add ai-analyzer and location-utils

2025-07-03 21:41:56 -04:00 · 2025-07-03 21:41:56 -04:00 · b62854909b
commit b62854909b
parent ae22315c59
10 changed files with 2510 additions and 186 deletions
--- a/.gitignore
+++ b/.gitignore
@ -1,9 +1,10 @@
+.vscode/
+*.md
+!README.md
 node_modules/
 .env
 results/
-linkedout.exe
-linkedout-macos
 zip*
 *.7z
 *obfuscated.js
-.history
+.history
--- a/README.md
+++ b/README.md
@ -0,0 +1,247 @@
+# LinkedOut - LinkedIn Posts Scraper
+
+A Node.js application that automates LinkedIn login and scrapes posts containing specific keywords. The tool is designed to help track job market trends, layoffs, and open work opportunities by monitoring LinkedIn content.
+
+## Features
+
+- **Automated LinkedIn Login**: Uses Playwright to automate browser interactions
+- **Keyword-based Search**: Searches for posts containing keywords from CSV files or CLI
+- **Flexible Keyword Sources**: Supports multiple CSV files in `keywords/` or CLI-only mode
+- **Configurable Search Parameters**: Customizable date ranges, sorting options, city, and scroll behavior
+- **Duplicate Detection**: Prevents duplicate posts and profiles in results
+- **Clean Text Processing**: Removes hashtags, emojis, and URLs from post content
+- **Timestamped Results**: Saves results to JSON files with timestamps
+- **Command-line Overrides**: Support for runtime parameter adjustments
+- **Enhanced Geographic Location Validation**: Validates user locations against 200+ Canadian cities with smart matching
+- **Local AI Analysis (Ollama)**: Free, private, and fast post-processing with local LLMs
+- **Flexible Processing**: Disable features, run AI analysis immediately, or process results later
+
+## Prerequisites
+
+- Node.js (v14 or higher)
+- Valid LinkedIn account credentials
+- [Ollama](https://ollama.ai/) with a model (free, private, local AI)
+
+## Installation
+
+1. Clone the repository or download the files
+2. Install dependencies:
+
+   ```bash
+   npm install
+   ```
+
+3. Copy the configuration template and customize:
+
+   ```bash
+   cp env-config.example .env
+   ```
+
+4. Edit `.env` with your settings (see Configuration section below)
+
+## Configuration
+
+### Environment Variables (.env file)
+
+Create a `.env` file from `env-config.example`:
+
+```env
+# LinkedIn Credentials (Required)
+LINKEDIN_USERNAME=your_email@example.com
+LINKEDIN_PASSWORD=your_password
+
+# Basic Settings
+HEADLESS=true
+KEYWORDS=keywords-layoff.csv   # Just the filename; always looks in keywords/ unless path is given
+DATE_POSTED=past-week
+SORT_BY=date_posted
+CITY=Toronto
+WHEELS=5
+
+# Enhanced Location Filtering
+LOCATION_FILTER=Ontario,Manitoba
+ENABLE_LOCATION_CHECK=true
+
+# Local AI Analysis (Ollama)
+ENABLE_LOCAL_AI=true
+OLLAMA_MODEL=mistral
+OLLAMA_HOST=http://localhost:11434
+RUN_LOCAL_AI_AFTER_SCRAPING=false  # true = run after scraping, false = run manually
+AI_CONTEXT=job layoffs and workforce reduction
+AI_CONFIDENCE=0.7
+AI_BATCH_SIZE=3
+```
+
+### Configuration Options
+
+#### Required
+
+- `LINKEDIN_USERNAME`: Your LinkedIn email/username
+- `LINKEDIN_PASSWORD`: Your LinkedIn password
+
+#### Basic Settings
+
+- `HEADLESS`: Browser headless mode (`true`/`false`, default: `true`)
+- `KEYWORDS`: CSV file name (default: `keywords-layoff.csv` in `keywords/` folder)
+- `DATE_POSTED`: Filter by date (`past-24h`, `past-week`, `past-month`, or empty)
+- `SORT_BY`: Sort results (`relevance` or `date_posted`)
+- `CITY`: Search location (default: `Toronto`)
+- `WHEELS`: Number of scrolls to load posts (default: `5`)
+
+#### Enhanced Location Filtering
+
+- `LOCATION_FILTER`: Geographic filter - supports multiple provinces/cities:
+  - Single: `Ontario` or `Toronto`
+  - Multiple: `Ontario,Manitoba` or `Toronto,Vancouver`
+- `ENABLE_LOCATION_CHECK`: Enable location validation (`true`/`false`)
+
+#### Local AI Analysis (Ollama)
+
+- `ENABLE_LOCAL_AI=true`: Enable local AI analysis
+- `OLLAMA_MODEL`: Model to use (`mistral`, `llama2`, `codellama`)
+- `OLLAMA_HOST`: Ollama server URL (default: `http://localhost:11434`)
+- `RUN_LOCAL_AI_AFTER_SCRAPING`: Run AI immediately after scraping (`true`/`false`)
+- `AI_CONTEXT`: Context for analysis (e.g., `job layoffs`)
+- `AI_CONFIDENCE`: Minimum confidence threshold (0.0-1.0, default: 0.7)
+- `AI_BATCH_SIZE`: Posts per batch (default: 3)
+
+## Usage
+
+### Basic Commands
+
+```bash
+# Standard scraping with configured settings
+node linkedout.js
+
+# Visual mode (see browser)
+node linkedout.js --headless=false
+
+# Use only these keywords (ignore CSV)
+node linkedout.js --keyword="layoff,downsizing"
+
+# Add extra keywords to CSV/CLI list
+node linkedout.js --add-keyword="hiring freeze,open to work"
+
+# Override city and date
+node linkedout.js --city="Vancouver" --date_posted=past-month
+
+# Custom output file
+node linkedout.js --output=results/myfile.json
+
+# Skip location and AI filtering (fastest)
+node linkedout.js --no-location --no-ai
+
+# Run AI analysis immediately after scraping
+node linkedout.js --ai-after
+
+# Show help
+node linkedout.js --help
+```
+
+### All Command-line Options
+
+- `--headless=true|false`: Override browser headless mode
+- `--keyword="kw1,kw2"`: Use only these keywords (comma-separated, overrides CSV)
+- `--add-keyword="kw1,kw2"`: Add extra keywords to CSV/CLI list
+- `--city="CityName"`: Override city
+- `--date_posted=VALUE`: Override date posted (past-24h, past-week, past-month, or empty)
+- `--sort_by=VALUE`: Override sort by (date_posted or relevance)
+- `--location_filter=VALUE`: Override location filter
+- `--output=FILE`: Output file name
+- `--no-location`: Disable location filtering
+- `--no-ai`: Disable AI analysis
+- `--ai-after`: Run local AI analysis after scraping
+- `--help, -h`: Show help message
+
+### Keyword Files
+
+- Place all keyword CSVs in the `keywords/` folder
+- Example: `keywords/keywords-layoff.csv`, `keywords/keywords-open-work.csv`
+- Custom CSV format: header `keyword` with one keyword per line
+
+### Local AI Analysis Commands
+
+After scraping, you can run AI analysis on the results:
+
+```bash
+# Analyze latest results
+node ai-analyzer-local.js --context="job layoffs"
+
+# Analyze specific file
+node ai-analyzer-local.js --input=results/results-2024-01-15.json --context="hiring"
+
+# Use different model
+node ai-analyzer-local.js --model=llama2 --context="remote work"
+
+# Change confidence and batch size
+node ai-analyzer-local.js --context="job layoffs" --confidence=0.8 --batch-size=5
+```
+
+## Workflow Examples
+
+### 1. Quick Start (All Features)
+
+```bash
+node linkedout.js --ai-after
+```
+
+### 2. Fast Scraping Only
+
+```bash
+node linkedout.js --no-location --no-ai
+```
+
+### 3. Location-Only Filtering
+
+```bash
+node linkedout.js --no-ai
+```
+
+### 4. Test Different AI Contexts
+
+```bash
+node linkedout.js --no-ai
+node ai-analyzer-local.js --context="job layoffs"
+node ai-analyzer-local.js --context="hiring opportunities"
+node ai-analyzer-local.js --context="remote work"
+```
+
+## Project Structure
+
+```
+linkedout/
+├── .env                     # Your configuration (create from template)
+├── env-config.example       # Configuration template
+├── linkedout.js             # Main scraper
+├── ai-analyzer-local.js     # Free local AI analyzer (Ollama)
+├── location-utils.js        # Enhanced location utilities
+├── package.json             # Dependencies
+├── keywords/                # All keyword CSVs go here
+│   ├── keywords-layoff.csv
