Spaces:
Sleeping
Sleeping
File size: 19,724 Bytes
25b98b6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import PyPDF2, os\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def read_pdf(path):\n",
" pdf_file = open(path, 'rb')\n",
" pdf_reader = PyPDF2.PdfReader(pdf_file)\n",
" text = ''\n",
" for page_num in range(len(pdf_reader.pages)):\n",
" page = pdf_reader.pages[page_num]\n",
" text += page.extract_text()\n",
" pdf_file.close()\n",
" return text\n",
"\n",
"invoices = []\n",
"path = 'invoices/'\n",
"\n",
"for file in os.listdir(path):\n",
" if file.startswith('invoice'):\n",
" text = read_pdf(path + file)\n",
" print(text)\n",
" invoices.append(text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"def save_as_csv(details, save_as = \"invoice.csv\"):\n",
" # if the csv already exists then concat a new one to it, else create a new one\n",
" if os.path.exists(save_as):\n",
" df = pd.read_csv(save_as)\n",
" df = pd.concat([df, pd.DataFrame(details, index=[0])], ignore_index=True)\n",
" else: \n",
" df = pd.DataFrame(details, index=[0])\n",
" df.to_csv(save_as, index=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import re\n",
"\n",
"def extract_invoice_details(text):\n",
" invoice_details = {}\n",
" try:\n",
" invoice_details['Order Number'] = re.search(r'Order Number: (\\S+)', text).group(1)\n",
" invoice_details['Invoice Number'] = re.search(r'Invoice Number : (\\S+)', text).group(1)\n",
" invoice_details['Order Date'] = re.search(r'Order Date: (\\d{2}\\.\\d{2}\\.\\d{4})', text).group(1)\n",
" invoice_details['Invoice Details'] = re.search(r'Invoice Details : (\\S+)', text).group(1)\n",
" invoice_details['Invoice Date'] = re.search(r'Invoice Date : (\\d{2}\\.\\d{2}\\.\\d{4})', text).group(1)\n",
" invoice_details['Billing Address'] = re.search(r'Billing Address :([\\s\\S]+?)Shipping Address :', text).group(1).strip()\n",
" invoice_details['Shipping Address'] = re.search(r'Shipping Address :([\\s\\S]+?)Place of supply:', text).group(1).strip()\n",
" invoice_details['PAN'] = re.search(r'PAN No:(\\S+)', text).group(1)\n",
" except:\n",
" print('Order Number not found')\n",
" \n",
" item_match = re.search(r'1([\\s\\S]+?)TOTAL:', text, re.DOTALL)\n",
" if item_match:\n",
" item_info = item_match.group(1)\n",
" item_name = re.search(r'\\nAmount\\n1([\\s\\S]+?)₹', item_info).group(1).strip()\n",
" invoice_details['Item'] = item_name\n",
" print(item_name)\n",
" else:\n",
" print(\"No item found in the invoice.\")\n",
" total_mount_match = re.search(r'TOTAL:([\\s\\S]+?)only', text, re.DOTALL)\n",
" if total_mount_match:\n",
" total_mount = total_mount_match.group(1).split('₹')[2].split('\\n')[0]\n",
" invoice_details['Total Amount'] = total_mount\n",
" else:\n",
" print(\"No total amount found in the invoice.\")\n",
" gstin_match = re.search(r'GST Registration No: ([\\s\\S]+?) ', text)\n",
" if gstin_match:\n",
" invoice_details['GSTIN'] = gstin_match.group(1).strip()\n",
" else:\n",
" print(\"No GSTIN found in the invoice.\")\n",
" by_match = re.search(r'By :([\\s\\S]+?)PAN No:', text)\n",
" if by_match:\n",
" invoice_details['Sold By'] = by_match.group(1).strip()\n",
" else:\n",
" print(\"No seller found in the invoice.\")\n",
" \n",
" return invoice_details"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"for invoice in invoices:\n",
" # print(invoice)\n",
" details = extract_invoice_details(invoice)\n",
" save_as_csv(details)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('invoice.csv')\n",
