#!/bin/bash# Take a list of URLs in a file and fetch them# Then extract all text with Links Browser# Then zip them# usage ./script.sh http://example.com/sitemap.html# extract all URLs from the sitemap page (list of pages on the Web site)links -dump $1 | egrep -o "http:.*\.aspx" >urls.txtwhile read inputlinedo# read a URL out of the fileurl="$(echo $inputline)"# get the filewget $url # extract the text from the file and save as .txt# this line doesn't work because $url is not the filename, e.g., page.aspxlinks -dump $url >$url.txt# delete the .aspx filerm $url# read from urls.txtdone < urls.txt# zip all of the text files for export into plagiarism toolzip website.zip *.txt