+│   └── keywords-open-work.csv
+├── results/                 # Output directory
+└── README.md                # This documentation
+```
+
+## Legal & Security
+
+- **Credentials**: Store securely in `.env`, add to `.gitignore`
+- **LinkedIn ToS**: Respect rate limits and usage guidelines
+- **Privacy**: Local AI keeps all data on your machine
+- **Usage**: Educational and research purposes only
+
+## Dependencies
+
+- `playwright`: Browser automation
+- `dotenv`: Environment variables
+- `csv-parser`: CSV file reading
+- Built-in: `fs`, `path`, `child_process`
+
+## Support
+
+For issues:
+
+1. Check this README
+2. Verify `.env` configuration
+3. Test with `--headless=false` for debugging
+4. Check Ollama status: `ollama list`
--- a/ai-analyzer-local.js
+++ b/ai-analyzer-local.js
@ -0,0 +1,540 @@
+#!/usr/bin/env node
+
+/**
+ * Local AI Post-Processing Analyzer for LinkedOut
+ *
+ * Uses Ollama for completely FREE local AI analysis.
+ *
+ * FEATURES:
+ *   - Analyze LinkedOut results for context relevance (layoffs, hiring, etc.)
+ *   - Works on latest or specified results file
+ *   - Batch processing for speed
+ *   - Configurable context, model, confidence, batch size
+ *   - CLI and .env configuration
+ *   - 100% local, private, and free
+ *
+ * USAGE:
+ *   node ai-analyzer-local.js [options]
+ *
+ * COMMAND-LINE OPTIONS:
+ *   --input=<file>       Input JSON file (default: latest in results/)
+ *   --context=<text>     AI context to analyze against (required)
+ *   --confidence=<num>   Minimum confidence threshold (0.0-1.0, default: 0.7)
+ *   --model=<name>       Ollama model to use (default: llama2)
+ *   --batch-size=<num>   Number of posts to process at once (default: 3)
+ *   --output=<file>      Output file (default: adds -ai-local suffix)
+ *   --help, -h           Show this help message
+ *
+ * EXAMPLES:
+ *   node ai-analyzer-local.js --context="job layoffs"
+ *   node ai-analyzer-local.js --input=results/results-2024-01-15.json --context="hiring"
+ *   node ai-analyzer-local.js --model=mistral --context="remote work"
+ *   node ai-analyzer-local.js --context="job layoffs" --confidence=0.8 --batch-size=5
+ *
+ * ENVIRONMENT VARIABLES (.env file):
+ *   AI_CONTEXT, AI_CONFIDENCE, AI_BATCH_SIZE, OLLAMA_MODEL, OLLAMA_HOST
+ *   See README for full list.
+ *
+ * OUTPUT:
+ *   - Saves to results/ with -ai-local suffix unless --output is specified
+ *
+ * DEPENDENCIES:
+ *   - Ollama (https://ollama.ai/)
+ *   - Node.js built-ins: fs, path, fetch
+ *
+ * SECURITY & LEGAL:
+ *   - All analysis is local, no data leaves your machine
+ *   - Use responsibly for educational/research purposes
+ */
+
+require("dotenv").config();
+const fs = require("fs");
+const path = require("path");
+
+// Configuration from environment and command line
+const DEFAULT_CONTEXT =
+  process.env.AI_CONTEXT || "job layoffs and workforce reduction";
+const DEFAULT_CONFIDENCE = parseFloat(process.env.AI_CONFIDENCE || "0.7");
+const DEFAULT_BATCH_SIZE = parseInt(process.env.AI_BATCH_SIZE || "3");
+const DEFAULT_MODEL = process.env.OLLAMA_MODEL || "llama2";
+const OLLAMA_HOST = process.env.OLLAMA_HOST || "http://localhost:11434";
+
+// Parse command line arguments
+const args = process.argv.slice(2);
+let inputFile = null;
+let context = DEFAULT_CONTEXT;
+let confidenceThreshold = DEFAULT_CONFIDENCE;
+let batchSize = DEFAULT_BATCH_SIZE;
+let model = DEFAULT_MODEL;
+let outputFile = null;
+
+for (const arg of args) {
+  if (arg.startsWith("--input=")) {
+    inputFile = arg.split("=")[1];
+  } else if (arg.startsWith("--context=")) {
+    context = arg.split("=")[1];
+  } else if (arg.startsWith("--confidence=")) {
+    confidenceThreshold = parseFloat(arg.split("=")[1]);
+  } else if (arg.startsWith("--batch-size=")) {
+    batchSize = parseInt(arg.split("=")[1]);
+  } else if (arg.startsWith("--model=")) {
+    model = arg.split("=")[1];
+  } else if (arg.startsWith("--output=")) {
+    outputFile = arg.split("=")[1];
+  }
+}
+
+if (!context) {
+  console.error("❌ Error: No AI context specified");
+  console.error('Use --context="your context" or set AI_CONTEXT in .env');
+  process.exit(1);
+}
+
+/**
+ * Check if Ollama is running and the model is available
+ */
+async function checkOllamaStatus() {
+  try {
+    // Check if Ollama is running
+    const response = await fetch(`${OLLAMA_HOST}/api/tags`);
+    if (!response.ok) {
+      throw new Error(`Ollama not running on ${OLLAMA_HOST}`);
+    }
+
+    const data = await response.json();
+    const availableModels = data.models.map((m) => m.name);
+
+    console.log(`🤖 Ollama is running`);
+    console.log(
+      `📦 Available models: ${availableModels
+        .map((m) => m.split(":")[0])
+        .join(", ")}`
+    );
+
+    // Check if requested model is available
+    const modelExists = availableModels.some((m) => m.startsWith(model));
+    if (!modelExists) {
+      console.error(`❌ Model "${model}" not found`);
+      console.error(`💡 Install it with: ollama pull ${model}`);
+      console.error(
+        `💡 Or choose from: ${availableModels
+          .map((m) => m.split(":")[0])
+          .join(", ")}`
+      );
+      process.exit(1);
+    }
+
+    console.log(`✅ Using model: ${model}`);
+    return true;
+  } catch (error) {
+    console.error("❌ Error connecting to Ollama:", error.message);
+    console.error("💡 Make sure Ollama is installed and running:");
+    console.error("   1. Install: https://ollama.ai/");
+    console.error("   2. Start: ollama serve");
+    console.error(`   3. Install model: ollama pull ${model}`);
+    process.exit(1);
+  }
+}
+
+/**
+ * Find the most recent results file if none specified
+ */
+function findLatestResultsFile() {
+  const resultsDir = "results";
+  if (!fs.existsSync(resultsDir)) {
+    throw new Error("Results directory not found. Run the scraper first.");
+  }
+
+  const files = fs
+    .readdirSync(resultsDir)
+    .filter(
+      (f) =>
+        f.startsWith("results-") && f.endsWith(".json") && !f.includes("-ai-")
+    )
+    .sort()
+    .reverse();
+
+  if (files.length === 0) {
+    throw new Error("No results files found. Run the scraper first.");
+  }
+
+  return path.join(resultsDir, files[0]);
+}
+
+/**
+ * Analyze multiple posts using local Ollama
+ */
+async function analyzeBatch(posts, context, model) {
+  console.log(`🤖 Analyzing batch of ${posts.length} posts with ${model}...`);
+
+  try {
+    const prompt = `You are an expert at analyzing LinkedIn posts for relevance to specific contexts.
+
+CONTEXT TO MATCH: "${context}"
+
+Analyze these ${
+      posts.length
+    } LinkedIn posts and determine if each relates to the context above.
+
+POSTS:
+${posts
+  .map(
+    (post, i) => `
+POST ${i + 1}:
+"${post.text.substring(0, 400)}${post.text.length > 400 ? "..." : ""}"
+`
+  )
+  .join("")}
+
+For each post, provide:
+- Is it relevant to "${context}"? (YES/NO)
+- Confidence level (0.0 to 1.0)
+- Brief reasoning
+
+Respond in this EXACT format for each post:
+POST 1: YES/NO | 0.X | brief reason
+POST 2: YES/NO | 0.X | brief reason
+POST 3: YES/NO | 0.X | brief reason
+
+Examples:
+- For layoff context: "laid off 50 employees" = YES | 0.9 | mentions layoffs
+- For hiring context: "we're hiring developers" = YES | 0.8 | job posting
+- Unrelated content = NO | 0.1 | not relevant to context`;
+
+    const response = await fetch(`${OLLAMA_HOST}/api/generate`, {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+      },
+      body: JSON.stringify({