"df.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"import PyPDF2, os, re\n",
"import pandas as pd\n",
"\n",
"class InvoiceConvertor:\n",
" \"\"\"\n",
" This class is hardcoded to read all pdf files that start with 'invoice' in the given user given path and convert them to a csv file.\n",
" \n",
" Usage:\n",
" convertor = InvoiceConvertor()\n",
" convertor.read_pdfs('path_to_pdfs')\n",
" result_df = convertor.convert()\n",
"\n",
" \"\"\"\n",
" def __init__(self):\n",
" self.invoices = []\n",
" \n",
" def read_pdfs(self,path):\n",
" for file in os.listdir(path):\n",
" if file.startswith('invoice'):\n",
" pdf_file = open(path + file, 'rb')\n",
" pdf_reader = PyPDF2.PdfReader(pdf_file)\n",
" text = ''\n",
" for page_num in range(len(pdf_reader.pages)):\n",
" page = pdf_reader.pages[page_num]\n",
" text += page.extract_text()\n",
" pdf_file.close()\n",
" self.invoices.append(text)\n",
" return self.invoices\n",
" \n",
" def save_as_csv(self, details, save_as = \"invoice.csv\"):\n",
" # if the csv already exists then concat a new one to it, else create a new one\n",
" if os.path.exists(save_as):\n",
" df = pd.read_csv(save_as)\n",
" df = pd.concat([df, pd.DataFrame(details, index=[0])], ignore_index=True)\n",
" else: \n",
" df = pd.DataFrame(details, index=[0])\n",
" df.to_csv(save_as, index=False)\n",
" \n",
" def extract_invoice_details(self, text):\n",
" invoice_details = {}\n",
" try:\n",
" invoice_details['Order Number'] = re.search(r'Order Number: (\\S+)', text).group(1)\n",
" invoice_details['Invoice Number'] = re.search(r'Invoice Number : (\\S+)', text).group(1)\n",
" invoice_details['Order Date'] = re.search(r'Order Date: (\\d{2}\\.\\d{2}\\.\\d{4})', text).group(1)\n",
" invoice_details['Invoice Details'] = re.search(r'Invoice Details : (\\S+)', text).group(1)\n",
" invoice_details['Invoice Date'] = re.search(r'Invoice Date : (\\d{2}\\.\\d{2}\\.\\d{4})', text).group(1)\n",
" invoice_details['Billing Address'] = re.search(r'Billing Address :([\\s\\S]+?)Shipping Address :', text).group(1).strip()\n",
" invoice_details['Shipping Address'] = re.search(r'Shipping Address :([\\s\\S]+?)Place of supply:', text).group(1).strip()\n",
" invoice_details['PAN'] = re.search(r'PAN No:(\\S+)', text).group(1)\n",
" except:\n",
" print('Order Number not found')\n",
"\n",
" item_match = re.search(r'1([\\s\\S]+?)TOTAL:', text, re.DOTALL)\n",
" if item_match:\n",
" item_info = item_match.group(1)\n",
" item_name = re.search(r'\\nAmount\\n1([\\s\\S]+?)₹', item_info).group(1).strip()\n",
" invoice_details['Item'] = item_name\n",
" # print(item_name)\n",
" else:\n",
" print(\"No item found in the invoice.\")\n",
" total_mount_match = re.search(r'TOTAL:([\\s\\S]+?)only', text, re.DOTALL)\n",
" if total_mount_match:\n",
" total_mount = total_mount_match.group(1).split('₹')[2].split('\\n')[0]\n",
" invoice_details['Total Amount'] = total_mount\n",
" else:\n",
" print(\"No total amount found in the invoice.\")\n",
" gstin_match = re.search(r'GST Registration No: ([\\s\\S]+?) ', text)\n",
" if gstin_match:\n",
" invoice_details['GSTIN'] = gstin_match.group(1).strip()\n",
" else:\n",
" print(\"No GSTIN found in the invoice.\")\n",
" by_match = re.search(r'By :([\\s\\S]+?)PAN No:', text)\n",
" if by_match:\n",
" invoice_details['Sold By'] = by_match.group(1).strip()\n",
" else:\n",
" print(\"No seller found in the invoice.\")\n",
" return invoice_details\n",
" \n",
