#!/bin/bash

# Joe Gillotti - 3/26/2012
# Save *all* videos from red tube

# Our user agent, so it doesn't look like we're curl
agent="Mozilla/5.0 (Windows NT 5.1; rv:10.0.2) Gecko/20100101 Firefox/10.0.2"

# The first page to start at
page="http://www.redtube.com/"

# Go forever..
while :; do 

	# Get all video id links on this page
	nums=`curl -s --user-agent "$agent" "$page" | egrep 'href="\/[0-9]+"' | grep -v class | sed 's/^[\t]*|//g' | cut -d\" -f2  | sed 's/\///'`

	# Go through all of them
	for i in $nums; do
		
		# URL to .mp4 file with the special session key at the end
		vid=`curl -s --user-agent "$agent" http://www.redtube.com/$i | grep videos.mp4.redtubefiles.com | grep -v param | cut -d\' -f2 | grep -v src`

		# Name of video
		name=`curl -s --user-agent "$agent" http://www.redtube.com/$i | grep '<title>' | cut -d\> -f2 | cut -d\| -f 1`

		# Path to save it to
		fn=vids/`echo "$name" | sed 's/^[\t]*//g' | sed 's/[\t]*$//g' | sed 's/ /_/g'`.mp4

		# Do we already have it? 
		if [ -f "$fn" ]; then
			echo Skipping $fn

		# No; save it!
		else 
			echo Saving... "$name"
			curl --stderr - -s --user-agent "$agent" --referer http://www.redtube.com/$i "$vid" -o "$fn" 
		fi
	done

	# Get URL of next page so we can do all their pages!
	page=`curl -s --user-agent "$agent" "$page"  | sed 's/<a/\n<a/g' | grep 'Next Page' | cut -d\" -f8`

	if [ -z "$page" ]; then
		echo Out of pages? 
		exit 1
	fi

	sleep 1
	echo Next page is $page
done