Spaces:
No application file
No application file
Commit ·
d4c60fd
1
Parent(s): 672ed4a
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,390 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import urllib
|
| 2 |
+
|
| 3 |
+
import pandas as pd
|
| 4 |
+
import numpy as np
|
| 5 |
+
from pdf2image import convert_from_path
|
| 6 |
+
import cv2
|
| 7 |
+
import pytesseract
|
| 8 |
+
import requests
|
| 9 |
+
import os
|
| 10 |
+
import json
|
| 11 |
+
from PIL import Image
|
| 12 |
+
import re
|
| 13 |
+
from roboflow import Roboflow
|
| 14 |
+
import gradio as gr
|
| 15 |
+
|
| 16 |
+
rf = Roboflow(api_key="TN586SQsdwjUUvMN3H8e")
|
| 17 |
+
project = rf.workspace().project("smartflyers")
|
| 18 |
+
model = project.version(9).model
|
| 19 |
+
|
| 20 |
+
# Define shops with their respective search URL and reference number regex
|
| 21 |
+
shops = {
|
| 22 |
+
'Latulippe': {
|
| 23 |
+
'url': 'https://latulippe.com/fr/recherche/?keywords=',
|
| 24 |
+
'regex': r'N° (\w+)'
|
| 25 |
+
},
|
| 26 |
+
'Decathlon': {
|
| 27 |
+
'url': 'https://www.decathlon.fr/search?Ntt=',
|
| 28 |
+
'regex': r'Réf. : (\d+)'
|
| 29 |
+
},
|
| 30 |
+
'Metro' : {
|
| 31 |
+
'url': 'https://www.metro.ca/en/online-grocery/search?filter=',
|
| 32 |
+
'regex': r'(\d{6})'
|
| 33 |
+
},
|
| 34 |
+
'Walmart' : {
|
| 35 |
+
'url': 'https://www.walmart.ca/search?q=',
|
| 36 |
+
'regex': r'(\d{6})'
|
| 37 |
+
},
|
| 38 |
+
'Canadian Tire' : {
|
| 39 |
+
'url': 'https://www.canadiantire.ca/en/search-results.html?q=',
|
| 40 |
+
'regex': r'(\d{6})'
|
| 41 |
+
},
|
| 42 |
+
'Rona' : {
|
| 43 |
+
'url': 'https://www.rona.ca/en/search?searchType=product&q=',
|
| 44 |
+
'regex': r'(\d{6})'
|
| 45 |
+
},
|
| 46 |
+
'Home Depot' : {
|
| 47 |
+
'url': 'https://www.homedepot.ca/en/home/search.html?q=',
|
| 48 |
+
'regex': r'(\d{6})'
|
| 49 |
+
},
|
| 50 |
+
'BMR' : {
|
| 51 |
+
'url': 'https://www.bmr.co/fr/recherche.html?q=',
|
| 52 |
+
'regex': r'(\d{6})'
|
| 53 |
+
},
|
| 54 |
+
'Reno Depot' : {
|
| 55 |
+
'url': 'https://www.renodepot.com/en/search#?q=',
|
| 56 |
+
'regex': r'(\d{6})'
|
| 57 |
+
},
|
| 58 |
+
'Maxi' : {
|
| 59 |
+
'url': 'https://www.maxi.ca/search?search-bar=',
|
| 60 |
+
'regex': r'(\d{6})'
|
| 61 |
+
},
|
| 62 |
+
'Super C' : {
|
| 63 |
+
'url': 'https://www.superc.ca/search?search-bar=',
|
| 64 |
+
'regex': r'(\d{6})'
|
| 65 |
+
},
|
| 66 |
+
'Provigo' : {
|
| 67 |
+
'url': 'https://www.provigo.ca/search?search-bar=',
|
| 68 |
+
'regex': r'(\d{6})'
|
| 69 |
+
},
|
| 70 |
+
'IGA' : {
|
| 71 |
+
'url': 'https://www.iga.net/en/search?t={14A91276-40BA-49D5-940D-3692DE3DC381}&k=',
|
| 72 |
+
'regex': r'(\d{6})'
|
| 73 |
+
},
|
| 74 |
+
'Jean Coutu' : {
|
| 75 |
+
'url': 'https://www.jeancoutu.com/recherche?searchTerm=',
|
| 76 |
+
