AtcSearch.R

require(gdata)
require("RCurl")
require("XML")


AtcSearch <- function(AtcCodes){
  #Function inside a function is bad practice...
  #DummySearch searches for one atc code
  DummySearch <- function(Code){  
  	#A link to WHO search
    htmlLink <- paste("http://www.whocc.no/atc_ddd_index/?code=", Code, sep="")
    doc <- htmlParse(getURL(htmlLink))
    Drug <- xpathSApply(doc, "//td", xmlValue)
    
    #No idea why these three are needed
    Drug <- gsub("Â", "", Drug)
    Drug <- gsub("\\s", " ", Drug)
    Drug <- trim(Drug) #gdata just for this...
    
    #if no drug is found, returning NULL
    if(sum(Drug == Code) == 0 | length(Drug) == 0) return()
    
    atcLevels <- xpathSApply(doc, "//b", xmlValue)
    out <- matrix(Drug[which(Drug == Code):length(Drug)], ncol= which(Drug == Code)-1, byrow=TRUE)
    #Basic handling of multiple DDDs and Units
    if(nrow(out) > 1) out <- t(apply(out, 2, function(x) paste(x[x != ""], collapse="/")))
    out <- data.frame(out, t(atcLevels))
    colnames(out) <- c(Drug[1:6], "Anatomical", "Therapeutic", "Subgroup", "ChemicalSubgroup")
    out 
  }
  
  #lapply to get all the codes.
  ret <- lapply(AtcCodes, DummySearch)   
  do.call("rbind", ret) 
}

#Some examples

AtcSearch("N01AX15")
AtcSearch(c("B01AA01", "N01AX15"))

#Not perfect for example, the who database isn't complete.
AtcSearch("QN01AX99")