Using the CLI

reader scrape https://example.com

reader scrape https://example.com -o output.json

reader scrape https://example.com https://example.org https://example.net \
  -c 3 \
  -o batch.json

# Markdown only (default)
reader scrape https://example.com

# HTML only
reader scrape https://example.com -f html

# Both
reader scrape https://example.com -f markdown,html

# Include full page content (disable main content extraction)
reader scrape https://example.com --no-main-content

# Keep only specific selectors
reader scrape https://blog.example.com \
  --include-tags ".article,.sidebar" \
  --exclude-tags ".comments,.ads"

# Wait for a specific element before extracting (useful for SPAs)
reader scrape https://spa.example.com --wait-for ".dashboard-loaded"

reader scrape https://example.com \
  --proxy http://user:pass@proxy.example.com:8080

# Discover links only
reader crawl https://docs.example.com -d 2 -m 30

# Crawl and scrape every page
reader crawl https://docs.example.com -d 2 -m 30 --scrape -o docs.json

reader scrape https://example.com -v

reader scrape https://example.com | jq -r '.data[0].markdown'

reader crawl https://docs.example.com --scrape |
  jq -r '.scraped.data[] | .metadata.website.title'

if reader scrape "$URL" -o out.json; then
  echo "Scraped successfully"
else
  echo "Scrape failed"
  exit 1
fi