Here are a variety of shell scripts you can use to strip out different elements.
# doctype
find . -regex ".*\.\(html\|py\)$" -type f -exec sed -i "s/<\!DOCTYPE\s\+html[^>]*>/<\!DOCTYPE html>/gi" {} \;
# meta charset
find . -regex ".*\.\(html\|py\)$" -type f -exec sed -i "s/<meta[^>]*content=[\"'][^\"']*utf-8[\"'][^>]*>/<meta charset=\"utf-8\">/gi" {} \;
# script text/javascript
find . -regex ".*\.\(html\|py\)$" -type f -exec sed -i "s/\(<script[^>]*\)\(\stype=[\"']text\/javascript[\"']\)\(\s\?[^>]*>\)/\1\3/gi" {} \;
# style text/css
find . -regex ".*\.\(html\|py\)$" -type f -exec sed -i "s/\(<style[^>]*\)\(\stype=[\"']text\/css[\"']\)\(\s\?[^>]*>\)/\1\3/gi" {} \;
# html xmlns
find . -regex ".*\.\(html\|py\)$" -type f -exec sed -i "s/\(<html[^>]*\)\(\sxmlns=[\"'][^\"']*[\"']\)\(\s\?[^>]*>\)/\1\3/gi" {} \;
# html xml:lang
find . -regex ".*\.\(html\|py\)$" -type f -exec sed -i "s/\(<html[^>]*\)\(\sxml:lang=[\"'][^\"']*[\"']\)\(\s\?[^>]*>\)/\1\3/gi" {} \;