image text extraction completed

2024-08-08 14:58:44 +01:00
parent 9a2a4c5fdd
commit c54dc17989
13 changed files with 331 additions and 7 deletions
@@ -0,0 +1,161 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -q pdfplumber"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from text_extractor import TextExtractor\n",
+    "from langchain_core.documents  import Document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# creating a function to extract texts from image\n",
+    "def create_image_document(image_path):\n",
+    "    # getting the image name from the image path\n",
+    "    image_name = image_path.split('/')[-1].split('.')[0]\n",
+    "    # setting image name as metadata\n",
+    "    metadata = {'filename': image_name}\n",
+    "    text_extractor = TextExtractor()\n",
+    "    text = text_extractor.read_text_from_image(image_path)\n",
+    "    # removing special characters and line breaks\n",
+    "    text = ''.join(e for e in text if e.isalnum() or e.isspace() or e == '\\n')\n",
+    "    doc = Document(page_content=text, metadata=metadata)\n",
+    "    # returning the document\n",
+    "    return [doc]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[Document(metadata={'filename': 'IMG_1438'}, page_content='ex   a\\n\\nAccidented car before repair\\n')]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# testing the function\n",
+    "image_path = 'data/IMG_1438.jpeg'\n",
+    "text = create_image_document(image_path)\n",
+    "print(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'filename': 'IMG_1438'}"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "text[0].metadata"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "smog_env",
+   "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": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}