bps-kit 1.0.1 → 1.0.2

package/templates/vault/apify-ultimate-scraper/reference/scripts/run_actor.js

@@ -0,0 +1,363 @@
+#!/usr/bin/env node
+/**
+ * Apify Actor Runner - Runs Apify actors and exports results.
+ *
+ * Usage:
+ *   # Quick answer (display in chat, no file saved)
+ *   node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
+ *
+ *   # Export to file
+ *   node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
+ */
+
+import { parseArgs } from 'node:util';
+import { writeFileSync, statSync } from 'node:fs';
+
+// User-Agent for tracking skill usage in Apify analytics
+const USER_AGENT = 'apify-agent-skills/apify-ultimate-scraper-1.3.0';
+
+// Parse command-line arguments
+function parseCliArgs() {
+    const options = {
+        actor: { type: 'string', short: 'a' },
+        input: { type: 'string', short: 'i' },
+        output: { type: 'string', short: 'o' },
+        format: { type: 'string', short: 'f', default: 'csv' },
+        timeout: { type: 'string', short: 't', default: '600' },
+        'poll-interval': { type: 'string', default: '5' },
+        help: { type: 'boolean', short: 'h' },
+    };
+
+    const { values } = parseArgs({ options, allowPositionals: false });
+
+    if (values.help) {
+        printHelp();
+        process.exit(0);
+    }
+
+    if (!values.actor) {
+        console.error('Error: --actor is required');
+        printHelp();
+        process.exit(1);
+    }
+
+    if (!values.input) {
+        console.error('Error: --input is required');
+        printHelp();
+        process.exit(1);
+    }
+
+    return {
+        actor: values.actor,
+        input: values.input,
+        output: values.output,
+        format: values.format || 'csv',
+        timeout: parseInt(values.timeout, 10),
+        pollInterval: parseInt(values['poll-interval'], 10),
+    };
+}
+
+function printHelp() {
+    console.log(`
+Apify Actor Runner - Run Apify actors and export results
+
+Usage:
+  node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
+
+Options:
+  --actor, -a       Actor ID (e.g., compass/crawler-google-places) [required]
+  --input, -i       Actor input as JSON string [required]
+  --output, -o      Output file path (optional - if not provided, displays quick answer)
+  --format, -f      Output format: csv, json (default: csv)
+  --timeout, -t     Max wait time in seconds (default: 600)
+  --poll-interval   Seconds between status checks (default: 5)
+  --help, -h        Show this help message
+
+Output Formats:
+  JSON (all data)     --output file.json --format json
+  CSV (all data)      --output file.csv --format csv
+  Quick answer        (no --output) - displays top 5 in chat
+
+Examples:
+  # Quick answer - display top 5 in chat
+  node --env-file=.env scripts/run_actor.js \\
+    --actor "compass/crawler-google-places" \\
+    --input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
+
+  # Export all data to CSV
+  node --env-file=.env scripts/run_actor.js \\
+    --actor "compass/crawler-google-places" \\
+    --input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
+    --output leads.csv --format csv
+`);
+}
+
+// Start an actor run and return { runId, datasetId }
+async function startActor(token, actorId, inputJson) {
+    // Convert "author/actor" format to "author~actor" for API compatibility
+    const apiActorId = actorId.replace('/', '~');
+    const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
+
+    let data;
+    try {
+        data = JSON.parse(inputJson);
+    } catch (e) {
+        console.error(`Error: Invalid JSON input: ${e.message}`);
+        process.exit(1);
+    }
+
+    const response = await fetch(url, {
+        method: 'POST',
+        headers: {
+            'Content-Type': 'application/json',
+            'User-Agent': `${USER_AGENT}/start_actor`,
+        },
+        body: JSON.stringify(data),
+    });
+
+    if (response.status === 404) {
+        console.error(`Error: Actor '${actorId}' not found`);
+        process.exit(1);
+    }
+
+    if (!response.ok) {
+        const text = await response.text();
+        console.error(`Error: API request failed (${response.status}): ${text}`);
+        process.exit(1);
+    }
+
+    const result = await response.json();
+    return {
+        runId: result.data.id,
+        datasetId: result.data.defaultDatasetId,
+    };
+}
+
+// Poll run status until complete or timeout
+async function pollUntilComplete(token, runId, timeout, interval) {
+    const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
+    const startTime = Date.now();
+    let lastStatus = null;
+
+    while (true) {
+        const response = await fetch(url);