'regex': r'(\d{6})'
|
| 77 |
+
},
|
| 78 |
+
'Pharmaprix' : {
|
| 79 |
+
'url': 'https://www1.pharmaprix.ca/search?search-bar=',
|
| 80 |
+
'regex': r'(\d{6})'
|
| 81 |
+
},
|
| 82 |
+
'Uniprix' : {
|
| 83 |
+
'url': 'https://www.uniprix.com/en/search?search-bar=',
|
| 84 |
+
'regex': r'(\d{6})'
|
| 85 |
+
},
|
| 86 |
+
'Familiprix' : {
|
| 87 |
+
'url': 'https://www.familiprix.com/en/search?search-bar=',
|
| 88 |
+
'regex': r'(\d{6})'
|
| 89 |
+
},
|
| 90 |
+
'SAQ' : {
|
| 91 |
+
'url': 'https://www.saq.com/en/search?search-bar=',
|
| 92 |
+
'regex': r'(\d{6})'
|
| 93 |
+
},
|
| 94 |
+
'Dollarama' : {
|
| 95 |
+
'url': 'https://www.dollarama.com/en-CA/search?text=',
|
| 96 |
+
'regex': r'(\d{6})'
|
| 97 |
+
},
|
| 98 |
+
'Canac' : {
|
| 99 |
+
'url': 'https://www.canac.ca/en/search?search-bar=',
|
| 100 |
+
'regex': r'(\d{6})'
|
| 101 |
+
},
|
| 102 |
+
'Patrick Morin' : {
|
| 103 |
+
'url': 'https://www.patrickmorin.com/en/search?search-bar=',
|
| 104 |
+
'regex': r'(\d{6})'
|
| 105 |
+
},
|
| 106 |
+
'Gagnon La Grande Quincaillerie' : {
|
| 107 |
+
'url': 'https://www.gagnonfreres.com/en/search?search-bar=',
|
| 108 |
+
'regex': r'(\d{6})'
|
| 109 |
+
},
|
| 110 |
+
'Tanguay' : {
|
| 111 |
+
'url': 'https://www.tanguay.ca/en/search?search-bar=',
|
| 112 |
+
'regex': r'(\d{6})'
|
| 113 |
+
},
|
| 114 |
+
'The Source' : {
|
| 115 |
+
'url': 'https://www.thesource.ca/en-ca/search?text=',
|
| 116 |
+
'regex': r'(\d{6})'
|
| 117 |
+
},
|
| 118 |
+
'Best Buy' : {
|
| 119 |
+
'url': 'https://www.bestbuy.ca/en-ca/search?search=',
|
| 120 |
+
'regex': r'(\d{6})'
|
| 121 |
+
},
|
| 122 |
+
'Staples' : {
|
| 123 |
+
'url': 'https://www.staples.ca/search?query=',
|
| 124 |
+
'regex': r'(\d{6})'
|
| 125 |
+
},
|
| 126 |
+
'Bureau en Gros' : {
|
| 127 |
+
'url': 'https://www.staples.ca/search?query=',
|
| 128 |
+
'regex': r'(\d{6})'
|
| 129 |
+
},
|
| 130 |
+
'Centre Hi-Fi' : {
|
| 131 |
+
'url': 'https://www.centrehifi.com/en/search?search-bar=',
|
| 132 |
+
'regex': r'(\d{6})'
|
| 133 |
+
},
|
| 134 |
+
'Stokes' : {
|
| 135 |
+
'url': 'https://www.stokesstores.com/en/search?search-bar=',
|
| 136 |
+
'regex': r'(\d{6})'
|
| 137 |
+
},
|
| 138 |
+
'RD Furniture' : {
|
| 139 |
+
'url': 'https://www.raymond.ca/en/search?search-bar=',
|
| 140 |
+
'regex': r'(\d{6})'
|
| 141 |
+
},
|
| 142 |
+
'Go Sport' : {
|
| 143 |
+
'url': 'https://www.gosport.ca/en/search?search-bar=',
|
| 144 |
+
'regex': r'(\d{6})'
|
| 145 |
+
},
|
| 146 |
+
'Sports Experts' : {
|
| 147 |
+
'url': 'https://www.sportsexperts.ca/en-CA/search?search-bar=',
|
| 148 |
+
'regex': r'(\d{6})'
|
| 149 |
+
},
|
| 150 |
+
'Atmosphere' : {
|
| 151 |
+
'url': 'https://www.atmosphere.ca/search?search-bar=',
|
| 152 |
+
'regex': r'(\d{6})'
|
| 153 |
+
},
|
| 154 |
+