+        model: model,
+        prompt: prompt,
+        stream: false,
+        options: {
+          temperature: 0.3,
+          top_p: 0.9,
+        },
+      }),
+    });
+
+    if (!response.ok) {
+      throw new Error(
+        `Ollama API error: ${response.status} ${response.statusText}`
+      );
+    }
+
+    const data = await response.json();
+    const aiResponse = data.response.trim();
+
+    // Parse the response
+    const analyses = [];
+    const lines = aiResponse.split("\n").filter((line) => line.trim());
+
+    for (let i = 0; i < posts.length; i++) {
+      let analysis = {
+        postIndex: i + 1,
+        isRelevant: false,
+        confidence: 0.5,
+        reasoning: "Could not parse AI response",
+      };
+
+      // Look for lines that match "POST X:" pattern
+      const postPattern = new RegExp(`POST\\s*${i + 1}:?\\s*(.+)`, "i");
+
+      for (const line of lines) {
+        const match = line.match(postPattern);
+        if (match) {
+          const content = match[1].trim();
+
+          // Parse: YES/NO | 0.X | reasoning
+          const parts = content.split("|").map((p) => p.trim());
+
+          if (parts.length >= 3) {
+            analysis.isRelevant = parts[0].toUpperCase().includes("YES");
+            analysis.confidence = Math.max(
+              0,
+              Math.min(1, parseFloat(parts[1]) || 0.5)
+            );
+            analysis.reasoning = parts[2] || "No reasoning provided";
+          } else {
+            // Fallback parsing
+            analysis.isRelevant =
+              content.toUpperCase().includes("YES") ||
+              content.toLowerCase().includes("relevant");
+            analysis.confidence = 0.6;
+            analysis.reasoning = content.substring(0, 100);
+          }
+          break;
+        }
+      }
+
+      analyses.push(analysis);
+    }
+
+    // If we didn't get enough analyses, fill in defaults
+    while (analyses.length < posts.length) {
+      analyses.push({
+        postIndex: analyses.length + 1,
+        isRelevant: false,
+        confidence: 0.3,
+        reasoning: "AI response parsing failed",
+      });
+    }
+
+    return analyses;
+  } catch (error) {
+    console.error(`❌ Error in batch AI analysis: ${error.message}`);
+
+    // Fallback: mark all as relevant with low confidence
+    return posts.map((_, i) => ({
+      postIndex: i + 1,
+      isRelevant: true,
+      confidence: 0.3,
+      reasoning: `Analysis failed: ${error.message}`,
+    }));
+  }
+}
+
+/**
+ * Analyze a single post using local Ollama (fallback)
+ */
+async function analyzeSinglePost(text, context, model) {
+  const prompt = `Analyze this LinkedIn post for relevance to: "${context}"
+
+Post: "${text}"
+
+Is this post relevant to "${context}"? Provide:
+1. YES or NO
+2. Confidence (0.0 to 1.0)  
+3. Brief reason
+
+Format: YES/NO | 0.X | reason`;
+
+  try {
+    const response = await fetch(`${OLLAMA_HOST}/api/generate`, {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+      },
+      body: JSON.stringify({
+        model: model,
+        prompt: prompt,
+        stream: false,
+        options: {
+          temperature: 0.3,
+        },
+      }),
+    });
+
+    if (!response.ok) {
+      throw new Error(`Ollama API error: ${response.status}`);
+    }
+
+    const data = await response.json();
+    const aiResponse = data.response.trim();
+
+    // Parse response
+    const parts = aiResponse.split("|").map((p) => p.trim());
+
+    if (parts.length >= 3) {
+      return {
+        isRelevant: parts[0].toUpperCase().includes("YES"),
+        confidence: Math.max(0, Math.min(1, parseFloat(parts[1]) || 0.5)),
+        reasoning: parts[2],
+      };
+    } else {
+      // Fallback parsing
+      return {
+        isRelevant:
+          aiResponse.toLowerCase().includes("yes") ||
+          aiResponse.toLowerCase().includes("relevant"),
+        confidence: 0.6,
+        reasoning: aiResponse.substring(0, 100),
+      };
+    }
+  } catch (error) {
+    return {
+      isRelevant: true, // Default to include on error
+      confidence: 0.3,
+      reasoning: `Analysis failed: ${error.message}`,
+    };
+  }
+}
+
+/**
+ * Main processing function
+ */
+async function main() {
+  try {
+    console.log("🚀 LinkedOut Local AI Analyzer Starting...");
+    console.log(`📊 Context: "${context}"`);
+    console.log(`🎯 Confidence Threshold: ${confidenceThreshold}`);
+    console.log(`📦 Batch Size: ${batchSize}`);
+    console.log(`🤖 Model: ${model}`);
+
+    // Check Ollama status
+    await checkOllamaStatus();
+
+    // Determine input file
+    if (!inputFile) {
+      inputFile = findLatestResultsFile();
+      console.log(`📂 Using latest results file: ${inputFile}`);
+    } else {
+      console.log(`📂 Using specified file: ${inputFile}`);
+    }
+
+    // Load results
+    if (!fs.existsSync(inputFile)) {
+      throw new Error(`Input file not found: ${inputFile}`);
+    }
+
+    const rawData = fs.readFileSync(inputFile, "utf-8");
+    const results = JSON.parse(rawData);
+
+    if (!Array.isArray(results) || results.length === 0) {
+      throw new Error("No posts found in input file");
+    }
+
+    console.log(`📋 Loaded ${results.length} posts for analysis`);
+
+    // Process in batches
+    const processedResults = [];
+    let totalRelevant = 0;
+    let totalProcessed = 0;
+
+    for (let i = 0; i < results.length; i += batchSize) {
+      const batch = results.slice(i, i + batchSize);
+      console.log(
+        `\n📦 Processing batch ${Math.floor(i / batchSize) + 1}/${Math.ceil(
+          results.length / batchSize
+        )} (${batch.length} posts)`
+      );
+
+      const analyses = await analyzeBatch(batch, context, model);
+
+      // Apply analyses to posts
+      for (let j = 0; j < batch.length; j++) {
+        const post = batch[j];
+        const analysis = analyses[j];
+
+        const enhancedPost = {
+          ...post,
+          aiRelevant: analysis.isRelevant,
+          aiConfidence: analysis.confidence,
+          aiReasoning: analysis.reasoning,
+          aiModel: model,
+          aiAnalyzedAt: new Date().toLocaleString("en-CA", {
+            year: "numeric",
+            month: "2-digit",
+            day: "2-digit",
+            hour: "2-digit",
+            minute: "2-digit",
+            second: "2-digit",
+            hour12: false,
+          }),
+          aiType: "local-ollama",
+          aiProcessed: true,
+        };
+
+        // Apply confidence threshold
+        if (analysis.confidence >= confidenceThreshold) {
+          if (analysis.isRelevant) {
+            processedResults.push(enhancedPost);
+            totalRelevant++;
+          }
+        } else {
+          // Include low-confidence posts but flag them
+          enhancedPost.lowConfidence = true;
+          processedResults.push(enhancedPost);
+        }
+
+        totalProcessed++;
+        console.log(
+          `   ${
+            analysis.isRelevant ? "✅" : "❌"
+          } Post ${totalProcessed}: ${analysis.confidence.toFixed(
+            2
+          )} confidence - ${analysis.reasoning.substring(0, 100)}...`
+        );
+      }
+
+      // Small delay between batches to be nice to the system
+      if (i + batchSize < results.length) {
+        console.log("⏳ Brief pause...");
+        await new Promise((resolve) => setTimeout(resolve, 500));
+      }
+    }
+
+    // Determine output file
+    if (!outputFile) {
+      const inputBasename = path.basename(inputFile, ".json");
