Update app.py

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from pdf2image import convert_from_bytes
+import pytesseract
+
+def extract_text(file):
+    """
+    Extracts text from a PDF file using OCR.
+    - Converts PDF pages to images.
+    - Runs Tesseract OCR on each image.
+    """
+    if file is None:
+        return ""
+    # 讀取 PDF 原始位元組
+    pdf_bytes = file.read()
+    # 每頁轉成影像 (dpi=300 for better OCR accuracy)
+    images = convert_from_bytes(pdf_bytes, dpi=300)
+    # 用 Tesseract OCR 擷取文字並累積
+    text = ""
+    for img in images:
+        text += pytesseract.image_to_string(img, lang='eng+chi_tra') + "\n\n"
+    return text
+
+# 建立 Gradio 介面
+iface = gr.Interface(
+    fn=extract_text,
+    inputs=gr.inputs.File(label="Upload your PDF"),
+    outputs=gr.outputs.Textbox(label="Extracted Text"),
+    title="PDF Text Extractor with OCR",
+    description="Upload a PDF file and extract all text (including from images) using Tesseract OCR."
+)
+
+if __name__ == "__main__":
+    # 若要產生公開連結，可改成 iface.launch(share=True)
+    iface.launch()