+        if (!response.ok) {
+            const text = await response.text();
+            console.error(`Error: Failed to get run status: ${text}`);
+            process.exit(1);
+        }
+
+        const result = await response.json();
+        const status = result.data.status;
+
+        // Only print when status changes
+        if (status !== lastStatus) {
+            console.log(`Status: ${status}`);
+            lastStatus = status;
+        }
+
+        if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
+            return status;
+        }
+
+        const elapsed = (Date.now() - startTime) / 1000;
+        if (elapsed > timeout) {
+            console.error(`Warning: Timeout after ${timeout}s, actor still running`);
+            return 'TIMED-OUT';
+        }
+
+        await sleep(interval * 1000);
+    }
+}
+
+// Download dataset items
+async function downloadResults(token, datasetId, outputPath, format) {
+    const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
+
+    const response = await fetch(url, {
+        headers: {
+            'User-Agent': `${USER_AGENT}/download_${format}`,
+        },
+    });
+
+    if (!response.ok) {
+        const text = await response.text();
+        console.error(`Error: Failed to download results: ${text}`);
+        process.exit(1);
+    }
+
+    const data = await response.json();
+
+    if (format === 'json') {
+        writeFileSync(outputPath, JSON.stringify(data, null, 2));
+    } else {
+        // CSV output
+        if (data.length > 0) {
+            const fieldnames = Object.keys(data[0]);
+            const csvLines = [fieldnames.join(',')];
+
+            for (const row of data) {
+                const values = fieldnames.map((key) => {
+                    let value = row[key];
+
+                    // Truncate long text fields
+                    if (typeof value === 'string' && value.length > 200) {
+                        value = value.slice(0, 200) + '...';
+                    } else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
+                        value = JSON.stringify(value) || '';
+                    }
+
+                    // CSV escape: wrap in quotes if contains comma, quote, or newline
+                    if (value === null || value === undefined) {
+                        return '';
+                    }
+                    const strValue = String(value);
+                    if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
+                        return `"${strValue.replace(/"/g, '""')}"`;
+                    }
+                    return strValue;
+                });
+                csvLines.push(values.join(','));
+            }
+
+            writeFileSync(outputPath, csvLines.join('\n'));
+        } else {
+            writeFileSync(outputPath, '');
+        }
+    }
+
+    console.log(`Saved to: ${outputPath}`);
+}
+
+// Display top 5 results in chat format
+async function displayQuickAnswer(token, datasetId) {
+    const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
+
+    const response = await fetch(url, {
+        headers: {
+            'User-Agent': `${USER_AGENT}/quick_answer`,
+        },
+    });
+
+    if (!response.ok) {
+        const text = await response.text();
+        console.error(`Error: Failed to download results: ${text}`);
+        process.exit(1);
+    }
+
+    const data = await response.json();
+    const total = data.length;
+
+    if (total === 0) {
+        console.log('\nNo results found.');
+        return;
+    }
+
+    // Display top 5
+    console.log(`\n${'='.repeat(60)}`);
+    console.log(`TOP 5 RESULTS (of ${total} total)`);
+    console.log('='.repeat(60));
+
+    for (let i = 0; i < Math.min(5, data.length); i++) {
+        const item = data[i];
+        console.log(`\n--- Result ${i + 1} ---`);
+
+        for (const [key, value] of Object.entries(item)) {
+            let displayValue = value;
+
+            // Truncate long values
+            if (typeof value === 'string' && value.length > 100) {
+                displayValue = value.slice(0, 100) + '...';
+            } else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
+                const jsonStr = JSON.stringify(value);
+                displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
+            }
+
+            console.log(`  ${key}: ${displayValue}`);
+        }
+    }
+
+    console.log(`\n${'='.repeat(60)}`);
+    if (total > 5) {
+        console.log(`Showing 5 of ${total} results.`);
+    }
+    console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
+    console.log('='.repeat(60));
+}
+
+// Report summary of downloaded data
+function reportSummary(outputPath, format) {
+    const stats = statSync(outputPath);
+    const size = stats.size;
+
+    let count;
+    try {
+        const content = require('fs').readFileSync(outputPath, 'utf-8');
+        if (format === 'json') {
+            const data = JSON.parse(content);
+            count = Array.isArray(data) ? data.length : 1;
+        } else {
+            // CSV - count lines minus header
+            const lines = content.split('\n').filter((line) => line.trim());
+            count = Math.max(0, lines.length - 1);
+        }
+    } catch {
+        count = 'unknown';
+    }
+
+    console.log(`Records: ${count}`);
+    console.log(`Size: ${size.toLocaleString()} bytes`);
+}
+
+// Helper: sleep for ms
+function sleep(ms) {
+    return new Promise((resolve) => setTimeout(resolve, ms));
+}
+
+// Main function
+async function main() {
+    // Parse args first so --help works without token
+    const args = parseCliArgs();
+
+    // Check for APIFY_TOKEN
+    const token = process.env.APIFY_TOKEN;
+    if (!token) {
+        console.error('Error: APIFY_TOKEN not found in .env file');
+        console.error('');
+        console.error('Add your token to .env file:');
+        console.error('  APIFY_TOKEN=your_token_here');
+        console.error('');
+        console.error('Get your token: https://console.apify.com/account/integrations');
+        process.exit(1);
+    }
+
+    // Start the actor run
+    console.log(`Starting actor: ${args.actor}`);
+    const { runId, datasetId } = await startActor(token, args.actor, args.input);
+    console.log(`Run ID: ${runId}`);
+    console.log(`Dataset ID: ${datasetId}`);
+
+    // Poll for completion
+    const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
+
+    if (status !== 'SUCCEEDED') {
+        console.error(`Error: Actor run ${status}`);
+        console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
+        process.exit(1);
+    }
+
+    // Determine output mode
+    if (args.output) {
+        // File output mode
+        await downloadResults(token, datasetId, args.output, args.format);
+        reportSummary(args.output, args.format);
+    } else {
+        // Quick answer mode - display in chat
+        await displayQuickAnswer(token, datasetId);
+    }
+}
+
+main().catch((err) => {
+    console.error(`Error: ${err.message}`);
+    process.exit(1);
+});

package/templates/vault/audio-transcriber/scripts/install-requirements.sh

@@ -0,0 +1,190 @@
+#!/usr/bin/env bash
+
+# Audio Transcriber - Requirements Installation Script
+# Automatically installs and validates dependencies
+
+set -euo pipefail
+
+# Colors
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+RED='\033[0;31m'
+BLUE='\033[0;34m'
+NC='\033[0m'
+
+echo -e "${BLUE}🔧 Audio Transcriber - Dependency Installation${NC}"
+echo ""
+
+# Check Python
+if ! command -v python3 &>/dev/null; then
+    echo -e "${RED}❌ Python 3 not found. Please install Python 3.8+${NC}"
+    exit 1
+fi
+
+PYTHON_VERSION=$(python3 --version | cut -d' ' -f2 | cut -d'.' -f1,2)
+echo -e "${GREEN}✅ Python ${PYTHON_VERSION} detected${NC}"
+
+# Check pip
+if ! python3 -m pip --version &>/dev/null; then
+    echo -e "${RED}❌ pip not found. Please install pip${NC}"
+    exit 1
+fi
+
+echo -e "${GREEN}✅ pip available${NC}"
+echo ""
+
+# Install system dependencies (macOS only)
+if [[ "$OSTYPE" == "darwin"* ]]; then
+    echo -e "${BLUE}📦 Checking system dependencies (macOS)...${NC}"
+    
+    # Check for Homebrew
+    if command -v brew &>/dev/null; then
+        # Install pkg-config and ffmpeg if not present
+        NEED_INSTALL=""
+        
+        if ! brew list pkg-config &>/dev/null 2>&1; then
+            NEED_INSTALL="$NEED_INSTALL pkg-config"
+        fi
+        
+        if ! brew list ffmpeg &>/dev/null 2>&1; then
+            NEED_INSTALL="$NEED_INSTALL ffmpeg"
+        fi
+        
+        if [[ -n "$NEED_INSTALL" ]]; then
+            echo -e "${BLUE}Installing:$NEED_INSTALL${NC}"
+            brew install $NEED_INSTALL --quiet
+            echo -e "${GREEN}✅ System dependencies installed${NC}"
+        else
+            echo -e "${GREEN}✅ System dependencies already installed${NC}"
+        fi
+    else
+        echo -e "${YELLOW}⚠️  Homebrew not found. Install manually if needed:${NC}"
+        echo "  /bin/bash -c \"\$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)\""
+    fi
+fi
+
+echo ""
+
+# Install faster-whisper (recommended)
+echo -e "${BLUE}📦 Installing Faster-Whisper...${NC}"
+
+# Try different installation methods based on Python environment