+      const inputDir = path.dirname(inputFile);
+      outputFile = path.join(inputDir, `${inputBasename}-ai-local.json`);
+    }
+
+    // Save results
+    fs.writeFileSync(
+      outputFile,
+      JSON.stringify(processedResults, null, 2),
+      "utf-8"
+    );
+
+    console.log("\n🎉 Local AI Analysis Complete!");
+    console.log(`📊 Results:`);
+    console.log(`   Total posts processed: ${totalProcessed}`);
+    console.log(`   Relevant posts found: ${totalRelevant}`);
+    console.log(`   Final results saved: ${processedResults.length}`);
+    console.log(`📁 Output saved to: ${outputFile}`);
+    console.log(`💰 Cost: $0.00 (completely free!)`);
+  } catch (error) {
+    console.error("❌ Error:", error.message);
+    process.exit(1);
+  }
+}
+
+// Show help if requested
+if (args.includes("--help") || args.includes("-h")) {
+  console.log(`
+LinkedOut Local AI Analyzer (Ollama)
+
+🚀 FREE local AI analysis - No API costs, complete privacy!
+
+Usage: node ai-analyzer-local.js [options]
+
+Options:
+  --input=<file>       Input JSON file (default: latest in results/)
+  --context=<text>     AI context to analyze against (required)
+  --confidence=<num>   Minimum confidence threshold (0.0-1.0, default: 0.7)
+  --model=<name>       Ollama model to use (default: llama2)
+  --batch-size=<num>   Number of posts to process at once (default: 3)
+  --output=<file>      Output file (default: adds -ai-local suffix)
+  --help, -h           Show this help message
+
+Examples:
+  node ai-analyzer-local.js --context="job layoffs"
+  node ai-analyzer-local.js --model=mistral --context="hiring opportunities"
+  node ai-analyzer-local.js --context="remote work" --confidence=0.8
+
+Prerequisites:
+  1. Install Ollama: https://ollama.ai/
+  2. Install a model: ollama pull llama2
+  3. Start Ollama: ollama serve
+
+Popular Models:
+  - llama2 (good general purpose)
+  - mistral (fast and accurate)
+  - codellama (good for technical content)
+  - llama2:13b (more accurate, slower)
+
+Environment Variables:
+  AI_CONTEXT           Default context for analysis
+  AI_CONFIDENCE        Default confidence threshold
+  AI_BATCH_SIZE        Default batch size
+  OLLAMA_MODEL         Default model (llama2, mistral, etc.)
+  OLLAMA_HOST          Ollama host (default: http://localhost:11434)
+`);
+  process.exit(0);
+}
+
+// Run the analyzer
+main();
--- a/keywords/keywords-layoff.csv
+++ b/keywords/keywords-layoff.csv
--- a/keywords/keywords-open-work.csv
+++ b/keywords/keywords-open-work.csv
--- a/linkedout.js
+++ b/linkedout.js
@ -1,57 +1,132 @@
 /**
- * LinkedIn Posts Scraper (linkedout)
+ * LinkedIn Posts Scraper (LinkedOut)
 *
- * This script logs into LinkedIn using credentials stored in a .env file,
- * reads keywords from a CSV file (keywords.csv), and scrapes posts matching
- * those keywords from LinkedIn's content search.
+ * A comprehensive tool for scraping LinkedIn posts based on keyword searches.
+ * Designed to track job market trends, layoffs, and open work opportunities
+ * by monitoring LinkedIn content automatically.
 *
- * Usage:
- *   node linkedout.js [--headless=true|false] [--keyword=additional_keyword]
+ * FEATURES:
+ *   - Automated LinkedIn login with browser automation
+ *   - Keyword-based post searching from CSV files or CLI
+ *   - Configurable search parameters (date, location, sorting)
+ *   - Duplicate detection for posts and profiles
+ *   - Text cleaning (removes hashtags, URLs, emojis)
+ *   - Timestamped JSON output files
+ *   - Command-line parameter overrides (see below)
+ *   - Enhanced geographic location validation
+ *   - Optional local AI-powered context analysis (Ollama)
 *
- * Command-line Parameters:
- *   --headless: Override the headless mode (true or false). Defaults to value in .env (HEADLESS).
- *   --keyword:  Append an additional keyword to the list of keywords from keywords.csv.
+ * USAGE:
+ *   node linkedout.js [options]
 *
- * Output:
- *   Saves results to a timestamped JSON file in the 'results' directory.
+ * COMMAND-LINE OPTIONS:
+ *   --headless=true|false         Override browser headless mode
+ *   --keyword="kw1,kw2"           Use only these keywords (comma-separated, overrides CSV)
+ *   --add-keyword="kw1,kw2"       Add extra keywords to CSV/CLI list
+ *   --city="CityName"             Override city
+ *   --date_posted=VALUE           Override date posted (past-24h, past-week, past-month, or empty)
+ *   --sort_by=VALUE               Override sort by (date_posted or relevance)
+ *   --location_filter=VALUE       Override location filter
+ *   --output=FILE                 Output file name
+ *   --no-location                 Disable location filtering
+ *   --no-ai                       Disable AI analysis
+ *   --ai-after                    Run local AI analysis after scraping
+ *   --help, -h                    Show this help message
 *
- * Requirements:
- *   - Node.js environment (or use the compiled executable)
- *   - Playwright installed (or included in the binary)
- *   - dotenv package for environment variables
- *   - csv-parser package for reading CSV files
+ * EXAMPLES:
+ *   node linkedout.js                                   # Standard scraping
+ *   node linkedout.js --headless=false                  # Visual mode
+ *   node linkedout.js --keyword="layoff,downsizing"     # Only these keywords
+ *   node linkedout.js --add-keyword="hiring freeze"     # Add extra keyword(s)
+ *   node linkedout.js --city="Vancouver" --date_posted=past-month
+ *   node linkedout.js --output=results/myfile.json
+ *   node linkedout.js --no-location --no-ai             # Fastest, no filters
+ *   node linkedout.js --ai-after                        # Run AI after scraping
 *
- * Environment Variables (.env):
- *   LINKEDIN_USERNAME - Your LinkedIn username
- *   LINKEDIN_PASSWORD - Your LinkedIn password
- *   HEADLESS - Default headless mode (true or false)
+ * POST-PROCESSING AI ANALYSIS:
+ *   node ai-analyzer-local.js --context="job layoffs"   # Run on latest results file
+ *   node ai-analyzer-local.js --input=results/results-2024-01-15.json --context="hiring"
 *
- * Example:
- *   node linkedout.js --headless=true --keyword=layoff
+ * ENVIRONMENT VARIABLES (.env file):
+ *   KEYWORDS=keywords-layoff.csv (filename only, always looks in keywords/ folder unless path is given)
+ *   See README for full list.
+ *
+ * OUTPUT:
+ *   - Saves to results/results-YYYY-MM-DD-HH-MM.json (or as specified by --output)
+ *   - Enhanced format with optional location validation and local AI analysis
+ *
+ * KEYWORD FILES:
+ *   - Place all keyword CSVs in the keywords/ folder
+ *   - keywords-layoff.csv: 33+ layoff-related terms
+ *   - keywords-open-work.csv: Terms for finding people open to work
+ *   - Custom CSV format: header "keyword" with one keyword per line
+ *
+ * DEPENDENCIES:
+ *   - playwright: Browser automation
+ *   - dotenv: Environment variable management
+ *   - csv-parser: CSV file parsing
+ *   - Node.js built-ins: fs, path, child_process
+ *
+ * SECURITY & LEGAL:
+ *   - Store credentials securely in .env file
+ *   - Respect LinkedIn's Terms of Service
+ *   - Use responsibly for educational/research purposes
+ *   - Consider rate limiting and LinkedIn API for production use
 */
-process.env.PLAYWRIGHT_BROWSERS_PATH = "0";
+//process.env.PLAYWRIGHT_BROWSERS_PATH = "0";
+// Suppress D-Bus notification errors in WSL
+process.env.NO_AT_BRIDGE = "1";
+process.env.DBUS_SESSION_BUS_ADDRESS = "/dev/null";