'SAIL' : {
|
| 155 |
+
'url': 'https://www.sail.ca/en/search?search-bar=',
|
| 156 |
+
'regex': r'(\d{6})'
|
| 157 |
+
},
|
| 158 |
+
'MEC' : {
|
| 159 |
+
'url': 'https://www.mec.ca/en/search?text=',
|
| 160 |
+
'regex': r'(\d{6})'
|
| 161 |
+
},
|
| 162 |
+
'Toys R Us' : {
|
| 163 |
+
'url': 'https://www.toysrus.ca/en/search?search-bar=',
|
| 164 |
+
'regex': r'(\d{6})'
|
| 165 |
+
},
|
| 166 |
+
# Add more shops and their respective information here
|
| 167 |
+
}
|
| 168 |
+
|
| 169 |
+
def pdf_to_images(pdf_path):
|
| 170 |
+
images = convert_from_path(pdf_path)
|
| 171 |
+
return [cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR) for img in images]
|
| 172 |
+
|
| 173 |
+
|
| 174 |
+
def get_yolo_predictions(image):
|
| 175 |
+
# Convert image to suitable format if required
|
| 176 |
+
# Use Roboflow API to get predictions
|
| 177 |
+
predictions = model.predict(image, confidence=0.20, overlap=50).json()
|
| 178 |
+
return predictions
|
| 179 |
+
|
| 180 |
+
def display_bbox_and_extract_text(image, predictions, page_number):
|
| 181 |
+
texts = [] # Store OCR text for each bbox
|
| 182 |
+
labeled_image = image.copy() # Copy the image to draw labels on it
|
| 183 |
+
font = cv2.FONT_HERSHEY_SIMPLEX
|
| 184 |
+
font_scale = 1 # Adjust the scale according to your image
|
| 185 |
+
color = (255, 255, 255) # White color for text
|
| 186 |
+
bg_color = (0, 0, 0) # Black background for text for visibility
|
| 187 |
+
thickness = 10 # Thickness of the bbox outline
|
| 188 |
+
text_thickness = 3 # Thickness of the font
|
| 189 |
+
|
| 190 |
+
for idx, pred in enumerate(predictions["predictions"]):
|
| 191 |
+
x_center = int(pred["x"])
|
| 192 |
+
y_center = int(pred["y"])
|
| 193 |
+
x = int(x_center - (pred["width"] / 2))
|
| 194 |
+
y = int(y_center - (pred["height"] / 2))
|
| 195 |
+
w = int(pred["width"])
|
| 196 |
+
h = int(pred["height"])
|
| 197 |
+
|
| 198 |
+
# Cropping the image to the bounding box
|
| 199 |
+
sub_image = image[y:y + h, x:x + w]
|
| 200 |
+
|
| 201 |
+
# Extract text using OCR
|
| 202 |
+
text = ocr(sub_image)
|
| 203 |
+
texts.append(text)
|
| 204 |
+
|
| 205 |
+
# Draw the bounding box on the image
|
| 206 |
+
start_point = (x, y)
|
| 207 |
+
end_point = (x + w, y + h)
|
| 208 |
+
bbox_color = (0, 255, 0) # Green color in BGR for bbox
|
| 209 |
+
labeled_image = cv2.rectangle(labeled_image, start_point, end_point, bbox_color, thickness)
|
| 210 |
+
|
| 211 |
+
# Put the label number near the bounding box with background for visibility
|
| 212 |
+
label_text = str(idx + 1)
|
| 213 |
+
label_size = cv2.getTextSize(label_text, font, font_scale, text_thickness)[0]
|
| 214 |
+
label_position = (x, y + label_size[1] + 10) if y > label_size[1] else (x, y + label_size[1] + 20)
|
| 215 |
