works with decathlon and latulippe

README.md

@@ -5,7 +5,7 @@ colorFrom: yellow
 colorTo: red
 sdk: gradio
 sdk_version: 4.1.1
-app_file: app.py
+app_file: app_static.py
 pinned: false
 ---
 

app.py

@@ -30,15 +30,28 @@ shop = None
 shops = {
     'Latulippe': {
         'url': 'https://latulippe.com/fr/recherche/?keywords=',
-        'regex': r'N° (M\d+)'
+        'regex': r'N° (M\d+)',
+        'multi_items': False,
     },
     'Decathlon': {
         'url': 'https://www.decathlon.fr/search?Ntt=',
-        'regex': r'Réf\. ?: ?([\d, ]+)'
+        'regex': r'Réf\. ?: ?([\d, ]+)',
+        'multi_items': True,
+        'brands': [
+            "Allsix", "Aptonia", "Artengo", "Atorka", "B'Twin", "Caperlan", "Domyos", "Dreamscape",
+            "FLX", "Forclaz", "Fouganza", "Geologic", "Geonaute", "Inesis", "Imviso", "Inovik",
+            "Itiwit", "KOODZA", "KOROK", "Kalenji", "Kimjaly", "Kipsta", "Kuikma", "Nabaiji",
+            "Newfeel", "Offload", "Olaian", "Opfeel", "Orao", "Oroks", "Outshock", "Oxelo",
+            "Perfly", "Pongori", "Quechua", "Rockrider", "Sandever", "Simond", "Solognac",
+            "Subea", "Tarmak", "Triban", "Tribord", "Urball", "Van Rysel", "Wed'Ze", "Decathlon"
+        ]
     },
     # Add more shops and their respective information here
 }
 
+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.")
@@ -100,10 +113,13 @@ with gr.Blocks() as demo:
         texts = []
         sku = []
 
-        print("selected_shop:", selected_shop)
+        #print("selected_shop:", selected_shop)
         search_url = shops[selected_shop]['url']
         ref_number_regex = shops[selected_shop]['regex']
-        print("search_url:", search_url)
+        # 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)
@@ -158,16 +174,62 @@ with gr.Blocks() as demo:
                     text = ocr(sub_image)
                     texts.append(text)
                     for object_number, text in enumerate(texts, start=1):
-                        print("object", object_number)
-                        print("text", text)
-                        # ref_numbers = re.findall(ref_number_regex, text)
-                        full_match = re.search(ref_number_regex, text)
+                        #print("object", object_number)
+                        #print("text", text)
                         ref_numbers = []
-                        if 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)
+                        if shops[selected_shop]['multi_items']:
+                            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)
+
+                        #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)
+                                    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()
+
+                        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)
+
+                        #print("PRODUCT NAME: ", product_name)
+
                         for ref in ref_numbers:
                             # print("SKU:", ref)
                             # append 'M' before the ref number
@@ -175,7 +237,7 @@ with gr.Blocks() as demo:
                             if ref not in sku:
                                 sku.append(ref)
                                 # if search_query not in hotspots_sku_links:
-                                hotspots_sku_links.append(search_query)
+                                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)))
             print("hotspots_sku_links: ", hotspots_sku_links)
             print("skus: ", sku)
@@ -185,13 +247,24 @@ with gr.Blocks() as demo:
 
     section_btn.click(section, [img_input, selected_shop], img_output)
 
+
     # def select_section(evt: gr.SelectData):
-    #     return hotspots_sku_links[evt.index]
+    #     # Format the URL as a Markdown link
+    #     url = hotspots_sku_links[evt.index]
+    #     return f"[Click here to visit the selected hotspot's link]({url})"
 
     def select_section(evt: gr.SelectData):
-        # Format the URL as a Markdown link
-        url = hotspots_sku_links[evt.index]
-        return f"[Click here to visit the selected hotspot's link]({url})"
+        hotspot_data = hotspots_sku_links[evt.index]
+        markdown_output = ""
+        for data in hotspot_data:
+            url = data['url']
+            price_str = ", ".join(data['prices']) if data['prices'] else "No price found"
+            product_name = data['product_name'] if data['product_name'] else "No product name found"
+            if product_name != "No product name found":
+                markdown_output += f"[{product_name}]({url}): {price_str}\n\n"
+            else:
+                markdown_output += f"[SKU: {data['sku']}]({url}): {price_str}\n\n"
+        return markdown_output
 
     img_output.select(select_section, None, selected_section)
 

test.py

@@ -1,17 +1,15 @@
 import re
 
-text = "Réf. : 8403098, 8403427, 8403427, 8403427"
+text = """
+This is some SAMPLE text.
+It INCLUDES some LINES
+with UPPER CASE words.
+"""
 
-# Regex to capture the entire sequence after "Réf. :"
-full_regex = r'Réf\. ?: ?([\d, ]+)'
+# Regex to match sequences of uppercase letters
+uppercase_words = re.findall(r'\b[A-Z]+\b', text)
 
-# Find the entire sequence
-full_match = re.search(full_regex, text)
+# Joining the extracted words with a space
+result = ' '.join(uppercase_words)
 
-ref_numbers = []
-if 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)  # This will correctly print: ['8403098', '8403427']
+print(result)  # This will print: SAMPLE INCLUDES LINES UPPER CASE