 const { chromium } = require("playwright");
 const fs = require("fs");
 const path = require("path");
 require("dotenv").config();
 const csv = require("csv-parser");
+const { spawn } = require("child_process");

-const DATE_POSTED = process.env.DATE_POSTED || "past-week"; // "past-24h", "past-week", "past-month", or ""
-const SORT_BY = process.env.SORT_BY || "date_posted"; // "relevance", "date_posted"
-const WHEELS = process.env.WHEELS || 5;
+// Core configuration
+const DATE_POSTED = process.env.DATE_POSTED || "past-week";
+const SORT_BY = process.env.SORT_BY || "date_posted";
+const WHEELS = parseInt(process.env.WHEELS) || 5;
 const CITY = process.env.CITY || "Toronto";

-// Read credentials and headless mode from .env
+// Location filtering configuration
+const LOCATION_FILTER = process.env.LOCATION_FILTER || "";
+const ENABLE_LOCATION_CHECK = process.env.ENABLE_LOCATION_CHECK === "true";
+
+// Local AI analysis configuration
+const ENABLE_LOCAL_AI = process.env.ENABLE_LOCAL_AI === "true";
+const RUN_LOCAL_AI_AFTER_SCRAPING =
+  process.env.RUN_LOCAL_AI_AFTER_SCRAPING === "true";
+const AI_CONTEXT =
+  process.env.AI_CONTEXT || "job layoffs and workforce reduction";
+
+// Import enhanced location utilities
+const {
+  parseLocationFilters,
+  validateLocationAgainstFilters,
+  extractLocationFromProfile,
+} = require("./location-utils");
+
+// Read credentials
 const LINKEDIN_USERNAME = process.env.LINKEDIN_USERNAME;
 const LINKEDIN_PASSWORD = process.env.LINKEDIN_PASSWORD;
-
-// Default headless mode from .env
 let HEADLESS = process.env.HEADLESS === "true";

 // Parse command-line arguments
 const args = process.argv.slice(2);
-let additionalKeyword = null;
+let cliKeywords = null; // If set, only use these
+let additionalKeywords = [];
+let disableLocation = false;
+let disableAI = false;
+let runAIAfter = RUN_LOCAL_AI_AFTER_SCRAPING;
+let cliCity = null;
+let cliDatePosted = null;
+let cliSortBy = null;
+let cliLocationFilter = null;
+let cliOutput = null;
+let showHelp = false;

 for (const arg of args) {
  if (arg.startsWith("--headless=")) {
@ -59,7 +134,99 @@ for (const arg of args) {
    HEADLESS = val === "true";
  }
  if (arg.startsWith("--keyword=")) {
-    additionalKeyword = arg.split("=")[1];
+    cliKeywords = arg
+      .split("=")[1]
+      .split(",")
+      .map((k) => k.trim())
+      .filter(Boolean);
+  }
+  if (arg.startsWith("--add-keyword=")) {
+    additionalKeywords = additionalKeywords.concat(
+      arg
+        .split("=")[1]
+        .split(",")
+        .map((k) => k.trim())
+        .filter(Boolean)
+    );
+  }
+  if (arg === "--no-location") {
+    disableLocation = true;
+  }
+  if (arg === "--no-ai") {
+    disableAI = true;
+  }
+  if (arg === "--ai-after") {
+    runAIAfter = true;
+  }
+  if (arg.startsWith("--city=")) {
+    cliCity = arg.split("=")[1];
+  }
+  if (arg.startsWith("--date_posted=")) {
+    cliDatePosted = arg.split("=")[1];
+  }
+  if (arg.startsWith("--sort_by=")) {
+    cliSortBy = arg.split("=")[1];
+  }
+  if (arg.startsWith("--location_filter=")) {
+    cliLocationFilter = arg.split("=")[1];
+  }
+  if (arg.startsWith("--output=")) {
+    cliOutput = arg.split("=")[1];
+  }
+  if (arg === "--help" || arg === "-h") {
+    showHelp = true;
+  }
+}
+
+if (showHelp) {
+  console.log(
+    `\nLinkedOut - LinkedIn Posts Scraper\n\nUsage: node linkedout.js [options]\n\nOptions:\n  --headless=true|false         Override browser headless mode\n  --keyword="kw1,kw2"           Use only these keywords (comma-separated, overrides CSV)\n  --add-keyword="kw1,kw2" Add extra keywords to CSV list\n  --city="CityName"             Override city\n  --date_posted=VALUE           Override date posted (past-24h, past-week, past-month or '')\n  --sort_by=VALUE               Override sort by (date_posted or relevance)\n  --location_filter=VALUE       Override location filter\n  --output=FILE                 Output file name\n  --no-location                 Disable location filtering\n  --no-ai                       Disable AI analysis\n  --ai-after                    Run local AI analysis after scraping\n  --help, -h                    Show this help message\n\nExamples:\n  node linkedout.js --keyword="layoff,downsizing"\n  node linkedout.js --add-keyword="hiring freeze"\n  node linkedout.js --city="Vancouver" --date_posted=past-month\n  node linkedout.js --output=results/myfile.json\n`
+  );
+  process.exit(0);
+}
+
+// Use CLI overrides if provided
+const EFFECTIVE_CITY = cliCity || CITY;
+const EFFECTIVE_DATE_POSTED = cliDatePosted || DATE_POSTED;
+const EFFECTIVE_SORT_BY = cliSortBy || SORT_BY;
+const EFFECTIVE_LOCATION_FILTER = cliLocationFilter || LOCATION_FILTER;
+
+// Read keywords from CSV or CLI
+const keywords = [];
+let keywordEnv = process.env.KEYWORDS || "keywords-layoff.csv";
+let csvPath = path.join(
+  process.cwd(),
+  keywordEnv.includes("/") ? keywordEnv : `keywords/${keywordEnv}`
+);
+
+function loadKeywordsAndStart() {
+  if (cliKeywords) {
+    // Only use CLI keywords
+    cliKeywords.forEach((k) => keywords.push(k));
+    if (additionalKeywords.length > 0) {
+      additionalKeywords.forEach((k) => keywords.push(k));
+    }
+    startScraper();
+  } else {
+    // Load from CSV, then add any additional keywords
+    fs.createReadStream(csvPath)
+      .pipe(csv())
+      .on("data", (row) => {
+        if (row.keyword) keywords.push(row.keyword.trim());
+      })
+      .on("end", () => {
+        if (keywords.length === 0) {
+          console.error("No keywords found in csv");
+          process.exit(1);
+        }
+        if (additionalKeywords.length > 0) {
+          additionalKeywords.forEach((k) => keywords.push(k));
+          console.log(
+            `Added additional keywords: ${additionalKeywords.join(", ")}`
+          );
+        }
+        startScraper();
+      });
  }
 }