" def convert(self):\n",
" for invoice in self.invoices:\n",
" details = self.extract_invoice_details(invoice)\n",
" self.save_as_csv(details)\n",
" return pd.read_csv('invoice.csv')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Order Number not found\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Order Number</th>\n",
" <th>Invoice Number</th>\n",
" <th>Order Date</th>\n",
" <th>Invoice Details</th>\n",
" <th>Invoice Date</th>\n",
" <th>Billing Address</th>\n",
" <th>Shipping Address</th>\n",
" <th>PAN</th>\n",
" <th>Item</th>\n",
" <th>Total Amount</th>\n",
" <th>GSTIN</th>\n",
" <th>Sold By</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>402-7035529-3886722</td>\n",
" <td>NAG1-192347</td>\n",
" <td>17.08.2023</td>\n",
" <td>MH-NAG1-1034-2324</td>\n",
" <td>17.08.2023</td>\n",
" <td>Pratik Dwivedi \\nBennett University, Plot Nos ...</td>\n",
" <td>Pratik Dwivedi \\nPratik Dwivedi \\nBennett Univ...</td>\n",
" <td>AALCA0171E</td>\n",
" <td>Cosmic Byte CB-EP-05 Wired Gaming in Ear Earph...</td>\n",
" <td>458.0</td>\n",
" <td>27AALCA0171E1ZZ</td>\n",
" <td>Appario Retail Private Ltd \\n*TCI Supply Chain...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>402-7035529-3886722</td>\n",
" <td>BOM5-1379800</td>\n",
" <td>17.08.2023</td>\n",
" <td>MH-BOM5-1034-2324</td>\n",
" <td>17.08.2023</td>\n",
" <td>Pratik Dwivedi \\nBennett University, Plot Nos ...</td>\n",
" <td>Pratik Dwivedi \\nPratik Dwivedi \\nBennett Univ...</td>\n",
" <td>AALCA0171E</td>\n",
" <td>LG Ultragear IPS Gaming Monitor 60 cm (24\\nInc...</td>\n",
" <td>13,099.00</td>\n",
" <td>27AALCA0171E1ZZ</td>\n",
" <td>Appario Retail Private Ltd \\n*Renaissance indu...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>405-4419941-9848328</td>\n",
" <td>DEX3-4683</td>\n",
" <td>23.07.2023</td>\n",
" <td>DL-DEX3-157533501-2324</td>\n",
" <td>23.07.2023</td>\n",
" <td>Pratik Dwivedi \\nC- 123 Sector 26, Sector 26 N...</td>\n",
" <td>Pratik Dwivedi \\nPratik Dwivedi \\nC- 123 Secto...</td>\n",
" <td>ABEPW6057C</td>\n",
" <td>Amozo Easy Fit Tempered Glass Screen Protector...</td>\n",
" <td>474.00</td>\n",
" <td>07ABEPW6057C1ZK</td>\n",
" <td>RADHIKA WALIA \\n*Plot no 28, Block A, Mohan Co...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>405-4419941-9848328</td>\n",
" <td>HYD8-29019</td>\n",
" <td>23.07.2023</td>\n",
" <td>TG-HYD8-817549015-2324</td>\n",
" <td>23.07.2023</td>\n",
" <td>Pratik Dwivedi \\nC- 123 Sector 26, Sector 26 N...</td>\n",
" <td>Pratik Dwivedi \\nPratik Dwivedi \\nC- 123 Secto...</td>\n",
" <td>AACCN8253B</td>\n",
" <td>ESR for iPhone 13/14 Cover, Shockproof Drop Pr...</td>\n",
" <td>399.00</td>\n",
" <td>36AACCN8253B1ZN</td>\n",
" <td>TIGER PUG COMMERCE PRIVATE LIMITED \\n*GMR Airp...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>405-0015964-5687515</td>\n",
" <td>IN-5040</td>\n",
" <td>23.07.2023</td>\n",
" <td>DL-1922955505-2324</td>\n",
" <td>23.07.2023</td>\n",
" <td>Pratik Dwivedi \\nC- 123 Sector 26, Sector 26 N...</td>\n",
" <td>Pratik Dwivedi \\nPratik Dwivedi \\nC- 123 Secto...</td>\n",
" <td>JISPS4412R</td>\n",
" <td>imluckies Camera Lens Protector Compatible wit...</td>\n",
" <td>149.00</td>\n",
" <td>07JISPS4412R1Z4</td>\n",
" <td>M.A.ENTERPRISES \\n*D2/235 GALI NO 6, 3rd PUSTA...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>408-4974466-7793143</td>\n",
" <td>JPX2-223775</td>\n",
" <td>02.01.2024</td>\n",
" <td>RJ-JPX2-1317922175-2324</td>\n",
" <td>02.01.2024</td>\n",
