upload

app.py

@@ -17,8 +17,8 @@ search_google = False
 # GOOGLE_CSE_ID = "b536303d151b94476"
 # GOOGLE_API_KEY = "AIzaSyBUvPKAZa2TddKYDJI9t0ac2A_JJqdgWHo"
 # GOOGLE_CSE_ID = "f3446c60c52cd4dc2"
-GOOGLE_API_KEY = "AIzaSyCoBYZK4khX_W5eW-AqEXKOclUIer6CiC8"
-GOOGLE_CSE_ID = "c3ba01991c1a14c7d"
+# GOOGLE_API_KEY = "AIzaSyCoBYZK4khX_W5eW-AqEXKOclUIer6CiC8"
+# GOOGLE_CSE_ID = "c3ba01991c1a14c7d"
 mode = 'local'
 # mode = 'rbf'
 
@@ -70,21 +70,23 @@ shops = {
 regex_price = r'(\d+\.?\d*) ?([€$])|([€$]) ?(\d+\.?\d*)'
 
 
-def app(img, selected_shop):
-    if img is None:
-        raise gr.Error("No file uploaded. Please upload an image.")
+# def app(img, selected_shop):
+#     if img is None:
+#         raise gr.Error("No file uploaded. Please upload an image.")
+#
+#     # Check if the uploaded file is a PDF
+#     if selected_shop is None:
+#         raise gr.Error("Please select a shop.")
+#
+#     try:
+#         image_annotated = section(img)
+#         pass
+#     except Exception as e:
+#         return gr.Error(f"An error occurred: {str(e)}")
+#
+#     return image_annotated, hotspots_sku_links[selected_shop]
 
-    # Check if the uploaded file is a PDF
-    if selected_shop is None:
-        raise gr.Error("Please select a shop.")
 
-    try:
-        image_annotated = section(img)
-        pass
-    except Exception as e:
-        return gr.Error(f"An error occurred: {str(e)}")
-
-    return image_annotated, hotspots_sku_links[selected_shop]
 def build_request(query, start=1, num=10, date_restrict=None, **params):
     request = {
         'key': GOOGLE_API_KEY,
@@ -112,6 +114,7 @@ def make_request(request):
     else:
         return None
 
+
 with gr.Blocks() as demo:
 
     with gr.Row():
@@ -127,6 +130,9 @@ with gr.Blocks() as demo:
     section_btn = gr.Button("Identify Hotspots")
     # selected_section = gr.Textbox(label="Selected Hotspot")
     selected_section = gr.Markdown(label="Selected Hotspot")
+    product_dataframe = gr.Dataframe(label="Products Found")
+
+
     def get_yolo_predictions(image, confidence_threshold):
         # Use Roboflow API to get predictions
         predictions = model.predict(image, confidence=confidence_threshold, overlap=10).json()
@@ -147,51 +153,23 @@ with gr.Blocks() as demo:
 
     def section(img, selected_shop, confidence_threshold):
         hostpots = []
-        texts = []
         sku = []
-        # Define your Google API key and Custom Search Engine ID
+        product_table_data = []
+
+        global hotspots_sku_links
+        hotspots_sku_links = []
 
         #print("selected_shop:", selected_shop)
         search_url = shops[selected_shop]['url']
         ref_number_regex = shops[selected_shop]['regex']
         # print("search_url:", search_url)
         brands = shops[selected_shop]['brands'] if 'brands' in shops[selected_shop] else None
+
         if brands:
             brands = [brand.upper() for brand in brands]
 
         if mode == 'rbf':
             predictions = get_yolo_predictions(img)
-            # print("-------")
-            # for idx, pred in enumerate(predictions["predictions"]):
-            #     x_center = int(pred["x"])
-            #     y_center = int(pred["y"])
-            #     x = int(x_center - (pred["width"] / 2))
-            #     y = int(y_center - (pred["height"] / 2))
-            #     w = int(pred["width"])
-            #     h = int(pred["height"])
-            #     # Cropping the image to the bounding box
-            #     sub_image = img[y:y + h, x:x + w]
-            #     cv2.imwrite(f"sub_image_{idx}.jpg", sub_image)
-            #
-            #     # Extract text using OCR
-            #     text = ocr(sub_image)
-            #     texts.append(text)
-            #
-            #     # print("bbox", idx)
-            #     for object_number, text in enumerate(texts, start=1):
-            #         print("object", object_number)
-            #         # print("text", text)
-            #         ref_numbers = re.findall(ref_number_regex, text)
-            #         for ref in ref_numbers:
-            #             print("SKU:", ref)
-            #             # append 'M' before the ref number
-            #             search_query = search_url + urllib.parse.quote(ref)
-            #             if ref not in sku:
-            #                 sku.append(ref)
-            #             # if search_query not in hotspots_sku_links:
-            #                 hotspots_sku_links.append(search_query)
-            #                 hostpots.append(((x, y, x + w, y + h), ref))
-            # return (img, hostpots)
         else:
             # local inference
             results = get_yolo_predictions_local(img, confidence_threshold)
@@ -207,8 +185,6 @@ with gr.Blocks() as demo:
                     w = int(coord[2] - coord[0])
                     h = int(coord[3] - coord[1])
                     sub_image = img[y:y + h, x:x + w]
-
-
                     if shops[selected_shop]['url'] is None or shops[selected_shop]['url'] == "":
                         # just append the hotspot to hostpots
                         hostpots.append(((x, y, x + w, y + h), str(idx)))
@@ -216,110 +192,131 @@ with gr.Blocks() as demo:
 