@ -84,9 +251,10 @@ function buildSearchUrl(keyword, city) {
  let url = `https://www.linkedin.com/search/results/content/?keywords=${encodeURIComponent(
    keyword + " " + city
  )}`;
-  if (DATE_POSTED)
-    url += `&datePosted=${encodeURIComponent(`"${DATE_POSTED}"`)}`;
-  if (SORT_BY) url += `&sortBy=${encodeURIComponent(`"${SORT_BY}"`)}`;
+  if (EFFECTIVE_DATE_POSTED)
+    url += `&datePosted=${encodeURIComponent(`"${EFFECTIVE_DATE_POSTED}"`)}`;
+  if (EFFECTIVE_SORT_BY)
+    url += `&sortBy=${encodeURIComponent(`"${EFFECTIVE_SORT_BY}"`)}`;
  url += `&origin=FACETED_SEARCH`;
  return url;
 }
@ -95,144 +263,386 @@ function containsAnyKeyword(text, keywords) {
  return keywords.some((k) => text.toLowerCase().includes(k.toLowerCase()));
 }

-// Read keywords from CSV
-const keywords = [];
-const csvPath = path.join(
-  process.cwd(),
-  process.env.KEYWORDS || "keywords-layoff.csv"
-);
+/**
+ * Enhanced profile location validation with smart waiting (no timeouts)
+ * Uses a new tab to avoid disrupting the main scraping flow
+ */
+async function validateProfileLocation(
+  context,
+  profileLink,
+  locationFilterString
+) {
+  if (!locationFilterString || !ENABLE_LOCATION_CHECK || disableLocation) {
+    return {
+      isValid: true,
+      location: "Not checked",
+      matchedFilter: null,
+      reasoning: "Location check disabled",
+      error: null,
+    };
+  }

-fs.createReadStream(csvPath)
-  .pipe(csv())
-  .on("data", (row) => {
-    if (row.keyword) keywords.push(row.keyword.trim());
-  })
-  .on("end", async () => {
-    if (keywords.length === 0) {
-      console.error("No keywords found in csv");
-      process.exit(1);
-    }
+  let profilePage = null;
+  try {
+    console.log(`🌍 Checking profile location: ${profileLink}`);

-    // Append additional keyword if provided
-    if (additionalKeyword) {
-      keywords.push(additionalKeyword);
-      console.log(`Added additional keyword from CLI: ${additionalKeyword}`);
-    }
-
-    const browser = await chromium.launch({
-      headless: HEADLESS,
-      args: ["--no-sandbox", "--disable-setuid-sandbox"],
-    });
-    const context = await browser.newContext();
-    const page = await Promise.race([
-      context.newPage(),
-      new Promise((_, reject) =>
-        setTimeout(() => reject(new Error("newPage timeout")), 10000)
-      ),
-    ]).catch((err) => {
-      console.error("Failed to create new page:", err);
-      process.exit(1);
+    // Create a new page/tab for profile validation
+    profilePage = await context.newPage();
+    await profilePage.goto(profileLink, {
+      waitUntil: "domcontentloaded",
+      timeout: 10000,
    });

-    try {
-      await page.goto("https://www.linkedin.com/login");
-      await page.fill('input[name="session_key"]', LINKEDIN_USERNAME);
-      await page.fill('input[name="session_password"]', LINKEDIN_PASSWORD);
-      await page.click('button[type="submit"]');
-      await page.waitForSelector("img.global-nav__me-photo", {
-        timeout: 10000,
-      });
+    // Always use smart waiting for key profile elements
+    await Promise.race([
+      profilePage.waitForSelector("h1", { timeout: 3000 }),
+      profilePage.waitForSelector("[data-field='experience_section']", {
+        timeout: 3000,
+      }),
+      profilePage.waitForSelector(".pv-text-details__left-panel", {
+        timeout: 3000,
+      }),
+    ]);

-      const seenPosts = new Set();
-      const seenProfiles = new Set();
-      const results = [];
+    // Use enhanced location extraction
+    const location = await extractLocationFromProfile(profilePage);

-      for (const keyword of keywords) {
-        const searchUrl = buildSearchUrl(keyword, CITY);
-        await page.goto(searchUrl, { waitUntil: "load" });
+    if (!location) {
+      return {
+        isValid: false,
+        location: "Location not found",
+        matchedFilter: null,
+        reasoning: "Could not extract location from profile",
+        error: "Location extraction failed",
+      };
+    }

