library(XML)
library(RCurl)
library(ggplot2)

results <- c()

## Loop through the 30 pages of player data
for(i in 1:30){
  theURL <- paste("http://www.nhl.com/ice/playerstats.htm?fetchKey=20122ALLSASAll&viewName=summary&sort=points&pg=", i, sep="")
  webpage <- getURL(theURL)
  h<-htmlParse(webpage)
  stats <- xmlToDataFrame(nodes = getNodeSet(h, "//tbody//tr"))[,-1]
  
  ## Grab the column names only on the first iteration
  if(i == 1){
    nodes<-getNodeSet(h, "//table [@summary='2011-2012 - Regular Season - Skater - Summary - Points']
                  //thead//tr//th//a[@title]")
    cols <- as.character(xmlToDataFrame(nodes)[,1])
    column.names <- gsub("\\n", "", cols)
    
    ## Append columns since any sorted column and Team column do not appear in a structured format in the HTML
    column.names<-append(column.names, "Team", after=1)
    column.names<-append(column.names, "P", after=6)
    
    ## Clean up column names so they are R-friendly
    column.names[8] <- "Plus.Minus"
    column.names[15] <- "Shooting.Percentage"
    column.names[16] <- "Time.On.Ice.Per.Game"
    column.names[17] <- "Avg.Shifts.Per.Game"
    column.names[18] <- "Faceoff.Win.Percentage"
    results <- rbind(results, stats)
    colnames(results) <- column.names
  }
  colnames(stats) <- column.names
  results <- rbind(results, stats)
}

## Remove plus signs from +/- so we can treat it as a number
results$Plus.Minus <- as.numeric(gsub("\\+", "", results$Plus.Minus))

## Format factors as numeric data types
results[,c(4:15, 17:18)] <- apply(results[,c(4:15, 17:18)], 2, function(x) as.numeric(as.character(x)))
results <- results[match(unique(results$Player ), results$Player),]

## We only care about the first Team listed and not if that player was on multiple teams in 2011-12
results$Team <- gsub("\\,\\s+\\w+", "", as.character(s.results$Team))

## Pull out a team to visualize
t.results <- subset(s.results, Team == "BOS")

## Plot the data and save in a PDF
pdf(file="Bruins.pdf", width=11, height=8)
ggplot(t.results, aes(x=Plus.Minus, y=P, size=Avg.Shifts.Per.Game, colour=Pos, label=Player)) +  geom_text() +
  labs(x="+/-", y="Points", title= t.results$Team)
dev.off()