GetWebsiteFromArchiveOrg.sh

# Download the site (exclude fonts/icons) from WaybackMachine! https://web.archive.org/
# Replace <TIMESPAMP> and example.com

wget --mirror \
     --convert-links \
     --adjust-extension \
     --page-requisites \
     --no-parent \
     --cut-dirs=3 \
     --restrict-file-names=unix \
     -e robots=off \
     --user-agent="Mozilla/5.0" \
     --reject-regex '/web/[0-9]+/https?://(fonts\.googleapis\.com|use\.fontawesome\.com)/' \
     "https://web.archive.org/web/<TIMESTAMP>/http://example.com/"

# Clean primary domain URLs
# Replace and example.com
find example.com/ -type f \( -name "*.html" -o -name "*.css" -o -name "*.js" \) \
  -exec sed -i -E 's#/web/[0-9]{14}/https?://(www\.)?example\.com/#/#g' {} \;

# Convert external domains to live URLs (fonts/icons)
# Replace and example.com
# Add / replace the urls from external websites
find example.com/ -type f \( -name "*.html" -o -name "*.css" -o -name "*.js" \) \
  -exec sed -i -E 's#/web/[0-9]{14}/https?://(fonts\.googleapis\.com|use\.fontawesome\.com)/#https://\1/#g' {} \;