+
|
| 216 |
+
# Draw background rectangle for text
|
| 217 |
+
label_bg_start = (label_position[0], label_position[1] - label_size[1] - 10)
|
| 218 |
+
label_bg_end = (label_position[0] + label_size[0], label_position[1] + 10)
|
| 219 |
+
labeled_image = cv2.rectangle(labeled_image, label_bg_start, label_bg_end, bg_color, -1)
|
| 220 |
+
|
| 221 |
+
# Put the label number on the image
|
| 222 |
+
labeled_image = cv2.putText(labeled_image, label_text, label_position, font, font_scale, color, text_thickness)
|
| 223 |
+
|
| 224 |
+
# Draw the page number on the image
|
| 225 |
+
page_text = f"Page {page_number}"
|
| 226 |
+
page_text_size = cv2.getTextSize(page_text, font, font_scale, text_thickness)[0]
|
| 227 |
+
page_text_position = (image.shape[1] - page_text_size[0] - 20, page_text_size[1] + 20) # top-right corner
|
| 228 |
+
col = (0, 0, 0) # Black color in BGR for page number
|
| 229 |
+
labeled_image = cv2.putText(labeled_image, page_text, page_text_position, font, font_scale, col, text_thickness)
|
| 230 |
+
|
| 231 |
+
# Convert the labeled image from BGR to RGB for display
|
| 232 |
+
labeled_image = cv2.cvtColor(labeled_image, cv2.COLOR_BGR2RGB)
|
| 233 |
+
return labeled_image, texts
|
| 234 |
+
|
| 235 |
+
|
| 236 |
+
def extract_reference_number(text):
|
| 237 |
+
# Look for "N°" followed by the reference number pattern
|
| 238 |
+
match = re.search(r'N°\s*([A-Za-z0-9]+)', text)
|
| 239 |
+
if match:
|
| 240 |
+
# Return the found reference number
|
| 241 |
+
return match.group(1)
|
| 242 |
+
else:
|
| 243 |
+
# Return None if no reference number is found
|
| 244 |
+
return None
|
| 245 |
+
|
| 246 |
+
def ocr(sub_image):
|
| 247 |
+
# Use OCR to get text from image
|
| 248 |
+
text = pytesseract.image_to_string(sub_image, lang='eng')
|
| 249 |
+
return text
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
# Set up your Google API key and Custom Search Engine ID
|
| 253 |
+
GOOGLE_API_KEY = 'AIzaSyCD5eIu3N2uD6Vf5GE0VLBpkPsJ3mEZgA0'
|
| 254 |
+
GOOGLE_CSE_ID = '32784ecc8a6bd4fad'
|
| 255 |
+
|
| 256 |
+
|
| 257 |
+
def search_google(query):
|
| 258 |
+
search_url = "https://www.googleapis.com/customsearch/v1"
|
| 259 |
+
params = {
|
| 260 |
+
'q': query,
|
| 261 |
+
'key': GOOGLE_API_KEY,
|
| 262 |
+
'cx': GOOGLE_CSE_ID,
|
| 263 |
+
'num': 1 # Number of search results to return
|
| 264 |
+
}
|
| 265 |
+
|
| 266 |
+
response = requests.get(search_url, params=params)
|
| 267 |
+
search_results = response.json()
|
| 268 |
+
print(json.dumps(search_results, indent=2))
|
| 269 |
+
|
| 270 |
+
# Extract the first search result URL
|
| 271 |
+
url = search_results['items'][0]['link'] if 'items' in search_results else None
|
| 272 |
+
return url
|
| 273 |
+
|
| 274 |
+
def search_latulippe(query):
