aboutsummaryrefslogtreecommitdiff
path: root/scripts/bin/extract-urls
blob: b925e868f5e74b3cbf0379d7d57688432d36123f (plain) (blame)
1
2
3
4
5
6
7
8
#!/usr/bin/env bash

REGEX="(https?://|www\\.)[\.A-Za-z0-9\-]+\\.[a-zA-Z]{2,4}(/[^ ]*)?"

while read line; do echo "$line"; done | \
  egrep -o "$REGEX" | \
  awk '!seen[$0]++';