URL="$1"

# Check for YouTube
if [[ "$URL" =~ youtube\.com/watch || "$URL" =~ youtu\.be/ || "$URL" =~ youtube\.com/shorts ]]; then
    CONTENT_TYPE="youtube"

# Check for PDF
elif [[ "$URL" =~ \.pdf$ ]]; then
    CONTENT_TYPE="pdf"

# Check if URL returns PDF
elif curl -sI "$URL" | grep -i "Content-Type: application/pdf" > /dev/null; then
    CONTENT_TYPE="pdf"

# Default to article
else
    CONTENT_TYPE="article"
fi

echo "📍 Detected: $CONTENT_TYPE"

# Use youtube-transcript skill workflow
echo "📺 Extracting YouTube transcript..."

# 1. Check for yt-dlp
if ! command -v yt-dlp &> /dev/null; then
    echo "Installing yt-dlp..."
    brew install yt-dlp
fi

# 2. Get video title
VIDEO_TITLE=$(yt-dlp --print "%(title)s" "$URL" | tr '/' '_' | tr ':' '-' | tr '?' '' | tr '"' '')

# 3. Download transcript
yt-dlp --write-auto-sub --skip-download --sub-langs en --output "temp_transcript" "$URL"

# 4. Convert to clean text (deduplicate)
python3 -c "
import sys, re
seen = set()
vtt_file = 'temp_transcript.en.vtt'
try:
    with open(vtt_file, 'r') as f:
        for line in f:
            line = line.strip()
            if line and not line.startswith('WEBVTT') and not line.startswith('Kind:') and not line.startswith('Language:') and '-->' not in line:
                clean = re.sub('<[^>]*>', '', line)
                clean = clean.replace('&amp;', '&').replace('&gt;', '>').replace('&lt;', '<')
                if clean and clean not in seen:
                    print(clean)
                    seen.add(clean)
except FileNotFoundError:
    print('Error: Could not find transcript file', file=sys.stderr)
    sys.exit(1)
" > "${VIDEO_TITLE}.txt"

# 5. Cleanup
rm -f temp_transcript.en.vtt

CONTENT_FILE="${VIDEO_TITLE}.txt"
echo "✓ Saved transcript: $CONTENT_FILE"

# Use article-extractor skill workflow
echo "📄 Extracting article content..."

# 1. Check for extraction tools
if command -v reader &> /dev/null; then
    TOOL="reader"
elif command -v trafilatura &> /dev/null; then
    TOOL="trafilatura"
else
    TOOL="fallback"
fi

echo "Using: $TOOL"

# 2. Extract based on tool
case $TOOL in
    reader)
        reader "$URL" > temp_article.txt
        ARTICLE_TITLE=$(head -n 1 temp_article.txt | sed 's/^# //')
        ;;

    trafilatura)
        METADATA=$(trafilatura --URL "$URL" --json)
        ARTICLE_TITLE=$(echo "$METADATA" | python3 -c "import json, sys; print(json.load(sys.stdin).get('title', 'Article'))")
        trafilatura --URL "$URL" --output-format txt --no-comments > temp_article.txt
        ;;

    fallback)
        ARTICLE_TITLE=$(curl -s "$URL" | grep -oP '<title>\K[^<]+' | head -n 1)
        ARTICLE_TITLE=${ARTICLE_TITLE%% - *}
        curl -s "$URL" | python3 -c "
from html.parser import HTMLParser
import sys

class ArticleExtractor(HTMLParser):
    def __init__(self):
        super().__init__()
        self.content = []
        self.skip_tags = {'script', 'style', 'nav', 'header', 'footer', 'aside', 'form'}
        self.in_content = False

    def handle_starttag(self, tag, attrs):
        if tag not in self.skip_tags and tag in {'p', 'article', 'main'}:
            self.in_content = True

    def handle_data(self, data):
        if self.in_content and data.strip():
            self.content.append(data.strip())

    def get_content(self):
        return '\n\n'.join(self.content)

parser = ArticleExtractor()
parser.feed(sys.stdin.read())
print(parser.get_content())
" > temp_article.txt
        ;;
esac

# 3. Clean filename
FILENAME=$(echo "$ARTICLE_TITLE" | tr '/' '-' | tr ':' '-' | tr '?' '' | tr '"' '' | cut -c 1-80 | sed 's/ *$//')
CONTENT_FILE="${FILENAME}.txt"
mv temp_article.txt "$CONTENT_FILE"

echo "✓ Saved article: $CONTENT_FILE"

