Download How We Roll episodes from RSS feed with better titles.

expanded_download-HowWeRoll.sh

#!/bin/bash
# Related one-line script: https://gist.github.com/fiskr/b0c01bbcbd2aefaa726d46bea30a3307
dataFile="urls.dat"
rssUrl="https://rss.simplecast.com/podcasts/3236/rss" # How We Roll podcast

# Download the RSS feed for episodes of the How We Roll Podcast
# then, retrieve from the HTML just the episode titles and URLs
# then, exclude subtitles, since we don't need those
# then, parse the URL from the attribute of the node
# then, delete all node tags, e.g. <title>
# then, get rid of unnecessary, leading whitespace
# then, get the title and URL separated only by a "|" character
# then, break them up into individual lines for each URL, in the format of "title | url"
# finally, clean up any lines that had no URLs in them by removing up to the last "X | Y" instance
curl $rssUrl | \
	grep -E "title|mp3" | \
  grep -v subtitle | \
	perl -pe 's/.*?url="([^"]+)".*/$1/g' 	| \
  perl -pe 's/<.*?>//g' 	| \
  perl -pe 's/^      //g'  | \
  perl -pe 's/\n/ | /g' | \
  perl -pe 's/mp3 \| /mp3 \n/g' | \
	perl -pe 's/.*? \| ([^\|]+? \| [^\|]+)$/$1/g' \
	> $dataFile \

IFS=$'\n' # make newlines the only separator
for line in $(cat ./$dataFile); do
    echo "$line"
		fileName="$(echo $line | perl -pe 's/^(.+?) \|.*?$/$1/g' | perl -pe 's/[\s]/_/g' | perl -pe 's/_-_/-/g' | perl -pe 's/__/_/g' | perl -pe 's/_-/-/g' | perl -pe 's/_$//g').mp3"
		echo "Filename: $fileName"
		url="$(echo $line | perl -pe 's/.*? \| (.*?.mp3)[\s]*?$/$1/g')"
		echo "URL: $url"
		wget -O $fileName $url
done

# Delete the temporary file with titles and URLs
rm $dataFile