Copy HTML table with multiple pages using R

Question

I am trying to create a data frame while clearing from the Internet. But there are a few pages that make up the table I'm trying to clear. the same link, but the page is different.

for the first page, here is how I clean it:

library(XML)
CB.13<- "http://www.nfl.com/stats/categorystats?tabSeq=1&season=2013&seasonType=REG&experience=&Submit=Go&archive=false&conference=null&d-447263-p=1&statisticPositionCategory=DEFENSIVE_BACK&qualified=true"
CB.13<- readHTMLTable(CB.13, header=FALSE)
cornerback.function<- function(CB.13){
  first<- "1"
  last<- "1"
  for (i in 1:length(CB.13)){
    lastrow<- nrow(CB.13[[i]])
    lastcol<- ncol(CB.13[[i]])
    if(as.numeric(CB.13[[i]] [1,1]) ==first & as.numeric(CB.13[[i]] [lastrow, lastcol]) ==last) {
      tab <- i
    }
  }
}
cornerback.function(CB.13)
cornerbacks.2013<- CB.13[[tab]]
cb.names<- c("Rk", "name", "Team", "Pos", "Comb", "Total", "Ast", "Sck", "SFTY", "PDef", "Int", "TDs", "Yds", "Lng", "FF", "Rec", "TD")
names(cornerbacks.2013)<- cb.names

I need to do this for several years, all with several pages. So is there a faster way to get all data pages instead of doing this for every single page of the table and merging them? the following link will be http://www.nfl.com/stats/categorystats?tabSeq=1&season=2013&seasonType=REG&Submit=Go&experience=&archive=false&conference=null&d-447263-p=2&statisticPositionCategory=DEFENSIVE_BACK&qualified

8 - , for loop through pages?

Answer 1

URL-, paste0, . . URL, :

url <- paste0(url1,year,url2,page,url3) ## you change page or year or both

. do.call(rbind,..):

library(XML)
url1 <- "http://www.nfl.com/stats/categorystats?tabSeq=1&season="
year <- 2013
url2 <- "&seasonType=REG&experience=&Submit=Go&archive=false&conference=null&d-447263-p="
page <- 1
url3 <- "&statisticPositionCategory=DEFENSIVE_BACK&qualified=true"

getTable <- 
  function(page=1,year=2013){
    url <- paste0(url1,year,url2,page,url3)
    tab = readHTMLTable(url,header=FALSE) ## see comment !!
    tab$result
}
## this will merge all tables in a single big table
do.call(rbind,lapply(seq_len(8),getTable,year=2013))

, URL , xpath , . , .

getNext <- 
function(url=url_base){
  doc <- htmlParse(url)
  XPATH_NEXT = "//*[@class='linkNavigation floatRight']/*[contains(., 'next')]"
  next_page <- unique(xpathSApply(doc,XPATH_NEXT,xmlGetAttr,'href'))
  if(length(next_page)>0)
    paste0("http://www.nfl.com",next_page)
  else ''
}
## url_base is your first  url
res <- list()
while(TRUE){
  tab = readHTMLTable(url_base,header=FALSE)
  res <- rbind(res,tab$result)
  url_base <- getNext(url_base)
  if (nchar(url_base)==0)
    break
}