command -v reader

npm install -g @mozilla/readability-cli
# or
npm install -g reader-cli

command -v trafilatura

pip3 install trafilatura

# Extract article
reader "URL" > article.txt

# Extract article
trafilatura --URL "URL" --output-format txt > article.txt

# Or with more options
trafilatura --URL "URL" --output-format txt --no-comments --no-tables > article.txt

# Download and extract basic content
curl -s "URL" | python3 -c "
from html.parser import HTMLParser
import sys

class ArticleExtractor(HTMLParser):
    def __init__(self):
        super().__init__()
        self.in_content = False
        self.content = []
        self.skip_tags = {'script', 'style', 'nav', 'header', 'footer', 'aside'}
        self.current_tag = None

    def handle_starttag(self, tag, attrs):
        if tag not in self.skip_tags:
            if tag in {'p', 'article', 'main', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'}:
                self.in_content = True
                self.current_tag = tag

    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())
" > article.txt

# reader outputs markdown with title at top
TITLE=$(reader "URL" | head -n 1 | sed 's/^# //')

# Get metadata including title
TITLE=$(trafilatura --URL "URL" --json | python3 -c "import json, sys; print(json.load(sys.stdin)['title'])")

TITLE=$(curl -s "URL" | grep -oP '<title>\K[^<]+' | sed 's/ - .*//' | sed 's/ | .*//')

# Get title
TITLE="Article Title from Website"

# Clean for filesystem (remove special chars, limit length)
FILENAME=$(echo "$TITLE" | tr '/' '-' | tr ':' '-' | tr '?' '' | tr '"' '' | tr '<' '' | tr '>' '' | tr '|' '-' | cut -c 1-100 | sed 's/ *$//')

# Add extension
FILENAME="${FILENAME}.txt"

ARTICLE_URL="https://example.com/article"

# Check for tools
if command -v reader &> /dev/null; then
    TOOL="reader"
    echo "Using reader (Mozilla Readability)"
elif command -v trafilatura &> /dev/null; then
    TOOL="trafilatura"
    echo "Using trafilatura"
else
    TOOL="fallback"
    echo "Using fallback method (may be less accurate)"
fi

# Extract article
case $TOOL in
    reader)
        # Get content
        reader "$ARTICLE_URL" > temp_article.txt
        # Get title (first line after # in markdown)
        TITLE=$(head -n 1 temp_article.txt | sed 's/^# //')
        ;;
    trafilatura)
        # Get title from metadata
        METADATA=$(trafilatura --URL "$ARTICLE_URL" --json)
        TITLE=$(echo "$METADATA" | python3 -c "import json, sys; print(json.load(sys.stdin).get('title', 'Article'))")
        # Get clean content
        trafilatura --URL "$ARTICLE_URL" --output-format txt --no-comments > temp_article.txt
        ;;
    fallback)
        # Get title
        TITLE=$(curl -s "$ARTICLE_URL" | grep -oP '<title>\K[^<]+' | head -n 1)
        TITLE=${TITLE%% - *}  # Remove site name
        TITLE=${TITLE%% | *}  # Remove site name (alternate)
        # Get content (basic extraction)
        curl -s "$ARTICLE_URL" | python3 -c "
from html.parser import HTMLParser
import sys

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

    def handle_starttag(self, tag, attrs):
        if tag not in self.skip_tags:
            if tag in {'p', 'article', 'main'}:
                self.in_content = True
            if tag in {'h1', 'h2', 'h3'}:
                self.content.append('\\n')

    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

# Clean filename
FILENAME=$(echo "$TITLE" | tr '/' '-' | tr ':' '-' | tr '?' '' | tr '"' '' | tr '<>' '' | tr '|' '-' | cut -c 1-80 | sed 's/ *$//' | sed 's/^ *//')
FILENAME="${FILENAME}.txt"

# Move to final filename
mv temp_article.txt "$FILENAME"

# Show result
echo "✓ Extracted article: $TITLE"
echo "✓ Saved to: $FILENAME"
echo ""
echo "Preview (first 10 lines):"
head -n 10 "$FILENAME"

# User: "Extract https://example.com/article"
reader "https://example.com/article" > temp.txt
TITLE=$(head -n 1 temp.txt | sed 's/^# //')
FILENAME="$(echo "$TITLE" | tr '/' '-').txt"
mv temp.txt "$FILENAME"
echo "✓ Saved to: $FILENAME"

if ! reader "$URL" > temp.txt 2>/dev/null; then
    if command -v trafilatura &> /dev/null; then
        trafilatura --URL "$URL" --output-format txt > temp.txt
    else
        echo "Error: Could not extract article. Install reader or trafilatura."
        exit 1
    fi
fi