Box Scores from MLB.com

box_scores.r

#	References: 

# http://www.r-bloggers.com/mlb-baseball-pitching-matchups-downloading-pitch-fx-data-using-the-xml-package-in-r%C2%A0updatedx6/
# http://blogisticreflections.wordpress.com/2009/10/04/using-r-to-analyze-baseball-games-in-real-time/


# http://gd2.mlb.com/components/game/mlb/year_2010/month_10/day_12/miniscoreboard.xml

################################################################################
#   Program Name:     xml-mlb-gameday.R
#   Author:           Erik
#   Created:          10/04/2009
#
#
#   Purpose:          show current scoreboard in R
#
################################################################################

## need XML package, may need to install w/ install.packages()
library(XML)

## create a boxscore object from an XML description of a game
createBoxScore <- function(x) {
  status <- if(x$.attrs["status"] != "In Progress")
    "Final" else if(x$.attrs["top_inning"] == "Y")
      "Top" else "Bot"

  bs <- list(status = status,
             inning = as.numeric(x$.attrs["inning"]),
             away.team = x$.attrs["away_name_abbrev"],
             away.runs = as.numeric(x$.attrs["away_team_runs"]),
             away.hits = as.numeric(x$.attrs["away_team_hits"]),
             away.errors = as.numeric(x$.attrs["away_team_errors"]),
             home.team = x$.attrs["home_name_abbrev"],
             home.runs = as.numeric(x$.attrs["home_team_runs"]),
             home.hits = as.numeric(x$.attrs["home_team_hits"]),
             home.errors = as.numeric(x$.attrs["home_team_errors"]))
  class(bs) <- "boxscore"
  bs
}

## print the boxscore object in traditional format
print.boxscore <- function(x, ...) {
  cat("     ", "R   ", "H  ", "E (",
      x$status, " ",
      x$inning, ")\n",
      format(x$away.team, width = 3), " ",
      format(x$away.runs, width = 2), "  ",
      format(x$away.hits, width = 2), "  ",
      x$away.errors, "\n",
      format(x$home.team, width = 3), " ",
      format(x$home.runs, width = 2), "  ",
      format(x$home.hits, width = 2), "  ",
      x$home.errors, "\n\n", sep = "")
}

## utility function ...
as.data.frame.boxscore <- function(x, row.names, optional, ...) {
  class(x) <- "list"
  as.data.frame(x)
}

## This is the "user accessible" public function you should be calling!
## downloads the XML data, and prints out boxscores for games on "date"
boxscore <- function(date = Sys.Date()) {
  if(date > Sys.Date())
    stop("Cannot retrieve scores from the future.")

  year  <- paste("year_", format(date, "%Y"), "/", sep = "")
  month <- paste("month_", format(date, "%m"), "/", sep = "")
  day   <- paste("day_", format(date, "%d"), "/", sep = "")

  xmlFile <-
    paste("http://gd2.mlb.com/components/game/mlb/",
          year, month, day, "miniscoreboard.xml", sep = "")
  xmlTree <- xmlTreeParse(xmlFile, useInternalNodes = TRUE)
  xp <- xpathApply(xmlTree, "//game")
  xmlList <- lapply(xp, xmlToList)

  bs.list <- lapply(xmlList, createBoxScore)
  names(bs.list) <-
    paste(sapply(bs.list, "[[", "away.team"),
                 "@",
          sapply(bs.list, "[[", "home.team"))
  bs.list
}

gamexml <- function(date = Sys.Date()) {
  if(date > Sys.Date())
    stop("Cannot retrieve scores from the future.")

  year  <- paste("year_", format(date, "%Y"), "/", sep = "")
  month <- paste("month_", format(date, "%m"), "/", sep = "")
  day   <- paste("day_", format(date, "%d"), "/", sep = "")

  xmlFile <-
    paste("http://gd2.mlb.com/components/game/mlb/",
          year, month, day, "miniscoreboard.xml", sep = "")
  xmlTree <- xmlTreeParse(xmlFile, useInternalNodes = TRUE)
  xp <- xpathApply(xmlTree, "//game")
 xp
}





bs <- boxscore(date = Sys.Date()-1)

bs.df <- do.call(rbind, lapply(bs, as.data.frame))

bs.df$updated <-  Sys.time() 
write.table(bs.df,file="~/Dropbox/Public/boxscore.csv",sep=",",na="",row.names=FALSE)
write.table(bs.df,file="~/Dropbox/Public/boxscore.txt",sep="\t",na="",row.names=FALSE)