diff options
Diffstat (limited to 'scripts/bin/extract-urls')
| -rwxr-xr-x | scripts/bin/extract-urls | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/scripts/bin/extract-urls b/scripts/bin/extract-urls new file mode 100755 index 0000000..b925e86 --- /dev/null +++ b/scripts/bin/extract-urls @@ -0,0 +1,8 @@ +#!/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]++'; + |
