Merge pull request #852 from maherp24/week1_day2

day2_webpage_summarizer

week1/community-contributions/day2_ollama_webpage_summarizer_bs4.ipynb

@@ -0,0 +1,157 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "33314df1",
+   "metadata": {},
+   "source": [
+    "# Webpage Summarizer with Ollama\n",
+    "\n",
+    "Scrape any webpage and get a quick summary using Ollama 3.2.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "64917274",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Cell 1: Setup and Dependencies\n",
+    "import requests\n",
+    "from bs4 import BeautifulSoup\n",
+    "import ollama\n",
+    "\n",
+    "# Check if Ollama is running\n",
+    "try:\n",
+    "    ollama.list()\n",
+    "    print(\"✓ Ollama is running!\")\n",
+    "except Exception as e:\n",
+    "    print(\"⚠ Warning: Can't connect to Ollama. Make sure it's running!\")\n",
+    "    print(\"  Run 'ollama serve' in your terminal if needed.\")\n",
+    "\n",
+    "print(\"\\nReady to summarize webpages!\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "981ff805",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Cell 2: Set URL to scrape\n",
+    "# Change this URL to whatever webpage you want to summarize\n",
+    "url = \"https://github.com/maherp24\"\n",
+    "\n",
+    "print(f\"Will summarize: {url}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a45d7c1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "try:\n",
+    "    # Get the webpage\n",
+    "    response = requests.get(url, timeout=10)\n",
+    "    response.raise_for_status()\n",
+    "    \n",
+    "    print(\"✓ Webpage fetched!\")\n",
+    "    \n",
+    "    # Parse HTML\n",
+    "    soup = BeautifulSoup(response.content, 'html.parser')\n",
+    "    \n",
+    "    # Extract text from paragraphs\n",
+    "    paragraphs = soup.find_all('p')\n",
+    "    text = ' '.join([p.get_text() for p in paragraphs])\n",
+    "    \n",
+    "    # Clean up whitespace\n",
+    "    text = ' '.join(text.split())\n",
+    "    \n",
+    "    # Limit to 4000 characters to avoid token issues\n",
+    "    if len(text) > 4000:\n",
+    "        text = text[:4000]\n",
+    "        print(f\"✓ Extracted {len(text)} characters (truncated to 4000)\")\n",
+    "    else:\n",
+    "        print(f\"✓ Extracted {len(text)} characters\")\n",
+    "    \n",
+    "    print(f\"\\nFirst 200 characters:\\n{text[:200]}...\")\n",
+    "    \n",
+    "except Exception as e:\n",
+    "    print(f\"❌ Error scraping webpage: {e}\")\n",
+    "    text = None\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "66ea2618",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Cell 4: Summarize with Ollama\n",
+    "if text:\n",
+    "    print(\"\\nGenerating summary with Ollama...\")\n",
+    "    print(\"This might take a few seconds...\\n\")\n",
+    "    \n",
+    "    try:\n",
+    "        # Call Ollama\n",
+    "        response = ollama.chat(\n",
+    "            model='llama3.2',\n",
+    "            messages=[{\n",
+    "                'role': 'user',\n",
+    "                'content': f'Summarize this webpage content in 3-5 sentences:\\n\\n{text}'\n",
+    "            }]\n",
+    "        )\n",
+    "        \n",
+    "        summary = response['message']['content']\n",
+    "        \n",
+    "        print(\"=\" * 60)\n",
+    "        print(\"SUMMARY\")\n",
+    "        print(\"=\" * 60)\n",
+    "        print(summary)\n",
+    "        print(\"=\" * 60)\n",
+    "        \n",
+    "    except Exception as e:\n",
+    "        print(f\"❌ Error with Ollama: {e}\")\n",
+    "        print(\"\\nMake sure:\")\n",
+    "        print(\"  1. Ollama is running ('ollama serve')\")\n",
+    "        print(\"  2. llama3.2 model is installed ('ollama pull llama3.2')\")\n",
+    "else:\n",
+    "    print(\"No text to summarize (scraping failed)\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d78d1ee1",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}