Helpfull commands & patterns

# SED replace all html tags
sed -e 's/<[^>]*>//g'

# SED multiple divided by ;
sed 's/ab/~/g; s/bc/ab/g; s/~/bc/g'

# SED delete empty lines
sed '/^\s*$/d' 

# SED delete all lines except pattern 
sed '/pattern/!d'

# SED get all HTML links
sed -n 's/.*href="\([^"]*\).*/\1/p' file.txt

# SED extract links from sitemap
grep -Po 'http(s?)://[^ \"()\<>]*' file.xml > file_extracted.xml

# WGET download from text file
wget -b -e robots=off --wait 1 --limit-rate=300k -i sitemap.xml --user-agent="Mozilla/5.0 (X11; U; Linux i686; en-US; │rv:1.9.0.3) Gecko/2008092416 Firefox/3.0.3"

# Linux - Removes all tags in all xml and pattern in files in folder
find . -name "*.xml" -type f -exec sed -i 's/<[^>]*>//g; /pattern/d' {} \;

# Linux count lines
ls -1 | wc -l 

# AWK - Remove duplicate lines
awk '!seen[$0]++' file.txt > newfile.txt

# REGEX until
(?:(?!/).)*

# REGEX html tags pattern
<[^>]*>

# REGEX last occurence -
.*\-

# REGEX after
[^/]+$