-        try {
-          await page.waitForSelector(".feed-shared-update-v2", {
-            timeout: 3000,
+    // Parse location filters
+    const locationFilters = parseLocationFilters(locationFilterString);
+
+    // Validate against filters
+    const validationResult = validateLocationAgainstFilters(
+      location,
+      locationFilters
+    );
+
+    return {
+      isValid: validationResult.isValid,
+      location,
+      matchedFilter: validationResult.matchedFilter,
+      reasoning: validationResult.reasoning,
+      error: validationResult.isValid ? null : validationResult.reasoning,
+    };
+  } catch (error) {
+    console.error(`❌ Error checking profile location: ${error.message}`);
+    return {
+      isValid: false,
+      location: "Error checking location",
+      matchedFilter: null,
+      reasoning: `Error: ${error.message}`,
+      error: error.message,
+    };
+  } finally {
+    // Always close the profile page to clean up
+    if (profilePage) {
+      try {
+        await profilePage.close();
+      } catch (closeError) {
+        console.error(`⚠️  Error closing profile page: ${closeError.message}`);
+      }
+    }
+  }
+}
+
+/**
+ * Run local AI analysis after scraping is complete
+ */
+async function runPostScrapingLocalAI(resultsFile) {
+  if (disableAI || !ENABLE_LOCAL_AI || !runAIAfter) {
+    return;
+  }
+
+  console.log("\n🧠 Starting post-scraping local AI analysis...");
+
+  const analyzerScript = "ai-analyzer-local.js";
+  const args = [`--input=${resultsFile}`, `--context=${AI_CONTEXT}`];
+
+  console.log(`🚀 Running: node ${analyzerScript} ${args.join(" ")}`);
+
+  return new Promise((resolve, reject) => {
+    const child = spawn("node", [analyzerScript, ...args], {
+      stdio: "inherit",
+      cwd: process.cwd(),
+    });
+
+    child.on("close", (code) => {
+      if (code === 0) {
+        console.log("✅ Local AI analysis completed successfully");
+        resolve();
+      } else {
+        console.error(`❌ Local AI analysis failed with code ${code}`);
+        reject(new Error(`Local AI analysis process exited with code ${code}`));
+      }
+    });
+
+    child.on("error", (error) => {
+      console.error(`❌ Failed to run local AI analysis: ${error.message}`);
+      reject(error);
+    });
+  });
+}
+
+async function startScraper() {
+  console.log("\n🚀 LinkedOut Scraper Starting...");
+  console.log(`📊 Keywords: ${keywords.length}`);
+  console.log(
+    `🌍 Location Filter: ${
+      ENABLE_LOCATION_CHECK && !disableLocation
+        ? LOCATION_FILTER || "None"
+        : "Disabled"
+    }`
+  );
+  console.log(
+    `🧠 Local AI Analysis: ${
+      ENABLE_LOCAL_AI && !disableAI
+        ? runAIAfter
+          ? "After scraping"
+          : "Manual"
+        : "Disabled"
+    }`
+  );
+
+  const browser = await chromium.launch({
+    headless: HEADLESS,
+    args: ["--no-sandbox", "--disable-setuid-sandbox"],
+  });
+  const context = await browser.newContext();
+  const page = await Promise.race([
+    context.newPage(),
+    new Promise((_, reject) =>
+      setTimeout(() => reject(new Error("newPage timeout")), 10000)
+    ),
+  ]).catch((err) => {
+    console.error("Failed to create new page:", err);
+    process.exit(1);
+  });
+
+  let scrapeError = null;
+  try {
+    await page.goto("https://www.linkedin.com/login");
+    await page.fill('input[name="session_key"]', LINKEDIN_USERNAME);
+    await page.fill('input[name="session_password"]', LINKEDIN_PASSWORD);
+    await page.click('button[type="submit"]');
+    await page.waitForSelector("img.global-nav__me-photo", {
+      timeout: 15000,
+    });
+
+    const seenPosts = new Set();
+    const seenProfiles = new Set();
+    const results = [];
+    const rejectedResults = [];
+
+    for (const keyword of keywords) {
+      const searchUrl = buildSearchUrl(keyword, EFFECTIVE_CITY);
+      await page.goto(searchUrl, { waitUntil: "load" });
+
+      try {
+        await page.waitForSelector(".feed-shared-update-v2", {
+          timeout: 3000,
+        });
+      } catch (error) {
+        console.log(
+          `---\nNo posts found for keyword: ${keyword}\nCity: ${EFFECTIVE_CITY}\nDate posted: ${EFFECTIVE_DATE_POSTED}\nSort by: ${EFFECTIVE_SORT_BY}`
+        );
+        continue;
+      }
+
+      for (let i = 0; i < WHEELS; i++) {
+        await page.mouse.wheel(0, 1000);
+        await page.waitForTimeout(1000);
+      }
+
+      const postContainers = await page.$$(".feed-shared-update-v2");
+      for (const container of postContainers) {
+        let text = "";
+        const textHandle = await container.$(
+          "div.update-components-text, span.break-words"
+        );
+        if (textHandle) {
+          text = (await textHandle.textContent()) || "";
+          text = cleanText(text);
+        }
+        if (
+          !text ||
+          seenPosts.has(text) ||
+          text.length < 30 ||
+          !/[a-zA-Z0-9]/.test(text)
+        ) {
+          rejectedResults.push({
+            rejected: true,
+            reason: !text
+              ? "No text"
+              : seenPosts.has(text)
+              ? "Duplicate post"
+              : text.length < 30
+              ? "Text too short"
+              : "No alphanumeric content",
+            keyword,
+            text,
+            profileLink: null,
+            timestamp: new Date().toISOString(),
+          });
+          continue;
+        }
+        seenPosts.add(text);
+
+        let profileLink = "";
+        const profileLinkElement = await container.$('a[href*="/in/"]');
+        if (profileLinkElement) {
+          profileLink = await profileLinkElement.getAttribute("href");
+          if (profileLink && !profileLink.startsWith("http")) {
+            profileLink = `https://www.linkedin.com${profileLink}`;
+          }
+          profileLink = profileLink.split("?")[0];
+        }
+
+        if (!profileLink || seenProfiles.has(profileLink)) {
+          rejectedResults.push({
+            rejected: true,
+            reason: !profileLink ? "No profile link" : "Duplicate profile",
+            keyword,
+            text,
+            profileLink,
+            timestamp: new Date().toISOString(),
+          });
+          continue;
+        }
+        seenProfiles.add(profileLink);
+
+        // Double-check keyword presence
+        if (!containsAnyKeyword(text, keywords)) {
+          rejectedResults.push({
+            rejected: true,
+            reason: "Keyword not present",
+            keyword,
+            text,
+            profileLink,
+            timestamp: new Date().toISOString(),
+          });
+          continue;
+        }
+
+        console.log("---");
+        console.log("Keyword:", keyword);
+        console.log("Post:", text.substring(0, 100) + "...");
+        console.log("Profile:", profileLink);
+
+        // Enhanced location validation
+        const locationCheck = await validateProfileLocation(
+          context,
+          profileLink,
+          EFFECTIVE_LOCATION_FILTER
+        );
+        console.log("📍 Location:", locationCheck.location);
+        console.log("🎯 Match:", locationCheck.reasoning);
+
+        if (!locationCheck.isValid) {
+          rejectedResults.push({
+            rejected: true,
+            reason: `Location filter failed: ${locationCheck.error}`,
+            keyword,
+            text,
+            profileLink,
+            location: locationCheck.location,
+            locationReasoning: locationCheck.reasoning,
+            timestamp: new Date().toISOString(),
          });
-        } catch (error) {
          console.log(
-            `---\nNo posts found for keyword: ${keyword}\nDate posted: ${DATE_POSTED}\nSort by: ${SORT_BY}`
+            "❌ Skipping - Location filter failed:",
+            locationCheck.error
          );
          continue;
        }

-        for (let i = 0; i < WHEELS; i++) {
-          await page.mouse.wheel(0, 1000);
-          await page.waitForTimeout(1000);
-        }
+        console.log("✅ Post passed all filters");