" <td>Devpal \\n514/3, Ganesh vihar \\nROORKEE, UTTARA...</td>\n",
" <td>Devpal \\nDevpal \\n514/3, Ganesh vihar \\nROORKE...</td>\n",
" <td>AADCV4254H</td>\n",
" <td>Amazon Basics Sleek Rechargeable LED Table Lam...</td>\n",
" <td>569.00</td>\n",
" <td>08AADCV4254H1Z8</td>\n",
" <td>ETRADE MARKETING PRIVATE LIMITED \\n*Kh No 554 ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>Saregama Carvaan Telugu - Portable Music Playe...</td>\n",
" <td>6,320.00</td>\n",
" <td>36AARCA3925C1ZQBilling</td>\n",
" <td>AATS Connect Private Limited \\n* GMR Airport C...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Order Number Invoice Number Order Date Invoice Details \\\n",
"0 402-7035529-3886722 NAG1-192347 17.08.2023 MH-NAG1-1034-2324 \n",
"1 402-7035529-3886722 BOM5-1379800 17.08.2023 MH-BOM5-1034-2324 \n",
"2 405-4419941-9848328 DEX3-4683 23.07.2023 DL-DEX3-157533501-2324 \n",
"3 405-4419941-9848328 HYD8-29019 23.07.2023 TG-HYD8-817549015-2324 \n",
"4 405-0015964-5687515 IN-5040 23.07.2023 DL-1922955505-2324 \n",
"5 408-4974466-7793143 JPX2-223775 02.01.2024 RJ-JPX2-1317922175-2324 \n",
"6 NaN NaN NaN NaN \n",
"\n",
" Invoice Date Billing Address \\\n",
"0 17.08.2023 Pratik Dwivedi \\nBennett University, Plot Nos ... \n",
"1 17.08.2023 Pratik Dwivedi \\nBennett University, Plot Nos ... \n",
"2 23.07.2023 Pratik Dwivedi \\nC- 123 Sector 26, Sector 26 N... \n",
"3 23.07.2023 Pratik Dwivedi \\nC- 123 Sector 26, Sector 26 N... \n",
"4 23.07.2023 Pratik Dwivedi \\nC- 123 Sector 26, Sector 26 N... \n",
"5 02.01.2024 Devpal \\n514/3, Ganesh vihar \\nROORKEE, UTTARA... \n",
"6 NaN NaN \n",
"\n",
" Shipping Address PAN \\\n",
"0 Pratik Dwivedi \\nPratik Dwivedi \\nBennett Univ... AALCA0171E \n",
"1 Pratik Dwivedi \\nPratik Dwivedi \\nBennett Univ... AALCA0171E \n",
"2 Pratik Dwivedi \\nPratik Dwivedi \\nC- 123 Secto... ABEPW6057C \n",
"3 Pratik Dwivedi \\nPratik Dwivedi \\nC- 123 Secto... AACCN8253B \n",
"4 Pratik Dwivedi \\nPratik Dwivedi \\nC- 123 Secto... JISPS4412R \n",
"5 Devpal \\nDevpal \\n514/3, Ganesh vihar \\nROORKE... AADCV4254H \n",
"6 NaN NaN \n",
"\n",
" Item Total Amount \\\n",
"0 Cosmic Byte CB-EP-05 Wired Gaming in Ear Earph... 458.0 \n",
"1 LG Ultragear IPS Gaming Monitor 60 cm (24\\nInc... 13,099.00 \n",
"2 Amozo Easy Fit Tempered Glass Screen Protector... 474.00 \n",
"3 ESR for iPhone 13/14 Cover, Shockproof Drop Pr... 399.00 \n",
"4 imluckies Camera Lens Protector Compatible wit... 149.00 \n",
"5 Amazon Basics Sleek Rechargeable LED Table Lam... 569.00 \n",
"6 Saregama Carvaan Telugu - Portable Music Playe... 6,320.00 \n",
"\n",
" GSTIN Sold By \n",
"0 27AALCA0171E1ZZ Appario Retail Private Ltd \\n*TCI Supply Chain... \n",
"1 27AALCA0171E1ZZ Appario Retail Private Ltd \\n*Renaissance indu... \n",
"2 07ABEPW6057C1ZK RADHIKA WALIA \\n*Plot no 28, Block A, Mohan Co... \n",
"3 36AACCN8253B1ZN TIGER PUG COMMERCE PRIVATE LIMITED \\n*GMR Airp... \n",
"4 07JISPS4412R1Z4 M.A.ENTERPRISES \\n*D2/235 GALI NO 6, 3rd PUSTA... \n",
"5 08AADCV4254H1Z8 ETRADE MARKETING PRIVATE LIMITED \\n*Kh No 554 ... \n",
"6 36AARCA3925C1ZQBilling AATS Connect Private Limited \\n* GMR Airport C... "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"invoice_convertor = InvoiceConvertor()\n",
"invoice_convertor.read_pdfs('invoices/')\n",
"res = invoice_convertor.convert()\n",
"res.head(10)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "resparser",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|