adding example for PDF to image conversion in a notebook

examples/convert_pdf_to_images.ipynb

@@ -0,0 +1,174 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cc9d9bf6-9da8-4676-b8f9-2813c59df9f4",
+   "metadata": {},
+   "source": [
+    "# PDF to image conversion utility\n",
+    "\n",
+    "This notebook provides a utility function to convert PDF files into images using the `pdf2image` library.\n",
+    "\n",
+    "## Installation instructions\n",
+    "\n",
+    "Before running this notebook, you need to install some dependencies. Run the following commands in your terminal based on your operating system:\n",
+    "\n",
+    "### For Linux (Ubuntu/Debian):\n",
+    "```bash\n",
+    "sudo apt-get update\n",
+    "sudo apt-get install poppler-utils\n",
+    "```\n",
+    "\n",
+    "### For MacOS:\n",
+    "```bash\n",
+    "brew install poppler\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "efce81109fdba0b3",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-16T02:45:34.764142Z",
+     "start_time": "2024-09-16T02:45:33.616190Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: pdf2image in /Users/sim/Projects/litepali/venv/lib/python3.11/site-packages (1.17.0)\r\n",
+      "Requirement already satisfied: pillow in /Users/sim/Projects/litepali/venv/lib/python3.11/site-packages (from pdf2image) (10.4.0)\r\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install pdf2image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "16ae2110e9aa484e",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-16T02:45:38.554681Z",
+     "start_time": "2024-09-16T02:45:38.360640Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import multiprocessing\n",
+    "from pdf2image import convert_from_path"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "22bcd30911bc84c9",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-16T02:45:40.706663Z",
+     "start_time": "2024-09-16T02:45:40.701061Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "def convert_pdf_to_images(pdf_path, output_folder, dpi=300, thread_count=None):\n",
+    "    \"\"\"\n",
+    "    Convert a PDF file to a series of images.\n",
+    "    \n",
+    "    :param pdf_path: Path to the PDF file\n",
+    "    :param output_folder: Folder to save the output images\n",
+    "    :param dpi: DPI for the output images (default: 300)\n",
+    "    :param thread_count: Number of threads to use (default: auto-detect)\n",
+    "    \"\"\"\n",
+    "    # Create output folder if it doesn't exist\n",
+    "    os.makedirs(output_folder, exist_ok=True)\n",
+    "    \n",
+    "    # Auto-discover thread count if not provided\n",
+    "    if thread_count is None:\n",
+    "        thread_count = multiprocessing.cpu_count()\n",
+    "    \n",
+    "    # Convert PDF to images\n",
+    "    images = convert_from_path(\n",
+    "        pdf_path,\n",
+    "        dpi=dpi,\n",
+    "        thread_count=thread_count\n",
+    "    )\n",
+    "    \n",
+    "    # Save images\n",
+    "    for i, image in enumerate(images):\n",
+    "        image_path = os.path.join(output_folder, f'page_{i+1}.png')\n",
+    "        image.save(image_path, 'PNG')\n",
+    "    \n",
+    "    print(f\"Converted {len(images)} pages to images in {output_folder}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "379872a03498e63c",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-16T02:48:17.482166Z",
+     "start_time": "2024-09-16T02:48:17.476042Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Adapt your paths\n",
+    "pdf_path = 'input.pdf'\n",
+    "output_folder = 'results'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "61b78ee6f9514596",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-16T02:49:36.632924Z",
+     "start_time": "2024-09-16T02:48:21.096150Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Converted 218 pages to images in results\n"
+     ]
+    }
+   ],
+   "source": [
+    "convert_pdf_to_images(pdf_path, output_folder)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": 5
+}