-        const postContainers = await page.$$(".feed-shared-update-v2");
-        for (const container of postContainers) {
-          let text = "";
-          const textHandle = await container.$(
-            "div.update-components-text, span.break-words"
-          );
-          if (textHandle) {
-            text = (await textHandle.textContent()) || "";
-            text = cleanText(text);
-          }
-          if (
-            !text ||
-            seenPosts.has(text) ||
-            text.length < 30 ||
-            !/[a-zA-Z0-9]/.test(text)
-          )
-            continue;
-          seenPosts.add(text);
-
-          let profileLink = "";
-          const profileLinkElement = await container.$('a[href*="/in/"]');
-          if (profileLinkElement) {
-            profileLink = await profileLinkElement.getAttribute("href");
-            if (profileLink && !profileLink.startsWith("http")) {
-              profileLink = `https://www.linkedin.com${profileLink}`;
-            }
-            profileLink = profileLink.split("?")[0];
-          }
-
-          if (!profileLink || seenProfiles.has(profileLink)) continue;
-          seenProfiles.add(profileLink);
-
-          // Double-check keyword presence
-          if (!containsAnyKeyword(text, keywords)) continue;
-
-          console.log("---");
-          console.log("Keyword:", keyword);
-          console.log("Post:", text);
-          console.log("Profile:", profileLink);
-
-          results.push({
-            keyword,
-            text,
-            profileLink,
-          });
-        }
+        results.push({
+          keyword,
+          text,
+          profileLink,
+          location: locationCheck.location,
+          locationValid: locationCheck.isValid,
+          locationMatchedFilter: locationCheck.matchedFilter,
+          locationReasoning: locationCheck.reasoning,
+          timestamp: new Date().toLocaleString("en-CA", {
+            year: "numeric",
+            month: "2-digit",
+            day: "2-digit",
+            hour: "2-digit",
+            minute: "2-digit",
+            second: "2-digit",
+            hour12: false,
+          }),
+          aiProcessed: false,
+        });
      }
+    }

-      const now = new Date();
-      const timestamp = `${now.getFullYear()}-${String(
-        now.getMonth() + 1
-      ).padStart(2, "0")}-${String(now.getDate()).padStart(2, "0")}-${String(
+    const now = new Date();
+    const timestamp =
+      cliOutput ||
+      `${now.getFullYear()}-${String(now.getMonth() + 1).padStart(
+        2,
+        "0"
+      )}-${String(now.getDate()).padStart(2, "0")}-${String(
        now.getHours()
      ).padStart(2, "0")}-${String(now.getMinutes()).padStart(2, "0")}`;
-      const resultsDir = "results";
-      const resultsFile = `${resultsDir}/results-${timestamp}.json`;
+    const resultsDir = "results";
+    const resultsFile = `${resultsDir}/results-${timestamp}.json`;
+    const rejectedFile = `${resultsDir}/results-${timestamp}-rejected.json`;

-      if (!fs.existsSync(resultsDir)) {
-        fs.mkdirSync(resultsDir);
-      }
-
-      fs.writeFileSync(resultsFile, JSON.stringify(results, null, 2), "utf-8");
-      console.log(`Saved ${results.length} posts to ${resultsFile}`);
-    } catch (err) {
-      console.error("Error:", err);
-    } finally {
-      await browser.close();
+    if (!fs.existsSync(resultsDir)) {
+      fs.mkdirSync(resultsDir);
    }
-  });
+
+    fs.writeFileSync(resultsFile, JSON.stringify(results, null, 2), "utf-8");
+    fs.writeFileSync(
+      rejectedFile,
+      JSON.stringify(rejectedResults, null, 2),
+      "utf-8"
+    );
+    console.log(`\n🎉 Scraping Complete!`);
+    console.log(`📊 Saved ${results.length} posts to ${resultsFile}`);
+    console.log(
+      `📋 Saved ${rejectedResults.length} rejected posts to ${rejectedFile}`
+    );
+
+    // Run local AI analysis if requested
+    if (runAIAfter && results.length > 0 && !scrapeError) {
+      try {
+        await runPostScrapingLocalAI(resultsFile);
+      } catch (error) {
+        console.error(
+          "⚠️  Local AI analysis failed, but scraping completed successfully"
+        );
+      }
+    }
+
+    console.log(`\n💡 Next steps:`);
+    console.log(`   📋 Review results in ${resultsFile}`);
+    if (!runAIAfter && !disableAI) {
+      console.log(`   🧠 Local AI Analysis:`);
+      console.log(`      node ai-analyzer-local.js --context="${AI_CONTEXT}"`);
+      console.log(
+        `      node ai-analyzer-local.js --input=${resultsFile} --context="your context"`
+      );
+    }
+  } catch (err) {
+    scrapeError = err;
+    console.error("Error:", err);
+  } finally {
+    await browser.close();
+  }
+}
+
+loadKeywordsAndStart();
--- a/location-utils.js
+++ b/location-utils.js
--- a/package-lock.json
+++ b/package-lock.json
@ -11,7 +11,7 @@
      "dependencies": {
        "csv-parser": "^3.2.0",
        "dotenv": "^17.0.0",
-        "playwright": "^1.53.1"
+        "playwright": "^1.53.2"
      }
    },
    "node_modules/csv-parser": {
@ -53,12 +53,12 @@
      }
    },
    "node_modules/playwright": {
-      "version": "1.53.1",
-      "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.53.1.tgz",
-      "integrity": "sha512-LJ13YLr/ocweuwxyGf1XNFWIU4M2zUSo149Qbp+A4cpwDjsxRPj7k6H25LBrEHiEwxvRbD8HdwvQmRMSvquhYw==",
+      "version": "1.53.2",
+      "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.53.2.tgz",
+      "integrity": "sha512-6K/qQxVFuVQhRQhFsVZ9fGeatxirtrpPgxzBYWyZLEXJzqYwuL4fuNmfOfD5et1tJE4GScKyPNeLhZeRwuTU3A==",
      "license": "Apache-2.0",
      "dependencies": {
-        "playwright-core": "1.53.1"
+        "playwright-core": "1.53.2"
      },
      "bin": {
        "playwright": "cli.js"
@ -71,9 +71,9 @@
      }
    },
    "node_modules/playwright-core": {
-      "version": "1.53.1",
-      "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.53.1.tgz",
-      "integrity": "sha512-Z46Oq7tLAyT0lGoFx4DOuB1IA9D1TPj0QkYxpPVUnGDqHHvDpCftu1J2hM2PiWsNMoZh8+LQaarAWcDfPBc6zg==",
+      "version": "1.53.2",
+      "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.53.2.tgz",
+      "integrity": "sha512-ox/OytMy+2w1jcYEYlOo1Hhp8hZkLCximMTUTMBXjGUA1KoFfiSZ+DU+3a739jsPY0yoKH2TFy9S2fsJas8yAw==",
      "license": "Apache-2.0",
      "bin": {
        "playwright-core": "cli.js"
--- a/package.json
+++ b/package.json
@ -13,6 +13,6 @@
  "dependencies": {
    "csv-parser": "^3.2.0",
    "dotenv": "^17.0.0",
-    "playwright": "^1.53.1"
+    "playwright": "^1.53.2"
  }
 }
--- a/test/test.js
+++ b/test/test.js
@ -1,19 +1,19 @@
-console.log("START!");
-
-const { chromium } = require("playwright");
-(async () => {
-  console.log("browser!");
-
-  const browser = await chromium.launch({
-    headless: true,
-    args: ["--no-sandbox", "--disable-setuid-sandbox"],
-  });
-  console.log("new page!");
-
-  const page = await browser.newPage();
-  console.log("GOTO!");
-
-  await page.goto("https://example.com");
-  console.log("Success!");
-  await browser.close();
-})();
+console.log("START!");
+
+const { chromium } = require("playwright");
+(async () => {
+  console.log("browser!");
+
+  const browser = await chromium.launch({
+    headless: true,
+    args: ["--no-sandbox", "--disable-setuid-sandbox"],
+  });
+  console.log("new page!");
+
+  const page = await browser.newPage();
+  console.log("GOTO!");
+
+  await page.goto("https://example.com");
+  console.log("Success!");
+  await browser.close();
+})();