Python/ocr.html at main · 0xriteish/Python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
<!DOCTYPE html>
<html>
  <head>
    <script src="https://cdn.jsdelivr.net/npm/tesseract.js@5/dist/tesseract.min.js"></script>
  </head>
  <body>
    <h1>OCR Analysis</h1>
    <div id="log">Running...</div>
    <script>
      const { createWorker } = Tesseract;
      (async () => {
        const worker = await createWorker("eng");
        const ret = await worker.recognize("receipt_work.jpg");

        const words = ret.data.words.map((w) => ({
          text: w.text,
          bbox: w.bbox,
          confidence: w.confidence,
        }));

        // Log everything that looks like a number
        const matches = words.filter((w) => /\d/.test(w.text));

        const result = JSON.stringify(matches, null, 2);
        document.body.innerHTML += `<pre id="results">${result}</pre>`;
        document.getElementById("log").innerText = "Done";
        await worker.terminate();
      })();
    </script>
  </body>
</html>