Create captura2.py

captura2.py

@@ -0,0 +1,126 @@
+# Importando las librerías Gradio, requests, PIL e io
+import gradio as gr
+import requests
+from PIL import Image
+from io import BytesIO
+import argparse
+import os
+import cv2
+import requests
+import numpy as np
+from pathlib import Path
+import warnings
+
+import torch
+
+from groundingdino.models import build_model
+from groundingdino.util.slconfig import SLConfig
+from groundingdino.util.utils import clean_state_dict
+from groundingdino.util.inference import annotate, load_image, predict
+import groundingdino.datasets.transforms as T
+
+from huggingface_hub import hf_hub_download
+
+# Use this command for evaluate the GLIP-T model
+config_file = "groundingdino/config/GroundingDINO_SwinT_OGC.py"
+ckpt_repo_id = "ShilongLiu/GroundingDINO"
+ckpt_filenmae = "groundingdino_swint_ogc.pth"
+
+def load_model_hf(model_config_path, repo_id, filename, device='cpu'):
+    args = SLConfig.fromfile(model_config_path) 
+    model = build_model(args)
+    args.device = device
+
+    cache_file = hf_hub_download(repo_id=repo_id, filename=filename)
+    checkpoint = torch.load(cache_file, map_location='cpu')
+    log = model.load_state_dict(clean_state_dict(checkpoint['model']), strict=False)
+    print("Model loaded from {} \n => {}".format(cache_file, log))
+    _ = model.eval()
+    return model    
+
+def image_transform_grounding(init_image):
+    transform = T.Compose([
+        T.RandomResize([800], max_size=1333),
+        T.ToTensor(),
+        T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+    ])
+    image, _ = transform(init_image, None) # 3, h, w
+    return init_image, image
+
+def image_transform_grounding_for_vis(init_image):
+    transform = T.Compose([
+        T.RandomResize([800], max_size=1333),
+    ])
+    image, _ = transform(init_image, None) # 3, h, w
+    return image
+
+model = load_model_hf(config_file, ckpt_repo_id, ckpt_filenmae)
+
+def run_grounding(input_image, grounding_caption, box_threshold, text_threshold):
+    init_image = input_image.convert("RGB")
+    original_size = init_image.size
+
+    _, image_tensor = image_transform_grounding(init_image)
+    image_pil: Image = image_transform_grounding_for_vis(init_image)
+
+    # run grounding
+    boxes, logits, phrases = predict(model, image_tensor, grounding_caption, box_threshold, text_threshold, device='cpu')
+    annotated_frame = annotate(image_source=np.asarray(image_pil), boxes=boxes, logits=logits, phrases=phrases)
+    image_with_box = Image.fromarray(cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB))
+
+    return image_with_box
+
+
+# Definiendo la función captura_pagina
+def captura_pagina(url):
+    # Asignando la clave de la API y la URL
+    api_key = 'b77e9ec7b82e4447b93c73cf1af4a93f'
+    api_url = f'https://api.apiflash.com/v1/urltoimage?access_key={api_key}&url={url}'
+
+    # Haciendo una solicitud GET a la API
+    respuesta = requests.get(api_url, stream=True)
+
+    # Si la solicitud es exitosa, se procesa la imagen
+    if respuesta.status_code == 200:
+        image_data = b''
+        for chunk in respuesta.iter_content(8192):
+            image_data += chunk
+        image = Image.open(BytesIO(image_data))
+
+        # Set the fixed box_threshold and text_threshold
+        box_threshold = 0.38
+        text_threshold = 0.25
+        grounding_caption = "Find the webform in the picture of a web."
+
+        # Run the Grounding DINO model on the image
+        image_with_bb = run_grounding(image, grounding_caption, box_threshold, text_threshold)
+
+        return "¡Página web capturada con éxito!", image, image_with_bb
+    else:
+        # Si la solicitud no es exitosa, se retorna un mensaje de error
+        return f'Error: {respuesta.status_code}', None, None
+
+# Definiendo la función captura_pagina_app
+def captura_pagina_app():
+    # Creando un objeto de la clase Row de Gradio
+    with gr.Row():
+        with gr.Column():
+            # Agregando un cuadro de texto para ingresar la URL
+            textbox_url = gr.Textbox(label='URL')
+
+            # Agregando un botón para capturar la página web
+            btn_predecir = gr.Button(value='Predecir')
+        with gr.Column():
+            # Agregando un cuadro de texto para mostrar el estado
+            output_mensaje = gr.Textbox(label='Estado')
+
+            # Agregando dos imágenes para mostrar la captura de la página web
+            output_img1 = gr.Image()
+            output_img2 = gr.Image()
+
+    # Asociando la función captura_pagina con el botón
+    btn_predecir.click(
+        fn=captura_pagina,
+        inputs=textbox_url,
+        outputs=[output_mensaje, output_img1, output_img2]
+    )