|
| 275 |
+
# URLEncode the query to ensure it is HTTP-compliant.
|
| 276 |
+
encoded_query = urllib.parse.quote(query)
|
| 277 |
+
# Construct the search URL.
|
| 278 |
+
search_url = f"https://latulippe.com/fr/recherche/?keywords={encoded_query}"
|
| 279 |
+
return search_url
|
| 280 |
+
|
| 281 |
+
|
| 282 |
+
def create_search_url(shop_url, query):
|
| 283 |
+
# URLEncode the query to ensure it is HTTP-compliant.
|
| 284 |
+
encoded_query = urllib.parse.quote(query)
|
| 285 |
+
# Construct the search URL.
|
| 286 |
+
if '{}' in shop_url:
|
| 287 |
+
# The user provided a format string with a placeholder for the query
|
| 288 |
+
search_url = shop_url.format(encoded_query)
|
| 289 |
+
else:
|
| 290 |
+
# Append the query to the base URL
|
| 291 |
+
search_url = f"{shop_url}{encoded_query}"
|
| 292 |
+
return search_url
|
| 293 |
+
|
| 294 |
+
|
| 295 |
+
def clean_search_query(text):
|
| 296 |
+
# Add "Latulippe" to the beginning
|
| 297 |
+
text = "Latulippe " + text
|
| 298 |
+
# Keep only the first sentence by finding the first period followed by a space or the end of the text
|
| 299 |
+
first_sentence = re.split(r'(?<=[.!?]) +', text, maxsplit=1)[0]
|
| 300 |
+
# Convert to lowercase
|
| 301 |
+
first_sentence = first_sentence.lower()
|
| 302 |
+
# Replace newline characters with spaces
|
| 303 |
+
first_sentence = first_sentence.replace("\n", " ")
|
| 304 |
+
# Remove special characters except for basic punctuation
|
| 305 |
+
first_sentence = re.sub(r'[^a-z0-9\s,.]', '', first_sentence)
|
| 306 |
+
# Optionally, remove multiple consecutive spaces
|
| 307 |
+
first_sentence = re.sub(r'\s+', ' ', first_sentence).strip()
|
| 308 |
+
return first_sentence
|
| 309 |
+
|
| 310 |
+
# Function to create a table from the extracted data
|
| 311 |
+
def create_table(data):
|
| 312 |
+
# Assuming data is a list of tuples or lists with the following format:
|
| 313 |
+
# [(page_number, object_number, reference_code, url), (...), ...]
|
| 314 |
+
headers = ["Page", "Object", "Reference Code", "URL"]
|
| 315 |
+
# Convert URL to a clickable link
|
| 316 |
+
processed_data = []
|
| 317 |
+
for row in data:
|
| 318 |
+
clickable_link = f'<a href="{row[3]}" target="_blank">{row[3]}</a>'
|
| 319 |
+
processed_data.concat((row[0], row[1], row[2], clickable_link))
|
| 320 |
+
return gr.Dataframe(headers=headers, values=processed_data)
|
| 321 |
+
|
| 322 |
+
def app(pdf_path, selected_shop):
|
| 323 |
+
if pdf_path is None:
|
| 324 |
+
raise gr.Error("No file uploaded. Please upload a PDF file.")