                     # Extract text using OCR
                     text = ocr(sub_image)
-                    texts.append(text)
 
-                    for object_number, text in enumerate(texts, start=1):
-                        #print("object", object_number)
-                        #print("text", text)
+                    if selected_shop == "Latulippe":
+                        # if there is a 'i' between a "M" and a number, it is a sku. Replace the 'i' with a '1'
+                        text = re.sub(r'Mi(\d+)', r'M1\1', text)
+
+                    # for object_number, text in enumerate(texts, start=1):
+                    #print("object", object_number)
+                    print("text -----", text)
+                    ref_numbers = []
+                    if selected_shop == "Decathlon":
+                        full_match = re.search(ref_number_regex, text)
+                        if full_match:
+                            print("FULL MATCH: ", full_match)
+                            # Extracting all numbers from the captured sequence
+                            numbers_string = full_match.group(1)
+                            ref_numbers = re.findall(r'\d+', numbers_string)
+                            print("REF NUMBERS: ", ref_numbers)
+                    else:
+                        ref_numbers = re.findall(ref_number_regex, text)
+                        # print("REF NUMBERS: ", ref_numbers)
+
+                    if selected_shop == "Canadian Tire":
+                        temp_ref_numbers = ref_numbers
                         ref_numbers = []
-                        if selected_shop == "Decathlon":
-                            full_match = re.search(ref_number_regex, text)
-                            if full_match:
-                                #print("FULL MATCH: ", full_match)
-                                # Extracting all numbers from the captured sequence
-                                numbers_string = full_match.group(1)
-                                ref_numbers = re.findall(r'\d+', numbers_string)
-                        else:
-                            ref_numbers = re.findall(ref_number_regex, text)
-
-                        if selected_shop == "Canadian Tire":
-                            temp_ref_numbers = ref_numbers
-                            found_skus_new = []
-                            ref_numbers = []
-                            split = False
-                            for ref_sku in temp_ref_numbers:
-                                if '/' in ref_sku:
-                                    split = True
-                                    sku_split = ref_sku.split('/')
-                                    sku_last = sku_split[-1]
-                                    length = len(sku_last)
-                                    base_number = sku_split[0][:-length]
-                                    ref_numbers.append(sku_split[0])
-                                    # base number + sku for each sku in sku_split except the first one
-                                    for i in range(1, len(sku_split)):
-                                        ref_numbers.append(base_number + sku_split[i])
-
-                            if split == False:
-                                ref_numbers = temp_ref_numbers
-
-
-                        #print("REF NUMBERS: ", ref_numbers)
-
-                        matches = re.findall(regex_price, text)
-                        prices = []
-                        for match in matches:
-                            if match[0]:  # If the first group is not empty, the format is "price currency"
-                                prices.append(match[0] + match[1])
-                            else:  # Otherwise, the format is "currency price"
-                                prices.append(match[2] + match[3])
-                        # price = prices[0] if len(prices) > 0 else ""
-                        #print("PRICES: ", prices)
-
-                        if brands:
-                            # print("BRANDS: yes")
-                            # Extracting the product name
-                            lines = text.split('\n')
-                            product_name = ""
-                            found_brand = False
-                            name_started = False
-                            for line in lines:
-                                if any(brand in line for brand in brands):
-                                    found_brand = True
-                                    #print("FOUND BRAND", line)
+                        split = False
+                        for ref_sku in temp_ref_numbers:
+                            if '/' in ref_sku:
+                                split = True
+                                sku_split = ref_sku.split('/')
+                                sku_last = sku_split[-1]
+                                length = len(sku_last)
+                                base_number = sku_split[0][:-length]
+                                ref_numbers.append(sku_split[0])
+                                # base number + sku for each sku in sku_split except the first one
+                                for i in range(1, len(sku_split)):
+                                    ref_numbers.append(base_number + sku_split[i])
+
+                        if split == False:
+                            ref_numbers = temp_ref_numbers
+
+                    matches = re.findall(regex_price, text)
+                    prices = []
+                    for match in matches:
+                        if match[0]:  # If the first group is not empty, the format is "price currency"
+                            prices.append(match[0] + match[1])
+                        else:  # Otherwise, the format is "currency price"
+                            prices.append(match[2] + match[3])
+                    # price = prices[0] if len(prices) > 0 else ""
+                    #print("PRICES: ", prices)
+
+                    if brands:
+                        # print("BRANDS: yes")
+                        # Extracting the product name
+                        lines = text.split('\n')
+                        product_name = ""
+                        found_brand = False
+                        name_started = False
+                        for line in lines:
+                            if any(brand in line for brand in brands):
+                                found_brand = True
+                                #print("FOUND BRAND", line)
+                                continue
+                            if found_brand:
+                                #print('current line:', line)
+                                if line.strip() == "":  # Skip blank lines
                                     continue
-                                if found_brand:
-                                    #print('current line:', line)
-                                    if line.strip() == "":  # Skip blank lines
-                                        continue
-                                    if name_started and (line[0].isupper() or any(char.isdigit() for char in line)):
-                                        break
-                                    product_name += line.strip() + " "
-                                    name_started = True
-                            product_name = product_name.strip()
+                                if name_started and (line[0].isupper() or any(char.isdigit() for char in line)):
+                                    break
+                                product_name += line.strip() + " "
+                                name_started = True
+                        product_name = product_name.strip()
 
