diff --git a/Makefile b/Makefile index 109435a..5c29f50 100644 --- a/Makefile +++ b/Makefile @@ -4,3 +4,6 @@ help: pdftotext: @find ./data -iname '*.pdf' -execdir pdftotext {} \; @find ./data -not \( -path ./data/text -prune \) -iname '*.txt' -exec mv {} './data/text/' ';' + +extract: + @perl extract_urls.pl data/text/*.txt