|
| 325 |
+
|
| 326 |
+
# Check if the uploaded file is a PDF
|
| 327 |
+
if not pdf_path.name.lower().endswith('.pdf'):
|
| 328 |
+
raise gr.Error("Invalid file format. Please upload a PDF file.")
|
| 329 |
+
|
| 330 |
+
if selected_shop is None:
|
| 331 |
+
raise gr.Error("Please select a shop.")
|
| 332 |
+
|
| 333 |
+
# Retrieve the selected shop's information
|
| 334 |
+
search_url = shops[selected_shop]['url']
|
| 335 |
+
ref_number_regex = shops[selected_shop]['regex']
|
| 336 |
+
table = pd.DataFrame(columns=["Page", "Object", "Reference", "URL"])
|
| 337 |
+
images = pdf_to_images(pdf_path)
|
| 338 |
+
output_images = []
|
| 339 |
+
all_urls = []
|
| 340 |
+
|
| 341 |
+
# Process the PDF and generate outputs if no errors are found
|
| 342 |
+
try:
|
| 343 |
+
images = pdf_to_images(pdf_path)
|
| 344 |
+
for page_number, img in enumerate(images, start=1):
|
| 345 |
+
predictions = get_yolo_predictions(img)
|
| 346 |
+
img_with_bbox, texts = display_bbox_and_extract_text(img, predictions, page_number)
|
| 347 |
+
output_images.append(img_with_bbox)
|
| 348 |
+
|
| 349 |
+
# Extract reference numbers using regex and generate search URLs
|
| 350 |
+
#for text in texts:
|
| 351 |
+
for object_number, text in enumerate(texts, start=1):
|
| 352 |
+
ref_numbers = re.findall(ref_number_regex, text)
|
| 353 |
+
for ref in ref_numbers:
|
| 354 |
+
search_query = search_url + urllib.parse.quote(ref)
|
| 355 |
+
# all_urls.append({'page': page_number, 'object':object_number, 'reference': ref, 'url': search_query})
|
| 356 |
+
new_row = pd.Series({
|
| 357 |
+
"Page": page_number,
|
| 358 |
+
"Object": object_number,
|
| 359 |
+
"Reference": ref,
|
| 360 |
+
"URL": search_query
|
| 361 |
+
})
|
| 362 |
+
table = pd.concat([table, pd.DataFrame([new_row])], ignore_index=True)
|
| 363 |
+
|
| 364 |
+
table_html = table.to_html(escape=False, index=False)
|
| 365 |
+
pass
|
| 366 |
+
except Exception as e:
|
| 367 |
+
return gr.Error(f"An error occurred: {str(e)}")
|
| 368 |
+
|
| 369 |
+
return output_images, table_html
|
| 370 |
+
|
| 371 |
+
|
| 372 |
+
|
| 373 |
+
# Gradio interface definition
|
| 374 |
+
iface = gr.Interface(
|
| 375 |
+
fn=app,
|
| 376 |
+
inputs=[
|
| 377 |
+
gr.File(label="Upload PDF"), # Specify that you expect a file
|
| 378 |
+
gr.Dropdown(choices=list(shops.keys()), label="Select Shop")
|
| 379 |
+
],
|
| 380 |
+
outputs=[
|
| 381 |
+
gr.Gallery(label="Processed Images"), # Output for gallery
|
| 382 |
+
gr.HTML(label="Extracted Information") # Output for table
|
| 383 |
+
],
|
| 384 |
+
title="Automated Hotspotting",
|
| 385 |
+
description="Here is a demo of an automated hotspotting tool. Upload a PDF file and select the correponding shop to get started.",
|
| 386 |
+
#allow_flagging="never"
|
| 387 |
+
)
|
| 388 |
+
|
| 389 |
+
iface.launch(share=False)
|
| 390 |
+
|