extract_urls (304B)
1 #!/usr/bin/awk -f 2 { 3 if (split($0, words, " ")) { 4 for (word in words) { 5 if (match(words[word], /(http|https|ftp|gopher):\/\/[A-z0-9\-\/\.\?=%:]+[^'.:\r\?]/)) { 6 url = substr(words[word], RSTART, RLENGTH) 7 if (!urls[url]++) 8 print url 9 } 10 } 11 } 12 } 13 14 END { 15 if (length(urls) < 1) 16 exit 1 17 }