Created
February 29, 2016 04:21
-
-
Save tokorom/e7cc040943dfb0756abb to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
find . -name "index.html" > files.txt | |
for i in `cat files.txt`; do egrep -o '[a-zA-Z][a-zA-Z0-9_]{3,}[a-zA-Z0-9]' $i | sed '/\//d' | sort | uniq >> keyword_raw.txt ;done | |
cat keyword_raw.txt | sort | uniq > keyword.txt | |
for i in `cat files.txt`; do egrep -o '[a-zA-Z][a-zA-Z0-9]{3,}\([a-zA-Z0-9_: ]{0,}\)' $i | sed '/\//d' | sort | uniq >> method_raw.txt ;done | |
cat method_raw.txt | sort | uniq > method.txt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment