avinash · March 12, 2021 07:09
diff --git a/gistfile1.txt b/gistfile1.txt
 # Step 1: Download the HTML file corresponding to a year
 wget "https://papers.gceguide.com/A%20Levels/Mathematics%20(9709)/2020/" -O 2020.html

 # Step 2: Use sed, tr and awk to clean the HTML file so that we only have the names of the PDF files and download them individually with wget
 cat 2020.html | sed 's/<li class=.file.>/£/g' | tr '£' '\n' | grep pdf | sed 's/^.*class=.name.>//g' | sed 's/<.*$//g' | awk '{ print "wget \"https://papers.gceguide.com/A%20Levels/Mathematics%20(9709)/2020/" $0 "\"" }' | bash
	# Step 1: Download the HTML file corresponding to a year
	wget "https://papers.gceguide.com/A%20Levels/Mathematics%20(9709)/2020/" -O 2020.html

	# Step 2: Use sed, tr and awk to clean the HTML file so that we only have the names of the PDF files and download them individually with wget
	cat 2020.html \| sed 's/<li class=.file.>/£/g' \| tr '£' '\n' \| grep pdf \| sed 's/^.class=.name.>//g' \| sed 's/<.$//g' \| awk '{ print "wget \"https://papers.gceguide.com/A%20Levels/Mathematics%20(9709)/2020/" $0 "\"" }' \| bash