-                        else:
-                            # Regex to match sequences of uppercase letters
-                            uppercase_words = re.findall(r'\b[A-Z]+\b', text)
+                    else:
+                        # Regex to match sequences of uppercase letters
+                        uppercase_words = re.findall(r'\b[A-Z]+\b', text)
 
-                            # Joining the extracted words with a space
-                            product_name = ' '.join(uppercase_words)
+                        # Joining the extracted words with a space
+                        product_name = ' '.join(uppercase_words)
 
                         #print("PRODUCT NAME: ", product_name)
 
-                        for ref in ref_numbers:
-                            if search_google:
-                                # Use Google Search API to find items with the SKU
-                                to_seach = str(selected_shop) + ' ' + str(ref)
-                                # print("to_search: ", to_seach)
-                                request = build_request(to_seach)
-                                search_query = make_request(request)
-                                # print(f"First Result URL: {search_query}")
-                                if search_query is None:
-                                    search_query = search_url + urllib.parse.quote(ref)
-                            else:
+                    for ref in ref_numbers:
+                        print("ref", ref)
+                        if search_google:
+                            # Use Google Search API to find items with the SKU
+                            to_seach = str(selected_shop) + ' ' + str(ref)
+                            # print("to_search: ", to_seach)
+                            request = build_request(to_seach)
+                            search_query = make_request(request)
+                            # print(f"First Result URL: {search_query}")
+                            if search_query is None:
                                 search_query = search_url + urllib.parse.quote(ref)
-                            if ref not in sku:
-                                sku.append(ref)
-                                # if search_query not in hotspots_sku_links:
-                                hotspots_sku_links.append([{'sku': ref, 'url': search_query, 'prices': prices, 'product_name': product_name}])
-                                hostpots.append(((int(coord[0]), int(coord[1]), int(coord[2]), int(coord[3])), str(ref)))
-
+                        else:
+                            search_query = search_url + urllib.parse.quote(ref)
+                        if ref not in sku:
+                            sku.append(ref)
+                            # if search_query not in hotspots_sku_links:
+                            hotspots_sku_links.append([{'sku': ref, 'url': search_query, 'prices': prices, 'product_name': product_name}])
+                            hostpots.append(((int(coord[0]), int(coord[1]), int(coord[2]), int(coord[3])), str(ref)))
+
+            for data in hotspots_sku_links:
+                for item in data:
+                    product_table_data.append({
+                        'Reference Number': item['sku'],
+                        'Product Name': item['product_name'] if item['product_name'] else "Not Found",
+                        # 'Price': ", ".join(item['prices']) if item['prices'] else " ",
+                        'URL': item['url']
+                    })
+
+            # Create a DataFrame
+            product_dataframe_data = pd.DataFrame(product_table_data)
+
+            # flattern the list hotspots_sku_links
+            # hotspots_sku_links = [item for sublist in hotspots_sku_links for item in sublist]
             print("hotspots_sku_links: ", hotspots_sku_links)
+            print('length of hotspots_sku_links: ', len(hotspots_sku_links))
+            print('shape of hotspots_sku_links: ', np.shape(hotspots_sku_links))
             print("skus: ", sku)
-            return (img, hostpots)
+            print('length of skus: ', len(sku))
+            assert len(hotspots_sku_links) == len(sku)
+            return (img, hostpots), product_dataframe_data
+
 
+    section_btn.click(section, [img_input, selected_shop, confidence_threshold], [img_output, product_dataframe])
 
-    section_btn.click(section, [img_input, selected_shop, confidence_threshold], img_output)
 
 
     def select_section(evt: gr.SelectData):

app_file.py

@@ -17,8 +17,8 @@ search_google = False
 # GOOGLE_CSE_ID = "b536303d151b94476"
 # GOOGLE_API_KEY = "AIzaSyBUvPKAZa2TddKYDJI9t0ac2A_JJqdgWHo"
 # GOOGLE_CSE_ID = "f3446c60c52cd4dc2"
-GOOGLE_API_KEY = "AIzaSyCoBYZK4khX_W5eW-AqEXKOclUIer6CiC8"
-GOOGLE_CSE_ID = "c3ba01991c1a14c7d"
+# GOOGLE_API_KEY = "AIzaSyCoBYZK4khX_W5eW-AqEXKOclUIer6CiC8"
+# GOOGLE_CSE_ID = "c3ba01991c1a14c7d"
 mode = 'local'
 # mode = 'rbf'