%';
  71.     //cursor.style.cursor = 'pointer';
  72.     cursor.style.boxShadow = '0 8 24px rgba(0, 0, 0, 0.15)';
  73.     cursor.innerText = '👻';
  74.     cursor.style.fontSize = '20px';
  75.     cursor.style.border = "2px solid #888888";
  76.     cursor.style.zIndex = '9999';
  77.  
  78.     document.body.appendChild(cursor);
  79.  
  80.  
  81.     cursor.addEventListener('click', displayImageContent);
  82. })()