ec2_instances.R

library("rvest")
library("dplyr")

ec2_df <- html("http://www.ec2instances.info") %>%
  html_nodes("table") %>% 
  first %>% 
  html_table()

str(ec2_df)

## 'data.frame':    42 obs. of  16 variables:
##  $ Name                : chr  "M1 General Purpose Small" "M1 General Purpose Medium" "M1 General Purpose Large" "M1 General Purpose Extra Large" ...
##  $ API Name            : chr  "m1.small" "m1.medium" "m1.large" "m1.xlarge" ...
##  $ Memory              : chr  "1.7 GB" "3.75 GB" "7.5 GB" "15.0 GB" ...
##  $ Compute Units (ECU) : chr  "1 units" "2 units" "4 units" "8 units" ...
##  $ Cores               : chr  "1 cores" "1 cores" "2 cores" "4 cores" ...
##  $ ECU per Core        : chr  "1 units" "2 units" "2 units" "2 units" ...
##  $ Storage             : chr  "160 GB" "410 GB" "840 GB\n              (2 * 420 GB)" "1680 GB\n              (4 * 420 GB)" ...
##  $ Arch                : chr  "32/64-bit" "32/64-bit" "64-bit" "64-bit" ...
##  $ I/O Performance     : chr  "Low" "Moderate" "Moderate\n               / 500 Mbps" "High\n               / 1000 Mbps" ...
##  $ Max IPs             : int  8 12 30 60 12 60 240 240 60 120 ...
##  $ Enhanced Networking : chr  "No" "No" "No" "No" ...
##  $ Linux Virtualization: chr  "PV" "PV" "PV" "PV" ...
##  $ Linux cost          : chr  "$0.044 per hour" "$0.087 per hour" "$0.175 per hour" "$0.350 per hour" ...
##  $ Windows cost        : chr  "$0.075 per hour" "$0.149 per hour" "$0.299 per hour" "$0.598 per hour" ...
##  $ Windows SQL Web cost: chr  "$0.139 per hour" "$0.237 per hour" "$0.435 per hour" "$0.830 per hour" ...
##  $ Windows SQL Std cost: chr  "$0.629 per hour" "$0.744 per hour" "$0.955 per hour" "$1.362 per hour" ...