# Download and extract PDF
echo "📑 Downloading PDF..."

# 1. Download PDF
PDF_FILENAME=$(basename "$URL")
curl -L -o "$PDF_FILENAME" "$URL"

# 2. Extract text using pdftotext (if available)
if command -v pdftotext &> /dev/null; then
    pdftotext "$PDF_FILENAME" temp_pdf.txt
    CONTENT_FILE="${PDF_FILENAME%.pdf}.txt"
    mv temp_pdf.txt "$CONTENT_FILE"
    echo "✓ Extracted text from PDF: $CONTENT_FILE"

    # Optionally keep PDF
    echo "Keep original PDF? (y/n)"
    read -r KEEP_PDF
    if [[ ! "$KEEP_PDF" =~ ^[Yy]$ ]]; then
        rm "$PDF_FILENAME"
    fi
else
    # No pdftotext available
    echo "⚠️  pdftotext not found. PDF downloaded but not extracted."
    echo "   Install with: brew install poppler"
    CONTENT_FILE="$PDF_FILENAME"
fi

# Read the extracted content
CONTENT_FILE="[from previous step]"

# Invoke ship-learn-next skill logic:
# 1. Read the content file
# 2. Extract core actionable lessons
# 3. Create 5-rep progression plan
# 4. Save as: Ship-Learn-Next Plan - [Quest Title].md

# See ship-learn-next/SKILL.md for full details

✅ Tapestry Workflow Complete!

📥 Content Extracted:
   ✓ [Content type]: [Title]
   ✓ Saved to: [filename.txt]
   ✓ [X] words extracted

📋 Action Plan Created:
   ✓ Quest: [Quest title]
   ✓ Saved to: Ship-Learn-Next Plan - [Title].md

🎯 Your Quest: [One-line summary]

📍 Rep 1 (This Week): [Rep 1 goal]

When will you ship Rep 1?

#!/bin/bash

# Tapestry: Extract content + create action plan
# Usage: tapestry <URL>

URL="$1"

if [ -z "$URL" ]; then
    echo "Usage: tapestry <URL>"
    exit 1
fi

echo "🧵 Tapestry Workflow Starting..."
echo "URL: $URL"
echo ""

# Step 1: Detect content type
if [[ "$URL" =~ youtube\.com/watch || "$URL" =~ youtu\.be/ || "$URL" =~ youtube\.com/shorts ]]; then
    CONTENT_TYPE="youtube"
elif [[ "$URL" =~ \.pdf$ ]] || curl -sI "$URL" | grep -iq "Content-Type: application/pdf"; then
    CONTENT_TYPE="pdf"
else
    CONTENT_TYPE="article"
fi

echo "📍 Detected: $CONTENT_TYPE"
echo ""

# Step 2: Extract content
case $CONTENT_TYPE in
    youtube)
        echo "📺 Extracting YouTube transcript..."
        # [YouTube extraction code from above]
        ;;

    article)
        echo "📄 Extracting article..."
        # [Article extraction code from above]
        ;;

    pdf)
        echo "📑 Downloading PDF..."
        # [PDF extraction code from above]
        ;;
esac

echo ""

# Step 3: Create action plan
echo "🚀 Creating Ship-Learn-Next action plan..."
# [Plan creation using ship-learn-next skill]

echo ""
echo "✅ Tapestry Workflow Complete!"
echo ""
echo "📥 Content: $CONTENT_FILE"
echo "📋 Plan: Ship-Learn-Next Plan - [title].md"
echo ""
echo "🎯 Next: Review your action plan and ship Rep 1!"

User: tapestry https://www.youtube.com/watch?v=dQw4w9WgXcQ

Claude:
🧵 Tapestry Workflow Starting...
📍 Detected: youtube
📺 Extracting YouTube transcript...
✓ Saved transcript: Never Gonna Give You Up.txt

🚀 Creating action plan...
✓ Quest: Master Video Production
✓ Saved plan: Ship-Learn-Next Plan - Master Video Production.md

✅ Complete! When will you ship Rep 1?

User: weave https://example.com/how-to-build-saas

Claude:
🧵 Tapestry Workflow Starting...
📍 Detected: article
📄 Extracting article...
✓ Using reader (Mozilla Readability)
✓ Saved article: How to Build a SaaS.txt

🚀 Creating action plan...
✓ Quest: Build a SaaS MVP
✓ Saved plan: Ship-Learn-Next Plan - Build a SaaS MVP.md

✅ Complete! When will you ship Rep 1?

User: help me plan https://example.com/research-paper.pdf

Claude:
🧵 Tapestry Workflow Starting...
📍 Detected: pdf
📑 Downloading PDF...
✓ Downloaded: research-paper.pdf
✓ Extracted text: research-paper.txt

🚀 Creating action plan...
✓ Quest: Apply Research Findings
✓ Saved plan: Ship-Learn-Next Plan - Apply Research Findings.md

✅ Complete! When will you ship Rep 1?