使用 Gradio 和 Hugging Face 在 Lines 下使用 Python 代码构建文本提取器应用程序

# use an official python runtime as a parent image
from python:3.12
env pip_root_user_action=ignore

# set the working directory in the container
workdir $home/app

# install system dependencies
run apt-get update && apt-get install -y
run apt-get install -y tesseract-ocr
run apt-get install -y libtesseract-dev
run apt-get install -y libgl1-mesa-glx
run apt-get install -y libglib2.0-0
run pip install --upgrade pip

# copy requirements and install dependencies
copy requirements.txt requirements.txt
run pip install --no-cache-dir -r requirements.txt

# copy the app code
copy app.py ./

# expose the port for gradio
expose 7860

# run the application
cmd ["python", "app.py"]

import gradio as gr
import pytesseract
from pil import image
import os

def extract_text(image_path):
    if not image_path:
        return "no image uploaded. please upload an image."

    if not os.path.exists(image_path):
        return f"error: file not found at {image_path}"

    try:
        img = image.open(image_path)
        text = pytesseract.image_to_string(img)
        return text if text.strip() else "no text detected in the image."
    except exception as e:
        return f"an error occurred: {str(e)}"

iface = gr.interface(
    fn=extract_text,
    inputs=gr.image(type="filepath", label="upload an image"),
    outputs=gr.textbox(label="extracted text"),
    title="image text extractor",
    description="upload an image and extract text from it using ocr."
)

iface.launch(server_name="0.0.0.0", server_port=7860)

gradio
pytesseract
Pillow