+if python3 -m pip install faster-whisper --quiet 2>/dev/null; then
+    echo -e "${GREEN}✅ Faster-Whisper installed successfully${NC}"
+elif python3 -m pip install --user --break-system-packages faster-whisper --quiet 2>/dev/null; then
+    echo -e "${GREEN}✅ Faster-Whisper installed successfully (user mode)${NC}"
+else
+    echo -e "${YELLOW}⚠️  Faster-Whisper installation failed, trying Whisper...${NC}"
+    
+    if python3 -m pip install openai-whisper --quiet 2>/dev/null; then
+        echo -e "${GREEN}✅ Whisper installed successfully${NC}"
+    elif python3 -m pip install --user --break-system-packages openai-whisper --quiet 2>/dev/null; then
+        echo -e "${GREEN}✅ Whisper installed successfully (user mode)${NC}"
+    else
+        echo -e "${RED}❌ Failed to install transcription engine${NC}"
+        echo ""
+        echo -e "${YELLOW}Manual installation options:${NC}"
+        echo "  1. Use --break-system-packages (macOS/Homebrew Python):"
+        echo "     python3 -m pip install --user --break-system-packages openai-whisper"
+        echo ""
+        echo "  2. Use virtual environment (recommended):"
+        echo "     python3 -m venv ~/whisper-env"
+        echo "     source ~/whisper-env/bin/activate"
+        echo "     pip install faster-whisper"
+        echo ""
+        echo "  3. Use pipx (isolated):"
+        echo "     brew install pipx"
+        echo "     pipx install openai-whisper"
+        exit 1
+    fi
+fi
+
+# Install UI/progress libraries (tqdm, rich)
+echo ""
+echo -e "${BLUE}📦 Installing UI libraries (tqdm, rich)...${NC}"
+
+if python3 -m pip install tqdm rich --quiet 2>/dev/null; then
+    echo -e "${GREEN}✅ tqdm and rich installed successfully${NC}"
+elif python3 -m pip install --user --break-system-packages tqdm rich --quiet 2>/dev/null; then
+    echo -e "${GREEN}✅ tqdm and rich installed successfully (user mode)${NC}"
+else
+    echo -e "${YELLOW}⚠️  Optional UI libraries not installed (skill will still work)${NC}"
+fi
+
+# Check ffmpeg (optional but recommended)
+echo ""
+if command -v ffmpeg &>/dev/null; then
+    echo -e "${GREEN}✅ ffmpeg already installed${NC}"
+else
+    echo -e "${YELLOW}⚠️  ffmpeg not found (should have been installed earlier)${NC}"
+    if [[ "$OSTYPE" == "darwin"* ]] && command -v brew &>/dev/null; then
+        echo -e "${BLUE}Installing ffmpeg via Homebrew...${NC}"
+        brew install ffmpeg --quiet && echo -e "${GREEN}✅ ffmpeg installed${NC}"
+    else
+        echo -e "${BLUE}ℹ️  ffmpeg is optional but recommended for format conversion${NC}"
+        echo ""
+        echo "Install ffmpeg:"
+        if [[ "$OSTYPE" == "darwin"* ]]; then
+            echo "  brew install ffmpeg"
+        elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
+            echo "  sudo apt install ffmpeg  # Debian/Ubuntu"
+            echo "  sudo yum install ffmpeg  # CentOS/RHEL"
+        fi
+    fi
+fi
+
+# Verify installation
+echo ""
+echo -e "${BLUE}🔍 Verifying installation...${NC}"
+
+if python3 -c "import faster_whisper" 2>/dev/null; then
+    echo -e "${GREEN}✅ Faster-Whisper verified${NC}"
+    TRANSCRIBER="Faster-Whisper"
+elif python3 -c "import whisper" 2>/dev/null; then
+    echo -e "${GREEN}✅ Whisper verified${NC}"
+    TRANSCRIBER="Whisper"
+else
+    echo -e "${RED}❌ No transcription engine found after installation${NC}"
+    exit 1
+fi
+
+# Download initial model (optional)
+read -p "Download Whisper 'base' model now? (recommended, ~74MB) [Y/n]: " DOWNLOAD_MODEL
+
+if [[ ! "$DOWNLOAD_MODEL" =~ ^[Nn] ]]; then
+    echo ""
+    echo -e "${BLUE}📥 Downloading 'base' model...${NC}"
+    
+    python3 << 'EOF'
+try:
+    import faster_whisper
+    model = faster_whisper.WhisperModel("base", device="cpu", compute_type="int8")
+    print("✅ Model downloaded successfully")
+except:
+    try:
+        import whisper
+        model = whisper.load_model("base")
+        print("✅ Model downloaded successfully")
+    except Exception as e:
+        print(f"❌ Model download failed: {e}")
+EOF
+fi
+
+# Success summary
+echo ""
+echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+echo -e "${GREEN}✅ Installation Complete!${NC}"
+echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+echo ""
+echo "📊 Installed components:"
+echo "  • Transcription engine: $TRANSCRIBER"
+if command -v ffmpeg &>/dev/null; then
+    echo "  • Format conversion: ffmpeg (available)"
+else
+    echo "  • Format conversion: ffmpeg (not installed)"
+fi
+echo ""
+echo "🚀 Ready to use! Try:"
+echo "  copilot> transcribe audio to markdown: myfile.mp3"
+echo "  claude> transcreva este áudio: myfile.mp3"
+echo ""